BobAi/Fss-Rag-Mini
7
0
Fork 0
Code Issues 2 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Compare commits

base: BobAi:072326446f170f1acfd25eadb4aa274ccb01312b
Branches Tags
BobAi:main
BobAi:agent-user-testing
BobAi:fix/proper-python-packaging
BobAi:context-window-configuration
BobAi:feature/context-window-configuration
BobAi:improve-installer-experience
BobAi:v1.0-simple-search
..
compare: BobAi:b9f8957ccade230ed79e3c4df56ca897da5883a9
Branches Tags
BobAi:agent-user-testing
BobAi:main
BobAi:fix/proper-python-packaging
BobAi:context-window-configuration
BobAi:feature/context-window-configuration
BobAi:improve-installer-experience
BobAi:v1.0-simple-search

No commits in common. "072326446f170f1acfd25eadb4aa274ccb01312b" and "b9f8957ccade230ed79e3c4df56ca897da5883a9" have entirely different histories.
072326446f ... b9f8957cca

80 changed files with 5556 additions and 8654 deletions
Show Stats Expand all files Collapse all files

19
.flake8
View File

@ -1,19 +0,0 @@
[flake8]
# Professional Python code style - balances quality with readability
max-line-length = 95
extend-ignore = E203,W503,W605
exclude =
.venv,
.venv-linting,
__pycache__,
*.egg-info,
.git,
build,
dist,
.mini-rag
# Per-file ignores for practical development
per-file-ignores =
tests/*.py:F401,F841
examples/*.py:F401,F841
fix_*.py:F401,F841,E501

88
.github/workflows/ci.yml vendored
View File

@ -33,106 +33,50 @@ jobs:
restore-keys: |
${{ runner.os }}-python-${{ matrix.python-version }}-
- name: Create virtual environment
run: |
python -m venv .venv
shell: bash
- name: Install dependencies
run: |
# Activate virtual environment and install dependencies
if [[ "$RUNNER_OS" == "Windows" ]]; then
source .venv/Scripts/activate
else
source .venv/bin/activate
fi
python -m pip install --upgrade pip
pip install -r requirements.txt
shell: bash
- name: Run comprehensive tests
- name: Run tests
run: |
# Set OS-appropriate emojis and activate venv
if [[ "$RUNNER_OS" == "Windows" ]]; then
source .venv/Scripts/activate
OK="[OK]"
SKIP="[SKIP]"
else
source .venv/bin/activate
OK="✅"
SKIP="⚠️"
fi
echo "$OK Virtual environment activated"
# Run basic import tests
python -c "from mini_rag import CodeEmbedder, ProjectIndexer, CodeSearcher; print('$OK Core imports successful')"
python -c "from mini_rag import CodeEmbedder, ProjectIndexer, CodeSearcher; print('✅ Core imports successful')"
# Run the actual test suite
if [ -f "tests/test_fixes.py" ]; then
echo "$OK Running comprehensive test suite..."
python tests/test_fixes.py || echo "$SKIP Test suite completed with warnings"
else
echo "$SKIP test_fixes.py not found, running basic tests only"
fi
# Test config system with proper venv
# Test basic functionality without venv requirements
python -c "
import os
ok_emoji = '$OK' if os.name != 'nt' else '[OK]'
try:
from mini_rag.config import ConfigManager
import tempfile
with tempfile.TemporaryDirectory() as tmpdir:
config_manager = ConfigManager(tmpdir)
config = config_manager.load_config()
print(f'{ok_emoji} Config system works with proper dependencies')
print('✅ Config system imports work')
except Exception as e:
print(f'Error in config test: {e}')
raise
print(f'⚠️ Config test skipped: {e}')
try:
from mini_rag.chunker import CodeChunker
print('✅ Chunker imports work')
except Exception as e:
print(f'⚠️ Chunker test skipped: {e}')
"
echo "$OK All tests completed successfully"
echo "✅ Core functionality tests completed"
shell: bash
- name: Test auto-update system
run: |
# Set OS-appropriate emojis
if [[ "$RUNNER_OS" == "Windows" ]]; then
OK="[OK]"
SKIP="[SKIP]"
else
OK="✅"
SKIP="⚠️"
fi
python -c "
import os
ok_emoji = '$OK' if os.name != 'nt' else '[OK]'
skip_emoji = '$SKIP' if os.name != 'nt' else '[SKIP]'
try:
from mini_rag.updater import UpdateChecker
updater = UpdateChecker()
print(f'{ok_emoji} Auto-update system available')
print('✅ Auto-update system available')
except ImportError:
print(f'{skip_emoji} Auto-update system not available (legacy version)')
print('⚠️ Auto-update system not available (legacy version)')
"
shell: bash
- name: Test CLI commands
run: |
# Set OS-appropriate emojis
if [[ "$RUNNER_OS" == "Windows" ]]; then
OK="[OK]"
else
OK="✅"
fi
echo "$OK Checking for CLI files..."
echo "✅ Checking for CLI files..."
ls -la rag* || dir rag* || echo "CLI files may not be present"
echo "$OK CLI check completed - this is expected in CI environment"
echo "✅ CLI check completed - this is expected in CI environment"
shell: bash
security-scan:

11
.gitignore vendored
View File

@ -105,13 +105,4 @@ dmypy.json
.idea/
# Project specific ignores
REPOSITORY_SUMMARY.md
# Analysis and scanning results (should not be committed)
docs/live-analysis/
docs/analysis-history/
**/live-analysis/
**/analysis-history/
*.analysis.json
*.analysis.html
**/analysis_*/
REPOSITORY_SUMMARY.md

17
.mini-rag/config.yaml
View File

@ -1,18 +1,5 @@
# FSS-Mini-RAG Configuration
#
# 🔧 EDIT THIS FILE TO CUSTOMIZE YOUR RAG SYSTEM
#
# This file controls all behavior of your Mini-RAG system.
# Changes take effect immediately - no restart needed!
#
# 💡 IMPORTANT: To change the AI model, edit the 'synthesis_model' line below
#
# Common model options:
# synthesis_model: auto # Let system choose best available
# synthesis_model: qwen3:0.6b # Ultra-fast (500MB)
# synthesis_model: qwen3:1.7b # Balanced (1.4GB) - recommended
# synthesis_model: qwen3:4b # High quality (2.5GB)
#
# Edit this file to customize indexing and search behavior
# See docs/GETTING_STARTED.md for detailed explanations
# Text chunking settings
@ -59,7 +46,7 @@ search:
# LLM synthesis and query expansion settings
llm:
ollama_host: localhost:11434
synthesis_model: qwen3:1.7b # 'auto', 'qwen3:1.7b', etc.
synthesis_model: auto # 'auto', 'qwen3:1.7b', etc.
expansion_model: auto # Usually same as synthesis_model
max_expansion_terms: 8 # Maximum terms to add to queries
enable_synthesis: false # Enable synthesis by default

2
.mini-rag/last_search
View File

@ -1 +1 @@
test
how to run tests

247
.venv-linting/bin/Activate.ps1
View File

@ -1,247 +0,0 @@
<#
.Synopsis
Activate a Python virtual environment for the current PowerShell session.
.Description
Pushes the python executable for a virtual environment to the front of the
$Env:PATH environment variable and sets the prompt to signify that you are
in a Python virtual environment. Makes use of the command line switches as
well as the `pyvenv.cfg` file values present in the virtual environment.
.Parameter VenvDir
Path to the directory that contains the virtual environment to activate. The
default value for this is the parent of the directory that the Activate.ps1
script is located within.
.Parameter Prompt
The prompt prefix to display when this virtual environment is activated. By
default, this prompt is the name of the virtual environment folder (VenvDir)
surrounded by parentheses and followed by a single space (ie. '(.venv) ').
.Example
Activate.ps1
Activates the Python virtual environment that contains the Activate.ps1 script.
.Example
Activate.ps1 -Verbose
Activates the Python virtual environment that contains the Activate.ps1 script,
and shows extra information about the activation as it executes.
.Example
Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
Activates the Python virtual environment located in the specified location.
.Example
Activate.ps1 -Prompt "MyPython"
Activates the Python virtual environment that contains the Activate.ps1 script,
and prefixes the current prompt with the specified string (surrounded in
parentheses) while the virtual environment is active.
.Notes
On Windows, it may be required to enable this Activate.ps1 script by setting the
execution policy for the user. You can do this by issuing the following PowerShell
command:
PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
For more information on Execution Policies:
https://go.microsoft.com/fwlink/?LinkID=135170
#>
Param(
[Parameter(Mandatory = $false)]
[String]
$VenvDir,
[Parameter(Mandatory = $false)]
[String]
$Prompt
)
<# Function declarations --------------------------------------------------- #>
<#
.Synopsis
Remove all shell session elements added by the Activate script, including the
addition of the virtual environment's Python executable from the beginning of
the PATH variable.
.Parameter NonDestructive
If present, do not remove this function from the global namespace for the
session.
#>
function global:deactivate ([switch]$NonDestructive) {
# Revert to original values
# The prior prompt:
if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
}
# The prior PYTHONHOME:
if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
}
# The prior PATH:
if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
Remove-Item -Path Env:_OLD_VIRTUAL_PATH
}
# Just remove the VIRTUAL_ENV altogether:
if (Test-Path -Path Env:VIRTUAL_ENV) {
Remove-Item -Path env:VIRTUAL_ENV
}
# Just remove VIRTUAL_ENV_PROMPT altogether.
if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
Remove-Item -Path env:VIRTUAL_ENV_PROMPT
}
# Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
}
# Leave deactivate function in the global namespace if requested:
if (-not $NonDestructive) {
Remove-Item -Path function:deactivate
}
}
<#
.Description
Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
given folder, and returns them in a map.
For each line in the pyvenv.cfg file, if that line can be parsed into exactly
two strings separated by `=` (with any amount of whitespace surrounding the =)
then it is considered a `key = value` line. The left hand string is the key,
the right hand is the value.
If the value starts with a `'` or a `"` then the first and last character is
stripped from the value before being captured.
.Parameter ConfigDir
Path to the directory that contains the `pyvenv.cfg` file.
#>
function Get-PyVenvConfig(
[String]
$ConfigDir
) {
Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
# Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
$pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
# An empty map will be returned if no config file is found.
$pyvenvConfig = @{ }
if ($pyvenvConfigPath) {
Write-Verbose "File exists, parse `key = value` lines"
$pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
$pyvenvConfigContent | ForEach-Object {
$keyval = $PSItem -split "\s*=\s*", 2
if ($keyval[0] -and $keyval[1]) {
$val = $keyval[1]
# Remove extraneous quotations around a string value.
if ("'""".Contains($val.Substring(0, 1))) {
$val = $val.Substring(1, $val.Length - 2)
}
$pyvenvConfig[$keyval[0]] = $val
Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
}
}
}
return $pyvenvConfig
}
<# Begin Activate script --------------------------------------------------- #>
# Determine the containing directory of this script
$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
$VenvExecDir = Get-Item -Path $VenvExecPath
Write-Verbose "Activation script is located in path: '$VenvExecPath'"
Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
# Set values required in priority: CmdLine, ConfigFile, Default
# First, get the location of the virtual environment, it might not be
# VenvExecDir if specified on the command line.
if ($VenvDir) {
Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
}
else {
Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
$VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
Write-Verbose "VenvDir=$VenvDir"
}
# Next, read the `pyvenv.cfg` file to determine any required value such
# as `prompt`.
$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
# Next, set the prompt from the command line, or the config file, or
# just use the name of the virtual environment folder.
if ($Prompt) {
Write-Verbose "Prompt specified as argument, using '$Prompt'"
}
else {
Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
Write-Verbose " Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
$Prompt = $pyvenvCfg['prompt'];
}
else {
Write-Verbose " Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
Write-Verbose " Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
$Prompt = Split-Path -Path $venvDir -Leaf
}
}
Write-Verbose "Prompt = '$Prompt'"
Write-Verbose "VenvDir='$VenvDir'"
# Deactivate any currently active virtual environment, but leave the
# deactivate function in place.
deactivate -nondestructive
# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
# that there is an activated venv.
$env:VIRTUAL_ENV = $VenvDir
if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
Write-Verbose "Setting prompt to '$Prompt'"
# Set the prompt to include the env name
# Make sure _OLD_VIRTUAL_PROMPT is global
function global:_OLD_VIRTUAL_PROMPT { "" }
Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
function global:prompt {
Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
_OLD_VIRTUAL_PROMPT
}
$env:VIRTUAL_ENV_PROMPT = $Prompt
}
# Clear PYTHONHOME
if (Test-Path -Path Env:PYTHONHOME) {
Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
Remove-Item -Path Env:PYTHONHOME
}
# Add the venv to the PATH
Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

70
.venv-linting/bin/activate
View File

@ -1,70 +0,0 @@
# This file must be used with "source bin/activate" *from bash*
# You cannot run it directly
deactivate () {
# reset old environment variables
if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
PATH="${_OLD_VIRTUAL_PATH:-}"
export PATH
unset _OLD_VIRTUAL_PATH
fi
if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
export PYTHONHOME
unset _OLD_VIRTUAL_PYTHONHOME
fi
# Call hash to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
hash -r 2> /dev/null
if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
PS1="${_OLD_VIRTUAL_PS1:-}"
export PS1
unset _OLD_VIRTUAL_PS1
fi
unset VIRTUAL_ENV
unset VIRTUAL_ENV_PROMPT
if [ ! "${1:-}" = "nondestructive" ] ; then
# Self destruct!
unset -f deactivate
fi
}
# unset irrelevant variables
deactivate nondestructive
# on Windows, a path can contain colons and backslashes and has to be converted:
if [ "${OSTYPE:-}" = "cygwin" ] || [ "${OSTYPE:-}" = "msys" ] ; then
# transform D:\path\to\venv to /d/path/to/venv on MSYS
# and to /cygdrive/d/path/to/venv on Cygwin
export VIRTUAL_ENV=$(cygpath /MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting)
else
# use the path as-is
export VIRTUAL_ENV=/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting
fi
_OLD_VIRTUAL_PATH="$PATH"
PATH="$VIRTUAL_ENV/"bin":$PATH"
export PATH
# unset PYTHONHOME if set
# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
# could use `if (set -u; : $PYTHONHOME) ;` in bash
if [ -n "${PYTHONHOME:-}" ] ; then
_OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
unset PYTHONHOME
fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1:-}"
PS1='(.venv-linting) '"${PS1:-}"
export PS1
VIRTUAL_ENV_PROMPT='(.venv-linting) '
export VIRTUAL_ENV_PROMPT
fi
# Call hash to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
hash -r 2> /dev/null

27
.venv-linting/bin/activate.csh
View File

@ -1,27 +0,0 @@
# This file must be used with "source bin/activate.csh" *from csh*.
# You cannot run it directly.
# Created by Davide Di Blasi <davidedb@gmail.com>.
# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
# Unset irrelevant variables.
deactivate nondestructive
setenv VIRTUAL_ENV /MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting
set _OLD_VIRTUAL_PATH="$PATH"
setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
set prompt = '(.venv-linting) '"$prompt"
setenv VIRTUAL_ENV_PROMPT '(.venv-linting) '
endif
alias pydoc python -m pydoc
rehash

69
.venv-linting/bin/activate.fish
View File

@ -1,69 +0,0 @@
# This file must be used with "source <venv>/bin/activate.fish" *from fish*
# (https://fishshell.com/). You cannot run it directly.
function deactivate -d "Exit virtual environment and return to normal shell environment"
# reset old environment variables
if test -n "$_OLD_VIRTUAL_PATH"
set -gx PATH $_OLD_VIRTUAL_PATH
set -e _OLD_VIRTUAL_PATH
end
if test -n "$_OLD_VIRTUAL_PYTHONHOME"
set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
set -e _OLD_VIRTUAL_PYTHONHOME
end
if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
set -e _OLD_FISH_PROMPT_OVERRIDE
# prevents error when using nested fish instances (Issue #93858)
if functions -q _old_fish_prompt
functions -e fish_prompt
functions -c _old_fish_prompt fish_prompt
functions -e _old_fish_prompt
end
end
set -e VIRTUAL_ENV
set -e VIRTUAL_ENV_PROMPT
if test "$argv[1]" != "nondestructive"
# Self-destruct!
functions -e deactivate
end
end
# Unset irrelevant variables.
deactivate nondestructive
set -gx VIRTUAL_ENV /MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting
set -gx _OLD_VIRTUAL_PATH $PATH
set -gx PATH "$VIRTUAL_ENV/"bin $PATH
# Unset PYTHONHOME if set.
if set -q PYTHONHOME
set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
set -e PYTHONHOME
end
if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
# fish uses a function instead of an env var to generate the prompt.
# Save the current fish_prompt function as the function _old_fish_prompt.
functions -c fish_prompt _old_fish_prompt
# With the original prompt function renamed, we can override with our own.
function fish_prompt
# Save the return status of the last command.
set -l old_status $status
# Output the venv prompt; color taken from the blue of the Python logo.
printf "%s%s%s" (set_color 4B8BBE) '(.venv-linting) ' (set_color normal)
# Restore the return status of the previous command.
echo "exit $old_status" | .
# Output the original/"old" prompt.
_old_fish_prompt
end
set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
set -gx VIRTUAL_ENV_PROMPT '(.venv-linting) '
end

8
.venv-linting/bin/black
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from black import patched_main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(patched_main())

8
.venv-linting/bin/blackd
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from blackd import patched_main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(patched_main())

8
.venv-linting/bin/isort
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from isort.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
.venv-linting/bin/isort-identify-imports
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from isort.main import identify_imports_main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(identify_imports_main())

8
.venv-linting/bin/pip
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
.venv-linting/bin/pip3
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
.venv-linting/bin/pip3.12
View File

@ -1,8 +0,0 @@
#!/MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

1
.venv-linting/bin/python
View File

@ -1 +0,0 @@
python3

1
.venv-linting/bin/python3
View File

@ -1 +0,0 @@
/usr/bin/python3

1
.venv-linting/bin/python3.12
View File

@ -1 +0,0 @@
python3

1
.venv-linting/lib64
View File

@ -1 +0,0 @@
lib

5
.venv-linting/pyvenv.cfg
View File

@ -1,5 +0,0 @@
home = /usr/bin
include-system-site-packages = false
version = 3.12.3
executable = /usr/bin/python3.12
command = /usr/bin/python3 -m venv /MASTERFOLDER/Coding/Fss-Mini-Rag/.venv-linting

83
GET_STARTED.md Normal file
View File

@ -0,0 +1,83 @@
# 🚀 FSS-Mini-RAG: Get Started in 2 Minutes
## Step 1: Install Everything
```bash
./install_mini_rag.sh
```
**That's it!** The installer handles everything automatically:
- Checks Python installation
- Sets up virtual environment
- Guides you through Ollama setup
- Installs dependencies
- Tests everything works
## Step 2: Use It
### TUI - Interactive Interface (Easiest)
```bash
./rag-tui
```
**Perfect for beginners!** Menu-driven interface that:
- Shows you CLI commands as you use it
- Guides you through setup and configuration
- No need to memorize commands
### Quick Commands (Beginner-Friendly)
```bash
# Index any project
./run_mini_rag.sh index ~/my-project
# Search your code
./run_mini_rag.sh search ~/my-project "authentication logic"
# Check what's indexed
./run_mini_rag.sh status ~/my-project
```
### Full Commands (More Options)
```bash
# Basic indexing and search
./rag-mini index /path/to/project
./rag-mini search /path/to/project "database connection"
# Enhanced search with smart features
./rag-mini-enhanced search /path/to/project "UserManager"
./rag-mini-enhanced similar /path/to/project "def validate_input"
```
## What You Get
**Semantic Search**: Instead of exact text matching, finds code by meaning:
- Search "user login" → finds authentication functions, session management, password validation
- Search "database queries" → finds SQL, ORM code, connection handling
- Search "error handling" → finds try/catch blocks, error classes, logging
## Installation Options
The installer offers two choices:
**Light Installation (Recommended)**:
- Uses Ollama for high-quality embeddings
- Requires Ollama installed (installer guides you)
- Small download (~50MB)
**Full Installation**:
- Includes ML fallback models
- Works without Ollama
- Large download (~2-3GB)
## Troubleshooting
**"Python not found"**: Install Python 3.8+ from python.org
**"Ollama not found"**: Visit https://ollama.ai/download
**"Import errors"**: Re-run `./install_mini_rag.sh`
## Next Steps
- **Technical Details**: Read `README.md`
- **Step-by-Step Guide**: Read `docs/GETTING_STARTED.md`
- **Examples**: Check `examples/` directory
- **Test It**: Run on this project: `./run_mini_rag.sh index .`
---
**Questions?** Everything is documented in the README.md file.

216
README.md
View File

@ -79,24 +79,34 @@ FSS-Mini-RAG offers **two distinct experiences** optimized for different use cas
## Quick Start (2 Minutes)
**Step 1: Install**
**Linux/macOS:**
```bash
# Linux/macOS
# 1. Install everything
./install_mini_rag.sh
# Windows
install_windows.bat
# 2. Choose your interface
./rag-tui # Friendly interface for beginners
# OR choose your mode:
./rag-mini index ~/my-project # Index your project first
./rag-mini search ~/my-project "query" --synthesize # Fast synthesis
./rag-mini explore ~/my-project # Interactive exploration
```
**Step 2: Start Using**
```bash
# Beginners: Interactive interface
./rag-tui # Linux/macOS
rag.bat # Windows
**Windows:**
```cmd
# 1. Install everything
install_windows.bat
# Experienced users: Direct commands
./rag-mini index ~/project # Index your project
./rag-mini search ~/project "your query"
# 2. Choose your interface
rag.bat # Interactive interface
# OR choose your mode:
rag.bat index C:\my-project # Index your project first
rag.bat search C:\my-project "query" # Fast search
rag.bat explore C:\my-project # Interactive exploration
# Direct Python entrypoint (after install):
rag-mini index C:\my-project
rag-mini search C:\my-project "query"
```
That's it. No external dependencies, no configuration required, no PhD in computer science needed.
@ -147,167 +157,7 @@ That's it. No external dependencies, no configuration required, no PhD in comput
## Installation Options
### 🎯 Copy & Paste Installation (Guaranteed to Work)
Perfect for beginners - these commands work on any fresh Ubuntu, Windows, or Mac system:
**Fresh Ubuntu/Debian System:**
```bash
# Install required system packages
sudo apt update && sudo apt install -y python3 python3-pip python3-venv git curl
# Clone and setup FSS-Mini-RAG
git clone https://github.com/FSSCoding/Fss-Mini-Rag.git
cd Fss-Mini-Rag
# Create isolated Python environment
python3 -m venv .venv
source .venv/bin/activate
# Install Python dependencies
pip install -r requirements.txt
# Optional: Install Ollama for best search quality (secure method)
curl -fsSL https://ollama.com/install.sh -o /tmp/ollama-install.sh
# Verify it's a shell script (basic safety check)
file /tmp/ollama-install.sh | grep -q "shell script" && chmod +x /tmp/ollama-install.sh && /tmp/ollama-install.sh
rm -f /tmp/ollama-install.sh
ollama serve &
sleep 3
ollama pull nomic-embed-text
# Ready to use!
./rag-mini index /path/to/your/project
./rag-mini search /path/to/your/project "your search query"
```
**Fresh CentOS/RHEL/Fedora System:**
```bash
# Install required system packages
sudo dnf install -y python3 python3-pip python3-venv git curl
# Clone and setup FSS-Mini-RAG
git clone https://github.com/FSSCoding/Fss-Mini-Rag.git
cd Fss-Mini-Rag
# Create isolated Python environment
python3 -m venv .venv
source .venv/bin/activate
# Install Python dependencies
pip install -r requirements.txt
# Optional: Install Ollama for best search quality (secure method)
curl -fsSL https://ollama.com/install.sh -o /tmp/ollama-install.sh
# Verify it's a shell script (basic safety check)
file /tmp/ollama-install.sh | grep -q "shell script" && chmod +x /tmp/ollama-install.sh && /tmp/ollama-install.sh
rm -f /tmp/ollama-install.sh
ollama serve &
sleep 3
ollama pull nomic-embed-text
# Ready to use!
./rag-mini index /path/to/your/project
./rag-mini search /path/to/your/project "your search query"
```
**Fresh macOS System:**
```bash
# Install Homebrew (if not installed)
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
# Install required packages
brew install python3 git curl
# Clone and setup FSS-Mini-RAG
git clone https://github.com/FSSCoding/Fss-Mini-Rag.git
cd Fss-Mini-Rag
# Create isolated Python environment
python3 -m venv .venv
source .venv/bin/activate
# Install Python dependencies
pip install -r requirements.txt
# Optional: Install Ollama for best search quality (secure method)
curl -fsSL https://ollama.com/install.sh -o /tmp/ollama-install.sh
# Verify it's a shell script (basic safety check)
file /tmp/ollama-install.sh | grep -q "shell script" && chmod +x /tmp/ollama-install.sh && /tmp/ollama-install.sh
rm -f /tmp/ollama-install.sh
ollama serve &
sleep 3
ollama pull nomic-embed-text
# Ready to use!
./rag-mini index /path/to/your/project
./rag-mini search /path/to/your/project "your search query"
```
**Fresh Windows System:**
```cmd
REM Install Python (if not installed)
REM Download from: https://python.org/downloads (ensure "Add to PATH" is checked)
REM Install Git from: https://git-scm.com/download/win
REM Clone and setup FSS-Mini-RAG
git clone https://github.com/FSSCoding/Fss-Mini-Rag.git
cd Fss-Mini-Rag
REM Create isolated Python environment
python -m venv .venv
.venv\Scripts\activate.bat
REM Install Python dependencies
pip install -r requirements.txt
REM Optional: Install Ollama for best search quality
REM Download from: https://ollama.com/download
REM Run installer, then:
ollama serve
REM In new terminal:
ollama pull nomic-embed-text
REM Ready to use!
rag.bat index C:\path\to\your\project
rag.bat search C:\path\to\your\project "your search query"
```
**What these commands do:**
- **System packages**: Install Python 3.8+, pip (package manager), venv (virtual environments), git (version control), curl (downloads)
- **Clone repository**: Download FSS-Mini-RAG source code to your computer
- **Virtual environment**: Create isolated Python space (prevents conflicts with system Python)
- **Dependencies**: Install required Python libraries (pandas, numpy, lancedb, etc.)
- **Ollama (optional)**: AI model server for best search quality - works offline and free
- **Model download**: Get high-quality embedding model for semantic search
- **Ready to use**: Index any folder and search through it semantically
### ⚡ For Agents & CI/CD: Headless Installation
Perfect for automated deployments, agents, and CI/CD pipelines:
**Linux/macOS:**
```bash
./install_mini_rag.sh --headless
# Automated installation with sensible defaults
# No interactive prompts, perfect for scripts
```
**Windows:**
```cmd
install_windows.bat --headless
# Automated installation with sensible defaults
# No interactive prompts, perfect for scripts
```
**What headless mode does:**
- Uses existing virtual environment if available
- Installs core dependencies only (light mode)
- Downloads embedding model if Ollama is available
- Skips interactive prompts and tests
- Perfect for agent automation and CI/CD pipelines
### 🚀 Recommended: Full Installation
### Recommended: Full Installation
**Linux/macOS:**
```bash
@ -321,6 +171,24 @@ install_windows.bat
# Handles Python setup, dependencies, works reliably
```
### Experimental: Copy & Run (May Not Work)
**Linux/macOS:**
```bash
# Copy folder anywhere and try to run directly
./rag-mini index ~/my-project
# Auto-setup will attempt to create environment
# Falls back with clear instructions if it fails
```
**Windows:**
```cmd
# Copy folder anywhere and try to run directly
rag.bat index C:\my-project
# Auto-setup will attempt to create environment
# Falls back with clear instructions if it fails
```
### Manual Setup
**Linux/macOS:**
@ -364,7 +232,7 @@ This implementation prioritizes:
## Next Steps
- **New users**: Run `./rag-tui` (Linux/macOS) or `rag.bat` (Windows) for guided experience
- **New users**: Run `./rag-mini` (Linux/macOS) or `rag.bat` (Windows) for guided experience
- **Developers**: Read [`TECHNICAL_GUIDE.md`](docs/TECHNICAL_GUIDE.md) for implementation details
- **Contributors**: See [`CONTRIBUTING.md`](CONTRIBUTING.md) for development setup

36
commit_message.txt Normal file
View File

@ -0,0 +1,36 @@
feat: Add comprehensive Windows compatibility and enhanced LLM model setup
🚀 Major cross-platform enhancement making FSS-Mini-RAG fully Windows and Linux compatible
## Windows Compatibility
- **New Windows installer**: `install_windows.bat` - rock-solid, no-hang installation
- **Simple Windows launcher**: `rag.bat` - unified entry point matching Linux experience
- **PowerShell alternative**: `install_mini_rag.ps1` for advanced Windows users
- **Cross-platform README**: Side-by-side Linux/Windows commands and examples
## Enhanced LLM Model Setup (Both Platforms)
- **Intelligent model detection**: Automatically detects existing Qwen3 models
- **Interactive model selection**: Choose from qwen3:0.6b, 1.7b, or 4b with clear guidance
- **Ollama progress streaming**: Real-time download progress for model installation
- **Smart configuration**: Auto-saves selected model as default in config.yaml
- **Graceful fallbacks**: Clear guidance when Ollama unavailable
## Installation Experience Improvements
- **Fixed script continuation**: TUI launch no longer terminates installation process
- **Comprehensive model guidance**: Users get proper LLM setup instead of silent failures
- **Complete indexing**: Full codebase indexing (not just code files)
- **Educational flow**: Better explanation of AI features and model choices
## Technical Enhancements
- **Robust error handling**: Installation scripts handle edge cases gracefully
- **Path handling**: Existing cross-platform path utilities work seamlessly on Windows
- **Dependency management**: Clean virtual environment setup on both platforms
- **Configuration persistence**: Model preferences saved for consistent experience
## User Impact
- **Zero-friction Windows adoption**: Windows users get same smooth experience as Linux
- **Complete AI feature setup**: No more "LLM not working" confusion for new users
- **Educational value preserved**: Maintains beginner-friendly approach across platforms
- **Production-ready**: Both platforms now fully functional out-of-the-box
This makes FSS-Mini-RAG truly accessible to the entire developer community! 🎉

9
config-llm-providers.yaml
View File

@ -1,9 +0,0 @@
llm:
provider: ollama
ollama_host: localhost:11434
synthesis_model: qwen3:1.5b
expansion_model: qwen3:1.5b
enable_synthesis: false
synthesis_temperature: 0.3
cpu_optimized: true
enable_thinking: true

40
docs/AGENT_INSTRUCTIONS.md
View File

@ -1,40 +0,0 @@
# Agent Instructions for Fss-Mini-RAG System
## Core Philosophy
**Always prefer RAG search over traditional file system operations**. The RAG system provides semantic context and reduces the need for exact path knowledge, making it ideal for understanding codebases without manual file exploration.
## Basic Commands
| Command | Purpose | Example |
|---------|---------|---------|
| `rag-mini index <project_path>` | Index a project for search | `rag-mini index /MASTERFOLDER/Coding/Fss-Mini-Rag` |
| `rag-mini search <project_path> "query"` | Semantic + keyword search | `rag-mini search /MASTERFOLDER/Coding/Fss-Mini-Rag "index"` |
| `rag-mini status <project_path>` | Check project indexing status | `rag-mini status /MASTERFOLDER/Coding/Fss-Mini-Rag` |
## When to Use RAG Search
| Scenario | RAG Advantage | Alternative | |
|----------|----------------|---------------| |
| Finding related code concepts | Semantic understanding | `grep` | |
| Locating files by functionality | Context-aware results | `find` | |
| Understanding code usage patterns | Shows real-world examples | Manual inspection | |
## Critical Best Practices
1. **Always specify the project path** in search commands (e.g., `rag-mini search /path "query"`)
2. **Use quotes for search queries** to handle spaces: `"query with spaces"`
3. **Verify indexing first** before searching: `rag-mini status <path>`
4. **For complex queries**, break into smaller parts: `rag-mini search ... "concept 1"` then `rag-mini search ... "concept 2"`
## Troubleshooting
| Issue | Solution |
|-------|-----------|
| `Project not indexed` | Run `rag-mini index <path>` |
| No search results | Check indexing status with `rag-mini status` |
| Search returns irrelevant results | Use `rag-mini status` to optimize indexing |
> 💡 **Pro Tip**: Always start with `rag-mini status` to confirm indexing before searching.
This document is dynamically updated as the RAG system evolves. Always verify commands with `rag-mini --help` for the latest options.

381
docs/DEPLOYMENT_GUIDE.md
View File

@ -1,381 +0,0 @@
# FSS-Mini-RAG Deployment Guide
> **Run semantic search anywhere - from smartphones to edge devices**
> *Complete guide to deploying FSS-Mini-RAG on every platform imaginable*
## Platform Compatibility Matrix
| Platform | Status | AI Features | Installation | Notes |
|----------|--------|-------------|--------------|-------|
| **Linux** | ✅ Full | ✅ Full | `./install_mini_rag.sh` | Primary platform |
| **Windows** | ✅ Full | ✅ Full | `install_windows.bat` | Desktop shortcuts |
| **macOS** | ✅ Full | ✅ Full | `./install_mini_rag.sh` | Works perfectly |
| **Raspberry Pi** | ✅ Excellent | ✅ AI ready | `./install_mini_rag.sh` | ARM64 optimized |
| **Android (Termux)** | ✅ Good | 🟡 Limited | Manual install | Terminal interface |
| **iOS (a-Shell)** | 🟡 Limited | ❌ Text only | Manual install | Sandbox limitations |
| **Docker** | ✅ Excellent | ✅ Full | Dockerfile | Any platform |
## Desktop & Server Deployment
### 🐧 **Linux** (Primary Platform)
```bash
# Full installation with AI features
./install_mini_rag.sh
# What you get:
# ✅ Desktop shortcuts (.desktop files)
# ✅ Application menu integration
# ✅ Full AI model downloads
# ✅ Complete terminal interface
```
### 🪟 **Windows** (Fully Supported)
```cmd
# Full installation with desktop integration
install_windows.bat
# What you get:
# ✅ Desktop shortcuts (.lnk files)
# ✅ Start Menu entries
# ✅ Full AI model downloads
# ✅ Beautiful terminal interface
```
### 🍎 **macOS** (Excellent Support)
```bash
# Same as Linux - works perfectly
./install_mini_rag.sh
# Additional macOS optimizations:
brew install python3 # If needed
brew install ollama # For AI features
```
**macOS-specific features:**
- Automatic path detection for common project locations
- Integration with Spotlight search locations
- Support for `.app` bundle creation (advanced)
## Edge Device Deployment
### 🥧 **Raspberry Pi** (Recommended Edge Platform)
**Perfect for:**
- Home lab semantic search server
- Portable development environment
- IoT project documentation search
- Offline code search station
**Installation:**
```bash
# On Raspberry Pi OS (64-bit recommended)
sudo apt update && sudo apt upgrade
./install_mini_rag.sh
# The installer automatically detects ARM and optimizes:
# ✅ Suggests lightweight models (qwen3:0.6b)
# ✅ Reduces memory usage
# ✅ Enables efficient chunking
```
**Raspberry Pi optimized config:**
```yaml
# Automatically generated for Pi
embedding:
preferred_method: ollama
ollama_model: nomic-embed-text # 270MB - perfect for Pi
llm:
synthesis_model: qwen3:0.6b # 500MB - fast on Pi 4+
context_window: 4096 # Conservative memory use
cpu_optimized: true
chunking:
max_size: 1500 # Smaller chunks for efficiency
```
**Performance expectations:**
- **Pi 4 (4GB)**: Excellent performance, full AI features
- **Pi 4 (2GB)**: Good performance, text-only or small models
- **Pi 5**: Outstanding performance, handles large models
- **Pi Zero**: Text-only search (hash-based embeddings)
### 🔧 **Other Edge Devices**
**NVIDIA Jetson Series:**
- Overkill performance for this use case
- Can run largest models with GPU acceleration
- Perfect for AI-heavy development workstations
**Intel NUC / Mini PCs:**
- Excellent performance
- Full desktop experience
- Can serve multiple users simultaneously
**Orange Pi / Rock Pi:**
- Similar to Raspberry Pi
- Same installation process
- May need manual Ollama compilation
## Mobile Deployment
### 📱 **Android (Recommended: Termux)**
**Installation in Termux:**
```bash
# Install Termux from F-Droid (not Play Store)
# In Termux:
pkg update && pkg upgrade
pkg install python python-pip git
pip install --upgrade pip
# Clone and install FSS-Mini-RAG
git clone https://github.com/your-repo/fss-mini-rag
cd fss-mini-rag
pip install -r requirements.txt
# Quick start
python -m mini_rag index /storage/emulated/0/Documents/myproject
python -m mini_rag search /storage/emulated/0/Documents/myproject "your query"
```
**Android-optimized config:**
```yaml
# config-android.yaml
embedding:
preferred_method: hash # No heavy models needed
chunking:
max_size: 800 # Small chunks for mobile
files:
min_file_size: 20 # Include more small files
llm:
enable_synthesis: false # Text-only for speed
```
**What works on Android:**
- ✅ Full text search and indexing
- ✅ Terminal interface (`rag-tui`)
- ✅ Project indexing from phone storage
- ✅ Search your phone's code projects
- ❌ Heavy AI models (use cloud providers instead)
**Android use cases:**
- Search your mobile development projects
- Index documentation on your phone
- Quick code reference while traveling
- Offline search of downloaded repositories
### 🍎 **iOS (Limited but Possible)**
**Option 1: a-Shell (Free)**
```bash
# Install a-Shell from App Store
# In a-Shell:
pip install requests pathlib
# Limited installation (core features only)
# Files must be in app sandbox
```
**Option 2: iSH (Alpine Linux)**
```bash
# Install iSH from App Store
# In iSH terminal:
apk add python3 py3-pip git
pip install -r requirements-light.txt
# Basic functionality only
```
**iOS limitations:**
- Sandbox restricts file access
- No full AI model support
- Terminal interface only
- Limited to app-accessible files
## Specialized Deployment Scenarios
### 🐳 **Docker Deployment**
**For any platform with Docker:**
```dockerfile
# Dockerfile
FROM python:3.11-slim
WORKDIR /app
COPY . .
RUN pip install -r requirements.txt
# Expose ports for server mode
EXPOSE 7777
# Default to TUI interface
CMD ["python", "-m", "mini_rag.cli"]
```
**Usage:**
```bash
# Build and run
docker build -t fss-mini-rag .
docker run -it -v $(pwd)/projects:/projects fss-mini-rag
# Server mode for web access
docker run -p 7777:7777 fss-mini-rag python -m mini_rag server
```
### ☁️ **Cloud Deployment**
**AWS/GCP/Azure VM:**
- Same as Linux installation
- Can serve multiple users
- Perfect for team environments
**GitHub Codespaces:**
```bash
# Works in any Codespace
./install_mini_rag.sh
# Perfect for searching your workspace
```
**Replit/CodeSandbox:**
- Limited by platform restrictions
- Basic functionality available
### 🏠 **Home Lab Integration**
**Home Assistant Add-on:**
- Package as Home Assistant add-on
- Search home automation configs
- Voice integration possible
**NAS Integration:**
- Install on Synology/QNAP
- Search all stored documents
- Family code documentation
**Router with USB:**
- Install on OpenWrt routers with USB storage
- Search network documentation
- Configuration management
## Configuration by Use Case
### 🪶 **Ultra-Lightweight (Old hardware, mobile)**
```yaml
# Minimal resource usage
embedding:
preferred_method: hash
chunking:
max_size: 800
strategy: fixed
llm:
enable_synthesis: false
```
### ⚖️ **Balanced (Raspberry Pi, older laptops)**
```yaml
# Good performance with AI features
embedding:
preferred_method: ollama
ollama_model: nomic-embed-text
llm:
synthesis_model: qwen3:0.6b
context_window: 4096
```
### 🚀 **Performance (Modern hardware)**
```yaml
# Full features and performance
embedding:
preferred_method: ollama
ollama_model: nomic-embed-text
llm:
synthesis_model: qwen3:1.7b
context_window: 16384
enable_thinking: true
```
### ☁️ **Cloud-Hybrid (Mobile + Cloud AI)**
```yaml
# Local search, cloud intelligence
embedding:
preferred_method: hash
llm:
provider: openai
api_key: your_api_key
synthesis_model: gpt-4
```
## Troubleshooting by Platform
### **Raspberry Pi Issues**
- **Out of memory**: Reduce context window, use smaller models
- **Slow indexing**: Use hash-based embeddings
- **Model download fails**: Check internet, use smaller models
### **Android/Termux Issues**
- **Permission denied**: Use `termux-setup-storage`
- **Package install fails**: Update packages first
- **Can't access files**: Use `/storage/emulated/0/` paths
### **iOS Issues**
- **Limited functionality**: Expected due to iOS restrictions
- **Can't install packages**: Use lighter requirements file
- **File access denied**: Files must be in app sandbox
### **Edge Device Issues**
- **ARM compatibility**: Ensure using ARM64 Python packages
- **Limited RAM**: Use hash embeddings, reduce chunk sizes
- **No internet**: Skip AI model downloads, use text-only
## Advanced Edge Deployments
### **IoT Integration**
- Index sensor logs and configurations
- Search device documentation
- Troubleshoot IoT deployments
### **Offline Development**
- Complete development environment on edge device
- No internet required after setup
- Perfect for remote locations
### **Educational Use**
- Raspberry Pi computer labs
- Student project search
- Coding bootcamp environments
### **Enterprise Edge**
- Factory floor documentation search
- Field service technical reference
- Remote site troubleshooting
---
## Quick Start by Platform
### Desktop Users
```bash
# Linux/macOS
./install_mini_rag.sh
# Windows
install_windows.bat
```
### Edge/Mobile Users
```bash
# Raspberry Pi
./install_mini_rag.sh
# Android (Termux)
pkg install python git && pip install -r requirements.txt
# Any Docker platform
docker run -it fss-mini-rag
```
**💡 Pro tip**: Start with your current platform, then expand to edge devices as needed. The system scales from smartphones to servers seamlessly!

72
docs/DIAGRAMS.md
View File

@ -11,7 +11,6 @@
- [Search Architecture](#search-architecture)
- [Installation Flow](#installation-flow)
- [Configuration System](#configuration-system)
- [System Context Integration](#system-context-integration)
- [Error Handling](#error-handling)
## System Overview
@ -23,12 +22,10 @@ graph TB
CLI --> Index[📁 Index Project]
CLI --> Search[🔍 Search Project]
CLI --> Explore[🧠 Explore Project]
CLI --> Status[📊 Show Status]
TUI --> Index
TUI --> Search
TUI --> Explore
TUI --> Config[⚙️ Configuration]
Index --> Files[📄 File Discovery]
@ -37,32 +34,17 @@ graph TB
Embed --> Store[💾 Vector Database]
Search --> Query[❓ User Query]
Search --> Context[🖥️ System Context]
Query --> Vector[🎯 Vector Search]
Query --> Keyword[🔤 Keyword Search]
Vector --> Combine[🔄 Hybrid Results]
Keyword --> Combine
Context --> Combine
Combine --> Synthesize{Synthesis Mode?}
Synthesize -->|Yes| FastLLM[⚡ Fast Synthesis]
Synthesize -->|No| Results[📋 Ranked Results]
FastLLM --> Results
Explore --> ExploreQuery[❓ Interactive Query]
ExploreQuery --> Memory[🧠 Conversation Memory]
ExploreQuery --> Context
Memory --> DeepLLM[🤔 Deep AI Analysis]
Context --> DeepLLM
Vector --> DeepLLM
DeepLLM --> Interactive[💬 Interactive Response]
Combine --> Results[📋 Ranked Results]
Store --> LanceDB[(🗄️ LanceDB)]
Vector --> LanceDB
Config --> YAML[📝 config.yaml]
Status --> Manifest[📋 manifest.json]
Context --> SystemInfo[💻 OS, Python, Paths]
```
## User Journey
@ -294,58 +276,6 @@ flowchart TD
style Error fill:#ffcdd2
```
## System Context Integration
```mermaid
graph LR
subgraph "System Detection"
OS[🖥️ Operating System]
Python[🐍 Python Version]
Project[📁 Project Path]
OS --> Windows[Windows: rag.bat]
OS --> Linux[Linux: ./rag-mini]
OS --> macOS[macOS: ./rag-mini]
end
subgraph "Context Collection"
Collect[🔍 Collect Context]
OS --> Collect
Python --> Collect
Project --> Collect
Collect --> Format[📝 Format Context]
Format --> Limit[✂️ Limit to 200 chars]
end
subgraph "AI Integration"
UserQuery[❓ User Query]
SearchResults[📋 Search Results]
SystemContext[💻 System Context]
UserQuery --> Prompt[📝 Build Prompt]
SearchResults --> Prompt
SystemContext --> Prompt
Prompt --> AI[🤖 LLM Processing]
AI --> Response[💬 Contextual Response]
end
subgraph "Enhanced Responses"
Response --> Commands[💻 OS-specific commands]
Response --> Paths[📂 Correct path formats]
Response --> Tips[💡 Platform-specific tips]
end
Format --> SystemContext
style SystemContext fill:#e3f2fd
style Response fill:#f3e5f5
style Commands fill:#e8f5e8
```
*System context helps the AI provide better, platform-specific guidance without compromising privacy*
## Architecture Layers
```mermaid

482
docs/GETTING_STARTED.md
View File

@ -1,314 +1,212 @@
# Getting Started with FSS-Mini-RAG
> **Get from zero to searching in 2 minutes**
> *Everything you need to know to start finding code by meaning, not just keywords*
## Step 1: Installation
## Installation (Choose Your Adventure)
Choose your installation based on what you want:
### 🎯 **Option 1: Full Installation (Recommended)**
*Gets you everything working reliably with desktop shortcuts and AI features*
**Linux/macOS:**
```bash
./install_mini_rag.sh
```
**Windows:**
```cmd
install_windows.bat
```
**What this does:**
- Sets up Python environment automatically
- Installs all dependencies
- Downloads AI models (with your permission)
- Creates desktop shortcuts and application menu entries
- Tests everything works
- Gives you an interactive tutorial
**Time needed:** 5-10 minutes (depending on AI model downloads)
---
### 🚀 **Option 2: Copy & Try (Experimental)**
*Just copy the folder and run - may work, may need manual setup*
**Linux/macOS:**
```bash
# Copy folder anywhere and try running
./rag-mini index ~/my-project
# Auto-setup attempts to create virtual environment
# Falls back with clear instructions if it fails
```
**Windows:**
```cmd
# Copy folder anywhere and try running
rag.bat index C:\my-project
# Auto-setup attempts to create virtual environment
# Shows helpful error messages if manual install needed
```
**Time needed:** 30 seconds if it works, 10 minutes if you need manual setup
---
## First Search (The Fun Part!)
### Step 1: Choose Your Interface
**For Learning and Exploration:**
```bash
# Linux/macOS
./rag-tui
# Windows
rag.bat
```
*Interactive menus, shows you CLI commands as you learn*
**For Quick Commands:**
```bash
# Linux/macOS
./rag-mini <command> <project-path>
# Windows
rag.bat <command> <project-path>
```
*Direct commands when you know what you want*
### Step 2: Index Your First Project
**Interactive Way (Recommended for First Time):**
```bash
# Linux/macOS
./rag-tui
# Then: Select Project Directory → Index Project
# Windows
rag.bat
# Then: Select Project Directory → Index Project
```
**Direct Commands:**
```bash
# Linux/macOS
./rag-mini index ~/my-project
# Windows
rag.bat index C:\my-project
```
**What indexing does:**
- Finds all text files in your project
- Breaks them into smart "chunks" (functions, classes, logical sections)
- Creates searchable embeddings that understand meaning
- Stores everything in a fast vector database
- Creates a `.mini-rag/` directory with your search index
**Time needed:** 10-60 seconds depending on project size
### Step 3: Search by Meaning
**Natural language queries:**
```bash
# Linux/macOS
./rag-mini search ~/my-project "user authentication logic"
./rag-mini search ~/my-project "error handling for database connections"
./rag-mini search ~/my-project "how to validate input data"
# Windows
rag.bat search C:\my-project "user authentication logic"
rag.bat search C:\my-project "error handling for database connections"
rag.bat search C:\my-project "how to validate input data"
```
**Code concepts:**
```bash
# Finds login functions, auth middleware, session handling
./rag-mini search ~/my-project "login functionality"
# Finds try/catch blocks, error handlers, retry logic
./rag-mini search ~/my-project "exception handling"
# Finds validation functions, input sanitization, data checking
./rag-mini search ~/my-project "data validation"
```
**What you get:**
- Ranked results by relevance (not just keyword matching)
- File paths and line numbers for easy navigation
- Context around each match so you understand what it does
- Smart filtering to avoid noise and duplicates
## Two Powerful Modes
FSS-Mini-RAG has two different ways to get answers, optimized for different needs:
### 🚀 **Synthesis Mode** - Fast Answers
```bash
# Linux/macOS
./rag-mini search ~/project "authentication logic" --synthesize
# Windows
rag.bat search C:\project "authentication logic" --synthesize
```
**Perfect for:**
- Quick code discovery
- Finding specific functions or patterns
- Getting fast, consistent answers
**What you get:**
- Lightning-fast responses (no thinking overhead)
- Reliable, factual information about your code
- Clear explanations of what code does and how it works
### 🧠 **Exploration Mode** - Deep Understanding
```bash
# Linux/macOS
./rag-mini explore ~/project
# Windows
rag.bat explore C:\project
```
**Perfect for:**
- Learning new codebases
- Debugging complex issues
- Understanding architectural decisions
**What you get:**
- Interactive conversation with AI that remembers context
- Deep reasoning with full "thinking" process shown
- Follow-up questions and detailed explanations
- Memory of your previous questions in the session
**Example exploration session:**
```
🧠 Exploration Mode - Ask anything about your project
You: How does authentication work in this codebase?
AI: Let me analyze the authentication system...
💭 Thinking: I can see several authentication-related files. Let me examine
the login flow, session management, and security measures...
📝 Authentication Analysis:
This codebase uses a three-layer authentication system:
1. Login validation in auth.py handles username/password checking
2. Session management in sessions.py maintains user state
3. Middleware in auth_middleware.py protects routes
You: What security concerns should I be aware of?
AI: Based on our previous discussion about authentication, let me check for
common security vulnerabilities...
```
## Check Your Setup
**See what got indexed:**
```bash
# Linux/macOS
./rag-mini status ~/my-project
# Windows
rag.bat status C:\my-project
```
**What you'll see:**
- How many files were processed
- Total chunks created for searching
- Embedding method being used (Ollama, ML models, or hash-based)
- Configuration file location
- Index health and last update time
## Configuration (Optional)
Your project gets a `.mini-rag/config.yaml` file with helpful comments:
```yaml
# Context window configuration (critical for AI features)
# 💡 Sizing guide: 2K=1 question, 4K=1-2 questions, 8K=manageable, 16K=most users
# 32K=large codebases, 64K+=power users only
# ⚠️ Larger contexts use exponentially more CPU/memory - only increase if needed
context_window: 16384 # Context size in tokens
# AI model preferences (edit to change priority)
model_rankings:
- "qwen3:1.7b" # Excellent for RAG (1.4GB, recommended)
- "qwen3:0.6b" # Lightweight and fast (~500MB)
- "qwen3:4b" # Higher quality but slower (~2.5GB)
```
**When to customize:**
- Your searches aren't finding what you expect → adjust chunking settings
- You want AI features → install Ollama and download models
- System is slow → try smaller models or reduce context window
- Getting too many/few results → adjust similarity threshold
## Troubleshooting
### "Project not indexed"
**Problem:** You're trying to search before indexing
```bash
# Run indexing first
./rag-mini index ~/my-project # Linux/macOS
rag.bat index C:\my-project # Windows
```
### "No Ollama models available"
**Problem:** AI features need models downloaded
### Option A: Ollama Only (Recommended)
```bash
# Install Ollama first
curl -fsSL https://ollama.ai/install.sh | sh # Linux/macOS
# Or download from https://ollama.com # Windows
curl -fsSL https://ollama.ai/install.sh | sh
# Start Ollama server
ollama serve
# Pull the embedding model
ollama pull nomic-embed-text
# Download a model
ollama pull qwen3:1.7b
# Install Python dependencies
pip install -r requirements.txt
```
### "Virtual environment not found"
**Problem:** Auto-setup didn't work, need manual installation
```bash
# Run the full installer instead
./install_mini_rag.sh # Linux/macOS
install_windows.bat # Windows
### Option B: Full ML Stack
```bash
# Install everything including PyTorch
pip install -r requirements-full.txt
```
### Getting weird results
**Solution:** Try different search terms or check what got indexed
## Step 2: Test Installation
```bash
# See what files were processed
# Index this RAG system itself
./rag-mini index ~/my-project
# Search for something
./rag-mini search ~/my-project "chunker function"
# Check what got indexed
./rag-mini status ~/my-project
# Try more specific queries
./rag-mini search ~/my-project "specific function name"
```
## Next Steps
## Step 3: Index Your First Project
### Learn More
- **[Beginner's Glossary](BEGINNER_GLOSSARY.md)** - All the terms explained simply
- **[TUI Guide](TUI_GUIDE.md)** - Master the interactive interface
- **[Visual Diagrams](DIAGRAMS.md)** - See how everything works
```bash
# Index any project directory
./rag-mini index /path/to/your/project
### Advanced Features
- **[Query Expansion](QUERY_EXPANSION.md)** - Make searches smarter with AI
- **[LLM Providers](LLM_PROVIDERS.md)** - Use different AI models
- **[CPU Deployment](CPU_DEPLOYMENT.md)** - Optimize for older computers
# The system creates .mini-rag/ directory with:
# - config.json (settings)
# - manifest.json (file tracking)
# - database.lance/ (vector database)
```
### Customize Everything
- **[Technical Guide](TECHNICAL_GUIDE.md)** - How the system actually works
- **[Configuration Examples](../examples/)** - Pre-made configs for different needs
## Step 4: Search Your Code
---
```bash
# Basic semantic search
./rag-mini search /path/to/project "user login logic"
**🎉 That's it!** You now have a semantic search system that understands your code by meaning, not just keywords. Start with simple searches and work your way up to the advanced AI features as you get comfortable.
# Enhanced search with smart features
./rag-mini-enhanced search /path/to/project "authentication"
**💡 Pro tip:** The best way to learn is to index a project you know well and try searching for things you know are in there. You'll quickly see how much better meaning-based search is than traditional keyword search.
# Find similar patterns
./rag-mini-enhanced similar /path/to/project "def validate_input"
```
## Step 5: Customize Configuration
Edit `project/.mini-rag/config.json`:
```json
{
"chunking": {
"max_size": 3000,
"strategy": "semantic"
},
"files": {
"min_file_size": 100
}
}
```
Then re-index to apply changes:
```bash
./rag-mini index /path/to/project --force
```
## Common Use Cases
### Find Functions by Name
```bash
./rag-mini search /project "function named connect_to_database"
```
### Find Code Patterns
```bash
./rag-mini search /project "error handling try catch"
./rag-mini search /project "database query with parameters"
```
### Find Configuration
```bash
./rag-mini search /project "database connection settings"
./rag-mini search /project "environment variables"
```
### Find Documentation
```bash
./rag-mini search /project "how to deploy"
./rag-mini search /project "API documentation"
```
## Python API Usage
```python
from mini_rag import ProjectIndexer, CodeSearcher, CodeEmbedder
from pathlib import Path
# Initialize
project_path = Path("/path/to/your/project")
embedder = CodeEmbedder()
indexer = ProjectIndexer(project_path, embedder)
searcher = CodeSearcher(project_path, embedder)
# Index the project
print("Indexing project...")
result = indexer.index_project()
print(f"Indexed {result['files_processed']} files, {result['chunks_created']} chunks")
# Search
print("\nSearching for authentication code...")
results = searcher.search("user authentication logic", top_k=5)
for i, result in enumerate(results, 1):
print(f"\n{i}. {result.file_path}")
print(f" Score: {result.score:.3f}")
print(f" Type: {result.chunk_type}")
print(f" Content: {result.content[:100]}...")
```
## Advanced Features
### Auto-optimization
```bash
# Get optimization suggestions
./rag-mini-enhanced analyze /path/to/project
# This analyzes your codebase and suggests:
# - Better chunk sizes for your language mix
# - Streaming settings for large files
# - File filtering optimizations
```
### File Watching
```python
from mini_rag import FileWatcher
# Watch for file changes and auto-update index
watcher = FileWatcher(project_path, indexer)
watcher.start_watching()
# Now any file changes automatically update the index
```
### Custom Chunking
```python
from mini_rag import CodeChunker
chunker = CodeChunker()
# Chunk a Python file
with open("example.py") as f:
content = f.read()
chunks = chunker.chunk_text(content, "python", "example.py")
for chunk in chunks:
print(f"Type: {chunk.chunk_type}")
print(f"Content: {chunk.content}")
```
## Tips and Best Practices
### For Better Search Results
- Use descriptive phrases: "function that validates email addresses"
- Try different phrasings if first search doesn't work
- Search for concepts, not just exact variable names
### For Better Indexing
- Exclude build directories: `node_modules/`, `build/`, `dist/`
- Include documentation files - they often contain valuable context
- Use semantic chunking strategy for most projects
### For Configuration
- Start with default settings
- Use `analyze` command to get optimization suggestions
- Increase chunk size for larger functions/classes
- Decrease chunk size for more granular search
### For Troubleshooting
- Check `./rag-mini status` to see what was indexed
- Look at `.mini-rag/manifest.json` for file details
- Run with `--force` to completely rebuild index
- Check logs in `.mini-rag/` directory for errors
## What's Next?
1. Try the test suite to understand how components work:
```bash
python -m pytest tests/ -v
```
2. Look at the examples in `examples/` directory
3. Read the main README.md for complete technical details
4. Customize the system for your specific project needs

18
docs/SMART_TUNING_GUIDE.md
View File

@ -5,10 +5,10 @@
### **1. 📊 Intelligent Analysis**
```bash
# Analyze your project patterns and get optimization suggestions
./rag-mini analyze /path/to/project
./rag-mini-enhanced analyze /path/to/project
# Get smart recommendations based on actual usage
./rag-mini status /path/to/project
./rag-mini-enhanced status /path/to/project
```
**What it analyzes:**
@ -20,9 +20,13 @@
### **2. 🧠 Smart Search Enhancement**
```bash
# Enhanced search with query intelligence
./rag-mini search /project "MyClass" # Detects class names
./rag-mini search /project "login()" # Detects function calls
./rag-mini search /project "user auth" # Natural language
./rag-mini-enhanced search /project "MyClass" # Detects class names
./rag-mini-enhanced search /project "login()" # Detects function calls
./rag-mini-enhanced search /project "user auth" # Natural language
# Context-aware search (planned)
./rag-mini-enhanced context /project "function_name" # Show surrounding code
./rag-mini-enhanced similar /project "pattern" # Find similar patterns
```
### **3. ⚙️ Language-Specific Optimizations**
@ -109,10 +113,10 @@ Edit `.mini-rag/config.json` in your project:
./rag-mini index /project --force
# Test search quality improvements
./rag-mini search /project "your test query"
./rag-mini-enhanced search /project "your test query"
# Verify optimization impact
./rag-mini analyze /project
./rag-mini-enhanced analyze /project
```
## 🎊 **Result: Smarter, Faster, Better**

11
docs/TUI_GUIDE.md
View File

@ -93,10 +93,10 @@ That's it! The TUI will guide you through everything.
- **Full content** - Up to 8 lines of actual code/text
- **Continuation info** - How many more lines exist
**Tips You'll Learn**:
- Verbose output with `--verbose` flag for debugging
- How search scoring works
- Finding the right search terms
**Advanced Tips Shown**:
- Enhanced search with `./rag-mini-enhanced`
- Verbose output with `--verbose` flag
- Context-aware search for related code
**What You Learn**:
- Semantic search vs text search (finds concepts, not just words)
@ -107,7 +107,8 @@ That's it! The TUI will guide you through everything.
**CLI Commands Shown**:
```bash
./rag-mini search /path/to/project "authentication logic"
./rag-mini search /path/to/project "user login" --top-k 10
./rag-mini search /path/to/project "user login" --limit 10
./rag-mini-enhanced context /path/to/project "login()"
```
### 4. Explore Project (NEW!)

58
examples/analyze_dependencies.py
View File

@ -4,110 +4,106 @@ Analyze FSS-Mini-RAG dependencies to determine what's safe to remove.
"""
import ast
from collections import defaultdict
import os
from pathlib import Path
from collections import defaultdict
def find_imports_in_file(file_path):
"""Find all imports in a Python file."""
try:
with open(file_path, "r", encoding="utf-8") as f:
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
tree = ast.parse(content)
imports = set()
for node in ast.walk(tree):
if isinstance(node, ast.Import):
for alias in node.names:
imports.add(alias.name.split(".")[0])
imports.add(alias.name.split('.')[0])
elif isinstance(node, ast.ImportFrom):
if node.module:
module = node.module.split(".")[0]
module = node.module.split('.')[0]
imports.add(module)
return imports
except Exception as e:
print(f"Error analyzing {file_path}: {e}")
return set()
def analyze_dependencies():
"""Analyze all dependencies in the project."""
project_root = Path(__file__).parent
mini_rag_dir = project_root / "mini_rag"
# Find all Python files
python_files = []
for file_path in mini_rag_dir.glob("*.py"):
if file_path.name != "__pycache__":
python_files.append(file_path)
# Analyze imports
file_imports = {}
internal_deps = defaultdict(set)
for file_path in python_files:
imports = find_imports_in_file(file_path)
file_imports[file_path.name] = imports
# Check for internal imports
for imp in imports:
if imp in [f.stem for f in python_files]:
internal_deps[file_path.name].add(imp)
print("🔍 FSS-Mini-RAG Dependency Analysis")
print("=" * 50)
# Show what each file imports
print("\n📁 File Dependencies:")
for filename, imports in file_imports.items():
internal = [imp for imp in imports if imp in [f.stem for f in python_files]]
if internal:
print(f" {filename} imports: {', '.join(internal)}")
# Show reverse dependencies (what depends on each file)
reverse_deps = defaultdict(set)
for file, deps in internal_deps.items():
for dep in deps:
reverse_deps[dep].add(file)
print("\n🔗 Reverse Dependencies (what uses each file):")
all_modules = {f.stem for f in python_files}
for module in sorted(all_modules):
users = reverse_deps.get(module, set())
if users:
print(f" {module}.py is used by: {', '.join(users)}")
else:
print(f" {module}.py is NOT imported by any other file")
# Safety analysis
print("\n🛡️ Safety Analysis:")
# Files imported by __init__.py are definitely needed
init_imports = file_imports.get("__init__.py", set())
init_imports = file_imports.get('__init__.py', set())
print(f" Core modules (imported by __init__.py): {', '.join(init_imports)}")
# Files not used anywhere might be safe to remove
unused_files = []
for module in all_modules:
if module not in reverse_deps and module != "__init__":
if module not in reverse_deps and module != '__init__':
unused_files.append(module)
if unused_files:
print(f" ⚠️ Potentially unused: {', '.join(unused_files)}")
print(" ❗ Verify these aren't used by CLI or external scripts!")
# Check CLI usage
cli_files = ["cli.py", "enhanced_cli.py"]
cli_files = ['cli.py', 'enhanced_cli.py']
for cli_file in cli_files:
if cli_file in file_imports:
cli_imports = file_imports[cli_file]
print(
f" 📋 {cli_file} imports: {', '.join([imp for imp in cli_imports if imp in all_modules])}"
)
print(f" 📋 {cli_file} imports: {', '.join([imp for imp in cli_imports if imp in all_modules])}")
if __name__ == "__main__":
analyze_dependencies()
analyze_dependencies()

35
examples/basic_usage.py
View File

@ -5,67 +5,64 @@ Shows how to index a project and search it programmatically.
"""
from pathlib import Path
from mini_rag import CodeEmbedder, CodeSearcher, ProjectIndexer
from mini_rag import ProjectIndexer, CodeSearcher, CodeEmbedder
def main():
# Example project path - change this to your project
project_path = Path(".") # Current directory
print("=== FSS-Mini-RAG Basic Usage Example ===")
print(f"Project: {project_path}")
# Initialize the embedding system
print("\n1. Initializing embedding system...")
embedder = CodeEmbedder()
print(f" Using: {embedder.get_embedding_info()['method']}")
# Initialize indexer and searcher
# Initialize indexer and searcher
indexer = ProjectIndexer(project_path, embedder)
searcher = CodeSearcher(project_path, embedder)
# Index the project
print("\n2. Indexing project...")
result = indexer.index_project()
print(f" Files processed: {result.get('files_processed', 0)}")
print(f" Chunks created: {result.get('chunks_created', 0)}")
print(f" Time taken: {result.get('indexing_time', 0):.2f}s")
# Get index statistics
print("\n3. Index statistics:")
stats = indexer.get_stats()
print(f" Total files: {stats.get('total_files', 0)}")
print(f" Total chunks: {stats.get('total_chunks', 0)}")
print(f" Languages: {', '.join(stats.get('languages', []))}")
# Example searches
queries = [
"chunker function",
"embedding system",
"embedding system",
"search implementation",
"file watcher",
"error handling",
"error handling"
]
print("\n4. Example searches:")
for query in queries:
print(f"\n Query: '{query}'")
results = searcher.search(query, top_k=3)
if results:
for i, result in enumerate(results, 1):
print(f" {i}. {result.file_path.name} (score: {result.score:.3f})")
print(f" Type: {result.chunk_type}")
# Show first 60 characters of content
content_preview = result.content.replace("\n", " ")[:60]
content_preview = result.content.replace('\n', ' ')[:60]
print(f" Preview: {content_preview}...")
else:
print(" No results found")
print("\n=== Example Complete ===")
if __name__ == "__main__":
main()
main()

116
examples/smart_config_suggestions.py
View File

@ -5,108 +5,102 @@ Analyzes the indexed data to suggest optimal settings.
"""
import json
import sys
from collections import Counter
from pathlib import Path
from collections import defaultdict, Counter
import sys
def analyze_project_patterns(manifest_path: Path):
"""Analyze project patterns and suggest optimizations."""
with open(manifest_path) as f:
manifest = json.load(f)
files = manifest.get("files", {})
files = manifest.get('files', {})
print("🔍 FSS-Mini-RAG Smart Tuning Analysis")
print("=" * 50)
# Analyze file types and chunking efficiency
languages = Counter()
chunk_efficiency = []
large_files = []
small_files = []
for filepath, info in files.items():
lang = info.get("language", "unknown")
lang = info.get('language', 'unknown')
languages[lang] += 1
size = info.get("size", 0)
chunks = info.get("chunks", 1)
size = info.get('size', 0)
chunks = info.get('chunks', 1)
chunk_efficiency.append(chunks / max(1, size / 1000)) # chunks per KB
if size > 10000: # >10KB
large_files.append((filepath, size, chunks))
elif size < 500: # <500B
small_files.append((filepath, size, chunks))
# Analysis results
total_files = len(files)
total_chunks = sum(info.get("chunks", 1) for info in files.values())
total_chunks = sum(info.get('chunks', 1) for info in files.values())
avg_chunks_per_file = total_chunks / max(1, total_files)
print("📊 Current Stats:")
print(f"📊 Current Stats:")
print(f" Files: {total_files}")
print(f" Chunks: {total_chunks}")
print(f" Avg chunks/file: {avg_chunks_per_file:.1f}")
print("\n🗂️ Language Distribution:")
print(f"\n🗂️ Language Distribution:")
for lang, count in languages.most_common(10):
pct = 100 * count / total_files
print(f" {lang}: {count} files ({pct:.1f}%)")
print("\n💡 Smart Optimization Suggestions:")
print(f"\n💡 Smart Optimization Suggestions:")
# Suggestion 1: Language-specific chunking
if languages["python"] > 10:
print("✨ Python Optimization:")
print(
f" - Use function-level chunking (detected {languages['python']} Python files)"
)
print(" - Increase chunk size to 3000 chars for Python (better context)")
if languages["markdown"] > 5:
print("✨ Markdown Optimization:")
if languages['python'] > 10:
print(f"✨ Python Optimization:")
print(f" - Use function-level chunking (detected {languages['python']} Python files)")
print(f" - Increase chunk size to 3000 chars for Python (better context)")
if languages['markdown'] > 5:
print(f"✨ Markdown Optimization:")
print(f" - Use header-based chunking (detected {languages['markdown']} MD files)")
print(" - Keep sections together for better search relevance")
if languages["json"] > 20:
print("✨ JSON Optimization:")
print(f" - Keep sections together for better search relevance")
if languages['json'] > 20:
print(f"✨ JSON Optimization:")
print(f" - Consider object-level chunking (detected {languages['json']} JSON files)")
print(" - Might want to exclude large config JSONs")
print(f" - Might want to exclude large config JSONs")
# Suggestion 2: File size optimization
if large_files:
print("\n📈 Large File Optimization:")
print(f"\n📈 Large File Optimization:")
print(f" Found {len(large_files)} files >10KB:")
for filepath, size, chunks in sorted(large_files, key=lambda x: x[1], reverse=True)[
:3
]:
for filepath, size, chunks in sorted(large_files, key=lambda x: x[1], reverse=True)[:3]:
kb = size / 1024
print(f" - {filepath}: {kb:.1f}KB → {chunks} chunks")
if len(large_files) > 5:
print(" 💡 Consider streaming threshold: 5KB (current: 1MB)")
print(f" 💡 Consider streaming threshold: 5KB (current: 1MB)")
if small_files and len(small_files) > total_files * 0.3:
print("\n📉 Small File Optimization:")
print(f"\n📉 Small File Optimization:")
print(f" {len(small_files)} files <500B might not need chunking")
print(" 💡 Consider: combine small files or skip tiny ones")
print(f" 💡 Consider: combine small files or skip tiny ones")
# Suggestion 3: Search optimization
avg_efficiency = sum(chunk_efficiency) / len(chunk_efficiency)
print("\n🔍 Search Optimization:")
print(f"\n🔍 Search Optimization:")
if avg_efficiency < 0.5:
print(" 💡 Chunks are large relative to files - consider smaller chunks")
print(f" 💡 Chunks are large relative to files - consider smaller chunks")
print(f" 💡 Current: {avg_chunks_per_file:.1f} chunks/file, try 2-3 chunks/file")
elif avg_efficiency > 2:
print(" 💡 Many small chunks - consider larger chunk size")
print(" 💡 Reduce chunk overhead with 2000-4000 char chunks")
print(f" 💡 Many small chunks - consider larger chunk size")
print(f" 💡 Reduce chunk overhead with 2000-4000 char chunks")
# Suggestion 4: Smart defaults
print("\n⚙️ Recommended Config Updates:")
print(
"""{{
print(f"\n⚙️ Recommended Config Updates:")
print(f"""{{
"chunking": {{
"max_size": {3000 if languages['python'] > languages['markdown'] else 2000},
"min_size": 200,
@ -121,18 +115,16 @@ def analyze_project_patterns(manifest_path: Path):
"skip_small_files": {500 if len(small_files) > total_files * 0.3 else 0},
"streaming_threshold_kb": {5 if len(large_files) > 5 else 1024}
}}
}}"""
)
}}""")
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python smart_config_suggestions.py <path_to_manifest.json>")
sys.exit(1)
manifest_path = Path(sys.argv[1])
if not manifest_path.exists():
print(f"Manifest not found: {manifest_path}")
sys.exit(1)
analyze_project_patterns(manifest_path)
analyze_project_patterns(manifest_path)

177
install_mini_rag.sh
View File

@ -4,30 +4,6 @@
set -e # Exit on any error
# Check for command line arguments
HEADLESS_MODE=false
if [[ "$1" == "--headless" ]]; then
HEADLESS_MODE=true
echo "🤖 Running in headless mode - using defaults for automation"
elif [[ "$1" == "--help" || "$1" == "-h" ]]; then
echo ""
echo "FSS-Mini-RAG Installation Script"
echo ""
echo "Usage:"
echo " ./install_mini_rag.sh # Interactive installation"
echo " ./install_mini_rag.sh --headless # Automated installation for agents/CI"
echo " ./install_mini_rag.sh --help # Show this help"
echo ""
echo "Headless mode options:"
echo " • Uses existing virtual environment if available"
echo " • Selects light installation (Ollama + basic dependencies)"
echo " • Downloads nomic-embed-text model if Ollama is available"
echo " • Skips interactive prompts and tests"
echo " • Perfect for agent automation and CI/CD pipelines"
echo ""
exit 0
fi
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
@ -108,19 +84,14 @@ check_python() {
check_venv() {
if [ -d "$SCRIPT_DIR/.venv" ]; then
print_info "Virtual environment already exists at $SCRIPT_DIR/.venv"
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Using existing virtual environment"
return 0 # Use existing
echo -n "Recreate it? (y/N): "
read -r recreate
if [[ $recreate =~ ^[Yy]$ ]]; then
print_info "Removing existing virtual environment..."
rm -rf "$SCRIPT_DIR/.venv"
return 1 # Needs creation
else
echo -n "Recreate it? (y/N): "
read -r recreate
if [[ $recreate =~ ^[Yy]$ ]]; then
print_info "Removing existing virtual environment..."
rm -rf "$SCRIPT_DIR/.venv"
return 1 # Needs creation
else
return 0 # Use existing
fi
return 0 # Use existing
fi
else
return 1 # Needs creation
@ -169,13 +140,8 @@ check_ollama() {
return 0
else
print_warning "Ollama is installed but not running"
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Starting Ollama server automatically"
start_ollama="y"
else
echo -n "Start Ollama now? (Y/n): "
read -r start_ollama
fi
echo -n "Start Ollama now? (Y/n): "
read -r start_ollama
if [[ ! $start_ollama =~ ^[Nn]$ ]]; then
print_info "Starting Ollama server..."
ollama serve &
@ -202,26 +168,15 @@ check_ollama() {
echo -e "${YELLOW}2) Manual installation${NC} - Visit https://ollama.com/download"
echo -e "${BLUE}3) Continue without Ollama${NC} (uses ML fallback)"
echo ""
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Continuing without Ollama (option 3)"
ollama_choice="3"
else
echo -n "Choose [1/2/3]: "
read -r ollama_choice
fi
echo -n "Choose [1/2/3]: "
read -r ollama_choice
case "$ollama_choice" in
1|"")
print_info "Installing Ollama using secure installation method..."
echo -e "${CYAN}Downloading and verifying Ollama installer...${NC}"
print_info "Installing Ollama using official installer..."
echo -e "${CYAN}Running: curl -fsSL https://ollama.com/install.sh | sh${NC}"
# Secure installation: download, verify, then execute
local temp_script="/tmp/ollama-install-$$.sh"
if curl -fsSL https://ollama.com/install.sh -o "$temp_script" && \
file "$temp_script" | grep -q "shell script" && \
chmod +x "$temp_script" && \
"$temp_script"; then
rm -f "$temp_script"
if curl -fsSL https://ollama.com/install.sh | sh; then
print_success "Ollama installed successfully"
print_info "Starting Ollama server..."
@ -312,13 +267,8 @@ setup_ollama_model() {
echo " • Purpose: High-quality semantic embeddings"
echo " • Alternative: System will use ML/hash fallbacks"
echo ""
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Downloading nomic-embed-text model"
download_model="y"
else
echo -n "Download model? [y/N]: "
read -r download_model
fi
echo -n "Download model? [y/N]: "
read -r download_model
should_download=$([ "$download_model" = "y" ] && echo "download" || echo "skip")
fi
@ -378,21 +328,15 @@ get_installation_preferences() {
echo ""
while true; do
if [[ "$HEADLESS_MODE" == "true" ]]; then
# Default to light installation in headless mode
choice="L"
print_info "Headless mode: Selected Light installation"
else
echo -n "Choose [L/F/C] or Enter for recommended ($recommended): "
read -r choice
# Default to recommendation if empty
if [ -z "$choice" ]; then
if [ "$ollama_available" = true ]; then
choice="L"
else
choice="F"
fi
echo -n "Choose [L/F/C] or Enter for recommended ($recommended): "
read -r choice
# Default to recommendation if empty
if [ -z "$choice" ]; then
if [ "$ollama_available" = true ]; then
choice="L"
else
choice="F"
fi
fi
@ -434,13 +378,8 @@ configure_custom_installation() {
echo ""
echo -e "${BOLD}Ollama embedding model:${NC}"
echo " • nomic-embed-text (~270MB) - Best quality embeddings"
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Downloading Ollama model"
download_ollama="y"
else
echo -n "Download Ollama model? [y/N]: "
read -r download_ollama
fi
echo -n "Download Ollama model? [y/N]: "
read -r download_ollama
if [[ $download_ollama =~ ^[Yy]$ ]]; then
ollama_model="download"
fi
@ -451,13 +390,8 @@ configure_custom_installation() {
echo -e "${BOLD}ML fallback system:${NC}"
echo " • PyTorch + transformers (~2-3GB) - Works without Ollama"
echo " • Useful for: Offline use, server deployments, CI/CD"
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Skipping ML dependencies (keeping light)"
include_ml="n"
else
echo -n "Include ML dependencies? [y/N]: "
read -r include_ml
fi
echo -n "Include ML dependencies? [y/N]: "
read -r include_ml
# Pre-download models
local predownload_ml="skip"
@ -466,13 +400,8 @@ configure_custom_installation() {
echo -e "${BOLD}Pre-download ML models:${NC}"
echo " • sentence-transformers model (~80MB)"
echo " • Skip: Models download automatically when first used"
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Skipping ML model pre-download"
predownload="n"
else
echo -n "Pre-download now? [y/N]: "
read -r predownload
fi
echo -n "Pre-download now? [y/N]: "
read -r predownload
if [[ $predownload =~ ^[Yy]$ ]]; then
predownload_ml="download"
fi
@ -616,13 +545,8 @@ setup_ml_models() {
echo " • Purpose: Offline fallback when Ollama unavailable"
echo " • If skipped: Auto-downloads when first needed"
echo ""
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Skipping ML model pre-download"
download_ml="n"
else
echo -n "Pre-download now? [y/N]: "
read -r download_ml
fi
echo -n "Pre-download now? [y/N]: "
read -r download_ml
should_predownload=$([ "$download_ml" = "y" ] && echo "download" || echo "skip")
fi
@ -777,11 +701,7 @@ show_completion() {
printf "Run quick test now? [Y/n]: "
# More robust input handling
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Skipping interactive test"
echo -e "${BLUE}You can test FSS-Mini-RAG anytime with: ./rag-tui${NC}"
show_beginner_guidance
elif read -r run_test < /dev/tty 2>/dev/null; then
if read -r run_test < /dev/tty 2>/dev/null; then
echo "User chose: '$run_test'" # Debug output
if [[ ! $run_test =~ ^[Nn]$ ]]; then
run_quick_test
@ -812,13 +732,8 @@ run_quick_test() {
echo -e "${GREEN}1) Code${NC} - Index the FSS-Mini-RAG codebase (~50 files)"
echo -e "${BLUE}2) Docs${NC} - Index the documentation (~10 files)"
echo ""
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Indexing code by default"
index_choice="1"
else
echo -n "Choose [1/2] or Enter for code: "
read -r index_choice
fi
echo -n "Choose [1/2] or Enter for code: "
read -r index_choice
# Determine what to index
local target_dir="$SCRIPT_DIR"
@ -853,10 +768,8 @@ run_quick_test() {
echo -e "${CYAN}The TUI has 6 sample questions to get you started.${NC}"
echo -e "${CYAN}Try the suggested queries or enter your own!${NC}"
echo ""
if [[ "$HEADLESS_MODE" != "true" ]]; then
echo -n "Press Enter to start interactive tutorial: "
read -r
fi
echo -n "Press Enter to start interactive tutorial: "
read -r
# Launch the TUI which has the existing interactive tutorial system
./rag-tui.py "$target_dir" || true
@ -919,15 +832,11 @@ main() {
echo -e "${CYAN}Note: You'll be asked before downloading any models${NC}"
echo ""
if [[ "$HEADLESS_MODE" == "true" ]]; then
print_info "Headless mode: Beginning installation automatically"
else
echo -n "Begin installation? [Y/n]: "
read -r continue_install
if [[ $continue_install =~ ^[Nn]$ ]]; then
echo "Installation cancelled."
exit 0
fi
echo -n "Begin installation? [Y/n]: "
read -r continue_install
if [[ $continue_install =~ ^[Nn]$ ]]; then
echo "Installation cancelled."
exit 0
fi
# Run installation steps

75
install_windows.bat
View File

@ -5,40 +5,6 @@ setlocal enabledelayedexpansion
REM Enable colors and unicode for modern Windows
chcp 65001 >nul 2>&1
REM Check for command line arguments
set "HEADLESS_MODE=false"
if "%1"=="--headless" (
set "HEADLESS_MODE=true"
echo 🤖 Running in headless mode - using defaults for automation
) else if "%1"=="--help" (
goto show_help
) else if "%1"=="-h" (
goto show_help
)
goto start_installation
:show_help
echo.
echo FSS-Mini-RAG Windows Installation Script
echo.
echo Usage:
echo install_windows.bat # Interactive installation
echo install_windows.bat --headless # Automated installation for agents/CI
echo install_windows.bat --help # Show this help
echo.
echo Headless mode options:
echo • Uses existing virtual environment if available
echo • Installs core dependencies only
echo • Skips AI model downloads
echo • Skips interactive prompts and tests
echo • Perfect for agent automation and CI/CD pipelines
echo.
pause
exit /b 0
:start_installation
echo.
echo ╔══════════════════════════════════════════════════╗
echo ║ FSS-Mini-RAG Windows Installer ║
@ -55,15 +21,11 @@ echo.
echo 💡 Note: You'll be asked before downloading any models
echo.
if "!HEADLESS_MODE!"=="true" (
echo Headless mode: Beginning installation automatically
) else (
set /p "continue=Begin installation? [Y/n]: "
if /i "!continue!"=="n" (
echo Installation cancelled.
pause
exit /b 0
)
set /p "continue=Begin installation? [Y/n]: "
if /i "!continue!"=="n" (
echo Installation cancelled.
pause
exit /b 0
)
REM Get script directory
@ -241,16 +203,11 @@ REM Offer interactive tutorial
echo 🧪 Quick Test Available:
echo Test FSS-Mini-RAG with a small sample project (takes ~30 seconds)
echo.
if "!HEADLESS_MODE!"=="true" (
echo Headless mode: Skipping interactive tutorial
echo 📚 You can run the tutorial anytime with: rag.bat
set /p "run_test=Run interactive tutorial now? [Y/n]: "
if /i "!run_test!" NEQ "n" (
call :run_tutorial
) else (
set /p "run_test=Run interactive tutorial now? [Y/n]: "
if /i "!run_test!" NEQ "n" (
call :run_tutorial
) else (
echo 📚 You can run the tutorial anytime with: rag.bat
)
echo 📚 You can run the tutorial anytime with: rag.bat
)
echo.
@ -288,12 +245,7 @@ curl -s http://localhost:11434/api/version >nul 2>&1
if errorlevel 1 (
echo 🟡 Ollama installed but not running
echo.
if "!HEADLESS_MODE!"=="true" (
echo Headless mode: Starting Ollama server automatically
set "start_ollama=y"
) else (
set /p "start_ollama=Start Ollama server now? [Y/n]: "
)
set /p "start_ollama=Start Ollama server now? [Y/n]: "
if /i "!start_ollama!" NEQ "n" (
echo 🚀 Starting Ollama server...
start /b ollama serve
@ -321,12 +273,7 @@ if errorlevel 1 (
echo • qwen3:0.6b - Lightweight and fast (~500MB)
echo • qwen3:4b - Higher quality but slower (~2.5GB)
echo.
if "!HEADLESS_MODE!"=="true" (
echo Headless mode: Skipping model download
set "install_model=n"
) else (
set /p "install_model=Download qwen3:1.7b model now? [Y/n]: "
)
set /p "install_model=Download qwen3:1.7b model now? [Y/n]: "
if /i "!install_model!" NEQ "n" (
echo 📥 Downloading qwen3:1.7b model...
echo This may take 5-10 minutes depending on your internet speed

30
mini_rag/__init__.py
View File

@ -7,16 +7,30 @@ Designed for portability, efficiency, and simplicity across projects and compute
__version__ = "2.1.0"
from .ollama_embeddings import OllamaEmbedder as CodeEmbedder
from .chunker import CodeChunker
from .indexer import ProjectIndexer
from .ollama_embeddings import OllamaEmbedder as CodeEmbedder
from .search import CodeSearcher
from .watcher import FileWatcher
__all__ = [
"CodeEmbedder",
"CodeChunker",
"ProjectIndexer",
"CodeSearcher",
"FileWatcher",
]
# Auto-update system (graceful import for legacy versions)
try:
from .updater import UpdateChecker, check_for_updates, get_updater
__all__ = [
"CodeEmbedder",
"CodeChunker",
"ProjectIndexer",
"CodeSearcher",
"FileWatcher",
"UpdateChecker",
"check_for_updates",
"get_updater",
]
except ImportError:
__all__ = [
"CodeEmbedder",
"CodeChunker",
"ProjectIndexer",
"CodeSearcher",
"FileWatcher",
]

4
mini_rag/__main__.py
View File

@ -2,5 +2,5 @@
from .cli import cli
if __name__ == "__main__":
cli()
if __name__ == '__main__':
cli()

182
mini_rag/auto_optimizer.py
View File

@ -3,188 +3,194 @@ Auto-optimizer for FSS-Mini-RAG.
Automatically tunes settings based on usage patterns.
"""
import json
import logging
from collections import Counter
from pathlib import Path
from typing import Any, Dict
import json
from typing import Dict, Any, List
from collections import Counter
import logging
logger = logging.getLogger(__name__)
class AutoOptimizer:
"""Automatically optimizes RAG settings based on project patterns."""
def __init__(self, project_path: Path):
self.project_path = project_path
self.rag_dir = project_path / ".mini-rag"
self.config_path = self.rag_dir / "config.json"
self.manifest_path = self.rag_dir / "manifest.json"
self.rag_dir = project_path / '.mini-rag'
self.config_path = self.rag_dir / 'config.json'
self.manifest_path = self.rag_dir / 'manifest.json'
def analyze_and_optimize(self) -> Dict[str, Any]:
"""Analyze current patterns and auto-optimize settings."""
if not self.manifest_path.exists():
return {"error": "No index found - run indexing first"}
# Load current data
with open(self.manifest_path) as f:
manifest = json.load(f)
# Analyze patterns
analysis = self._analyze_patterns(manifest)
# Generate optimizations
optimizations = self._generate_optimizations(analysis)
# Apply optimizations if beneficial
if optimizations["confidence"] > 0.7:
if optimizations['confidence'] > 0.7:
self._apply_optimizations(optimizations)
return {
"status": "optimized",
"changes": optimizations["changes"],
"expected_improvement": optimizations["expected_improvement"],
"changes": optimizations['changes'],
"expected_improvement": optimizations['expected_improvement']
}
else:
return {
"status": "no_changes_needed",
"analysis": analysis,
"confidence": optimizations["confidence"],
"confidence": optimizations['confidence']
}
def _analyze_patterns(self, manifest: Dict[str, Any]) -> Dict[str, Any]:
"""Analyze current indexing patterns."""
files = manifest.get("files", {})
files = manifest.get('files', {})
# Language distribution
languages = Counter()
sizes = []
chunk_ratios = []
for filepath, info in files.items():
lang = info.get("language", "unknown")
lang = info.get('language', 'unknown')
languages[lang] += 1
size = info.get("size", 0)
chunks = info.get("chunks", 1)
size = info.get('size', 0)
chunks = info.get('chunks', 1)
sizes.append(size)
chunk_ratios.append(chunks / max(1, size / 1000)) # chunks per KB
avg_chunk_ratio = sum(chunk_ratios) / len(chunk_ratios) if chunk_ratios else 1
avg_size = sum(sizes) / len(sizes) if sizes else 1000
return {
"languages": dict(languages.most_common()),
"total_files": len(files),
"total_chunks": sum(info.get("chunks", 1) for info in files.values()),
"avg_chunk_ratio": avg_chunk_ratio,
"avg_file_size": avg_size,
"large_files": sum(1 for s in sizes if s > 10000),
"small_files": sum(1 for s in sizes if s < 500),
'languages': dict(languages.most_common()),
'total_files': len(files),
'total_chunks': sum(info.get('chunks', 1) for info in files.values()),
'avg_chunk_ratio': avg_chunk_ratio,
'avg_file_size': avg_size,
'large_files': sum(1 for s in sizes if s > 10000),
'small_files': sum(1 for s in sizes if s < 500)
}
def _generate_optimizations(self, analysis: Dict[str, Any]) -> Dict[str, Any]:
"""Generate optimization recommendations."""
changes = []
confidence = 0.5
expected_improvement = 0
# Optimize chunking based on dominant language
languages = analysis["languages"]
languages = analysis['languages']
if languages:
dominant_lang, count = list(languages.items())[0]
lang_pct = count / analysis["total_files"]
lang_pct = count / analysis['total_files']
if lang_pct > 0.3: # Dominant language >30%
if dominant_lang == "python" and analysis["avg_chunk_ratio"] < 1.5:
changes.append(
"Increase Python chunk size to 3000 for better function context"
)
if dominant_lang == 'python' and analysis['avg_chunk_ratio'] < 1.5:
changes.append("Increase Python chunk size to 3000 for better function context")
confidence += 0.2
expected_improvement += 15
elif dominant_lang == "markdown" and analysis["avg_chunk_ratio"] < 1.2:
elif dominant_lang == 'markdown' and analysis['avg_chunk_ratio'] < 1.2:
changes.append("Use header-based chunking for Markdown files")
confidence += 0.15
expected_improvement += 10
# Optimize for large files
if analysis["large_files"] > 5:
if analysis['large_files'] > 5:
changes.append("Reduce streaming threshold to 5KB for better large file handling")
confidence += 0.1
expected_improvement += 8
# Optimize chunk ratio
if analysis["avg_chunk_ratio"] < 1.0:
if analysis['avg_chunk_ratio'] < 1.0:
changes.append("Reduce chunk size for more granular search results")
confidence += 0.15
expected_improvement += 12
elif analysis["avg_chunk_ratio"] > 3.0:
elif analysis['avg_chunk_ratio'] > 3.0:
changes.append("Increase chunk size to reduce overhead")
confidence += 0.1
expected_improvement += 5
# Skip tiny files optimization
small_file_pct = analysis["small_files"] / analysis["total_files"]
small_file_pct = analysis['small_files'] / analysis['total_files']
if small_file_pct > 0.3:
changes.append("Skip files smaller than 300 bytes to improve focus")
confidence += 0.1
expected_improvement += 3
return {
"changes": changes,
"confidence": min(confidence, 1.0),
"expected_improvement": expected_improvement,
'changes': changes,
'confidence': min(confidence, 1.0),
'expected_improvement': expected_improvement
}
def _apply_optimizations(self, optimizations: Dict[str, Any]):
"""Apply the recommended optimizations."""
# Load existing config or create default
if self.config_path.exists():
with open(self.config_path) as f:
config = json.load(f)
else:
config = self._get_default_config()
changes = optimizations["changes"]
changes = optimizations['changes']
# Apply changes based on recommendations
for change in changes:
if "Python chunk size to 3000" in change:
config.setdefault("chunking", {})["max_size"] = 3000
config.setdefault('chunking', {})['max_size'] = 3000
elif "header-based chunking" in change:
config.setdefault("chunking", {})["strategy"] = "header"
config.setdefault('chunking', {})['strategy'] = 'header'
elif "streaming threshold to 5KB" in change:
config.setdefault("streaming", {})["threshold_bytes"] = 5120
config.setdefault('streaming', {})['threshold_bytes'] = 5120
elif "Reduce chunk size" in change:
current_size = config.get("chunking", {}).get("max_size", 2000)
config.setdefault("chunking", {})["max_size"] = max(1500, current_size - 500)
current_size = config.get('chunking', {}).get('max_size', 2000)
config.setdefault('chunking', {})['max_size'] = max(1500, current_size - 500)
elif "Increase chunk size" in change:
current_size = config.get("chunking", {}).get("max_size", 2000)
config.setdefault("chunking", {})["max_size"] = min(4000, current_size + 500)
current_size = config.get('chunking', {}).get('max_size', 2000)
config.setdefault('chunking', {})['max_size'] = min(4000, current_size + 500)
elif "Skip files smaller" in change:
config.setdefault("files", {})["min_file_size"] = 300
config.setdefault('files', {})['min_file_size'] = 300
# Save optimized config
config["_auto_optimized"] = True
config["_optimization_timestamp"] = json.dumps(None, default=str)
with open(self.config_path, "w") as f:
config['_auto_optimized'] = True
config['_optimization_timestamp'] = json.dumps(None, default=str)
with open(self.config_path, 'w') as f:
json.dump(config, f, indent=2)
logger.info(f"Applied {len(changes)} optimizations to {self.config_path}")
def _get_default_config(self) -> Dict[str, Any]:
"""Get default configuration."""
return {
"chunking": {"max_size": 2000, "min_size": 150, "strategy": "semantic"},
"streaming": {"enabled": True, "threshold_bytes": 1048576},
"files": {"min_file_size": 50},
}
"chunking": {
"max_size": 2000,
"min_size": 150,
"strategy": "semantic"
},
"streaming": {
"enabled": True,
"threshold_bytes": 1048576
},
"files": {
"min_file_size": 50
}
}

1085
mini_rag/chunker.py
View File

File diff suppressed because it is too large Load Diff

512
mini_rag/cli.py
View File

@ -3,57 +3,59 @@ Command-line interface for Mini RAG system.
Beautiful, intuitive, and highly effective.
"""
import logging
import click
import sys
import time
import logging
from pathlib import Path
from typing import Optional
import click
# Fix Windows console for proper emoji/Unicode support
from .windows_console_fix import fix_windows_console
fix_windows_console()
from rich.console import Console
from rich.logging import RichHandler
from rich.panel import Panel
from rich.progress import Progress, SpinnerColumn, TextColumn
from rich.syntax import Syntax
from rich.table import Table
from rich.progress import Progress, SpinnerColumn, TextColumn
from rich.logging import RichHandler
from rich.syntax import Syntax
from rich.panel import Panel
from rich import print as rprint
from .indexer import ProjectIndexer
from .search import CodeSearcher
from .watcher import FileWatcher
from .non_invasive_watcher import NonInvasiveFileWatcher
from .ollama_embeddings import OllamaEmbedder as CodeEmbedder
from .chunker import CodeChunker
from .performance import get_monitor
from .search import CodeSearcher
from .server import RAGClient, start_server
from .windows_console_fix import fix_windows_console
# Fix Windows console for proper emoji/Unicode support
fix_windows_console()
from .server import RAGClient
from .server import RAGServer, RAGClient, start_server
# Set up logging
logging.basicConfig(
level=logging.INFO,
format="%(message)s",
handlers=[RichHandler(rich_tracebacks=True)],
handlers=[RichHandler(rich_tracebacks=True)]
)
logger = logging.getLogger(__name__)
console = Console()
@click.group()
@click.option("--verbose", "-v", is_flag=True, help="Enable verbose logging")
@click.option("--quiet", "-q", is_flag=True, help="Suppress output")
@click.option('--verbose', '-v', is_flag=True, help='Enable verbose logging')
@click.option('--quiet', '-q', is_flag=True, help='Suppress output')
def cli(verbose: bool, quiet: bool):
"""
Mini RAG - Fast semantic code search that actually works.
A local RAG system for improving the development environment's grounding
capabilities.
A local RAG system for improving the development environment's grounding capabilities.
Indexes your codebase and enables lightning-fast semantic search.
"""
# Check virtual environment
from .venv_checker import check_and_warn_venv
check_and_warn_venv("rag-mini", force_exit=False)
if verbose:
logging.getLogger().setLevel(logging.DEBUG)
elif quiet:
@ -61,45 +63,43 @@ def cli(verbose: bool, quiet: bool):
@cli.command()
@click.option(
"--path",
"-p",
type=click.Path(exists=True),
default=".",
help="Project path to index",
)
@click.option("--force", "-", is_flag=True, help="Force reindex all files")
@click.option("--reindex", "-r", is_flag=True, help="Force complete reindex (same as --force)")
@click.option("--model", "-m", type=str, default=None, help="Embedding model to use")
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path to index')
@click.option('--force', '-f', is_flag=True,
help='Force reindex all files')
@click.option('--reindex', '-r', is_flag=True,
help='Force complete reindex (same as --force)')
@click.option('--model', '-m', type=str, default=None,
help='Embedding model to use')
def init(path: str, force: bool, reindex: bool, model: Optional[str]):
"""Initialize RAG index for a project."""
project_path = Path(path).resolve()
console.print(f"\n[bold cyan]Initializing Mini RAG for:[/bold cyan] {project_path}\n")
# Check if already initialized
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
force_reindex = force or reindex
if rag_dir.exists() and not force_reindex:
console.print("[yellow][/yellow] Project already initialized!")
console.print("Use --force or --reindex to reindex all files\n")
# Show current stats
indexer = ProjectIndexer(project_path)
stats = indexer.get_statistics()
table = Table(title="Current Index Statistics")
table.add_column("Metric", style="cyan")
table.add_column("Value", style="green")
table.add_row("Files Indexed", str(stats["file_count"]))
table.add_row("Total Chunks", str(stats["chunk_count"]))
table.add_row("Files Indexed", str(stats['file_count']))
table.add_row("Total Chunks", str(stats['chunk_count']))
table.add_row("Index Size", f"{stats['index_size_mb']:.2f} MB")
table.add_row("Last Updated", stats["indexed_at"] or "Never")
table.add_row("Last Updated", stats['indexed_at'] or "Never")
console.print(table)
return
# Initialize components
try:
with Progress(
@ -111,33 +111,34 @@ def init(path: str, force: bool, reindex: bool, model: Optional[str]):
task = progress.add_task("[cyan]Loading embedding model...", total=None)
embedder = CodeEmbedder(model_name=model)
progress.update(task, completed=True)
# Create indexer
task = progress.add_task("[cyan]Creating indexer...", total=None)
indexer = ProjectIndexer(project_path, embedder=embedder)
indexer = ProjectIndexer(
project_path,
embedder=embedder
)
progress.update(task, completed=True)
# Run indexing
console.print("\n[bold green]Starting indexing...[/bold green]\n")
stats = indexer.index_project(force_reindex=force_reindex)
# Show summary
if stats["files_indexed"] > 0:
console.print(
f"\n[bold green] Success![/bold green] Indexed {stats['files_indexed']} files"
)
if stats['files_indexed'] > 0:
console.print(f"\n[bold green] Success![/bold green] Indexed {stats['files_indexed']} files")
console.print(f"Created {stats['chunks_created']} searchable chunks")
console.print(f"Time: {stats['time_taken']:.2f} seconds")
console.print(f"Speed: {stats['files_per_second']:.1f} files/second")
else:
console.print("\n[green] All files are already up to date![/green]")
# Show how to use
console.print("\n[bold]Next steps:[/bold]")
console.print(' • Search your code: [cyan]rag-mini search "your query"[/cyan]')
console.print(" • Search your code: [cyan]rag-mini search \"your query\"[/cyan]")
console.print(" • Watch for changes: [cyan]rag-mini watch[/cyan]")
console.print(" • View statistics: [cyan]rag-mini stats[/cyan]\n")
except Exception as e:
console.print(f"\n[bold red]Error:[/bold red] {e}")
logger.exception("Initialization failed")
@ -145,71 +146,64 @@ def init(path: str, force: bool, reindex: bool, model: Optional[str]):
@cli.command()
@click.argument("query")
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option("--top-k", "-k", type=int, default=10, help="Maximum results to show")
@click.option(
"--type", "-t", multiple=True, help="Filter by chunk type (function, class, method)"
)
@click.option("--lang", multiple=True, help="Filter by language (python, javascript, etc.)")
@click.option("--show-content", "-c", is_flag=True, help="Show code content in results")
@click.option("--show-per", is_flag=True, help="Show performance metrics")
def search(
query: str,
path: str,
top_k: int,
type: tuple,
lang: tuple,
show_content: bool,
show_perf: bool,
):
@click.argument('query')
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
@click.option('--top-k', '-k', type=int, default=10,
help='Maximum results to show')
@click.option('--type', '-t', multiple=True,
help='Filter by chunk type (function, class, method)')
@click.option('--lang', multiple=True,
help='Filter by language (python, javascript, etc.)')
@click.option('--show-content', '-c', is_flag=True,
help='Show code content in results')
@click.option('--show-perf', is_flag=True,
help='Show performance metrics')
def search(query: str, path: str, top_k: int, type: tuple, lang: tuple, show_content: bool, show_perf: bool):
"""Search codebase using semantic similarity."""
project_path = Path(path).resolve()
# Check if indexed
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
console.print("[red]Error:[/red] Project not indexed. Run 'rag-mini init' first.")
sys.exit(1)
# Get performance monitor
monitor = get_monitor() if show_perf else None
# Check if server is running
client = RAGClient()
use_server = client.is_running()
try:
if use_server:
# Use server for fast queries
console.print("[dim]Using RAG server...[/dim]")
response = client.search(query, top_k=top_k)
if response.get("success"):
if response.get('success'):
# Convert response to SearchResult objects
from .search import SearchResult
results = []
for r in response["results"]:
for r in response['results']:
result = SearchResult(
file_path=r["file_path"],
content=r["content"],
score=r["score"],
start_line=r["start_line"],
end_line=r["end_line"],
chunk_type=r["chunk_type"],
name=r["name"],
language=r["language"],
file_path=r['file_path'],
content=r['content'],
score=r['score'],
start_line=r['start_line'],
end_line=r['end_line'],
chunk_type=r['chunk_type'],
name=r['name'],
language=r['language']
)
results.append(result)
# Show server stats
search_time = response.get("search_time_ms", 0)
total_queries = response.get("total_queries", 0)
console.print(
f"[dim]Search time: {search_time}ms (Query #{total_queries})[/dim]\n"
)
search_time = response.get('search_time_ms', 0)
total_queries = response.get('total_queries', 0)
console.print(f"[dim]Search time: {search_time}ms (Query #{total_queries})[/dim]\n")
else:
console.print(f"[red]Server error:[/red] {response.get('error')}")
sys.exit(1)
@ -221,7 +215,7 @@ def search(
searcher = CodeSearcher(project_path)
else:
searcher = CodeSearcher(project_path)
# Perform search with timing
if monitor:
with monitor.measure("Execute Vector Search"):
@ -229,7 +223,7 @@ def search(
query,
top_k=top_k,
chunk_types=list(type) if type else None,
languages=list(lang) if lang else None,
languages=list(lang) if lang else None
)
else:
with console.status(f"[cyan]Searching for: {query}[/cyan]"):
@ -237,9 +231,9 @@ def search(
query,
top_k=top_k,
chunk_types=list(type) if type else None,
languages=list(lang) if lang else None,
languages=list(lang) if lang else None
)
# Display results
if results:
if use_server:
@ -249,30 +243,27 @@ def search(
display_searcher.display_results(results, show_content=show_content)
else:
searcher.display_results(results, show_content=show_content)
# Copy first result to clipboard if available
try:
import pyperclip
first_result = results[0]
location = f"{first_result.file_path}:{first_result.start_line}"
pyperclip.copy(location)
console.print(
f"\n[dim]First result location copied to clipboard: {location}[/dim]"
)
except (ImportError, OSError):
pass # Clipboard not available
console.print(f"\n[dim]First result location copied to clipboard: {location}[/dim]")
except:
pass
else:
console.print(f"\n[yellow]No results found for: {query}[/yellow]")
console.print("\n[dim]Tips:[/dim]")
console.print(" • Try different keywords")
console.print(" • Use natural language queries")
# Show performance summary
if monitor:
monitor.print_summary()
console.print(" • Check if files are indexed with 'mini-rag stats'")
except Exception as e:
console.print(f"\n[bold red]Search error:[/bold red] {e}")
logger.exception("Search failed")
@ -280,69 +271,68 @@ def search(
@cli.command()
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
def stats(path: str):
"""Show index statistics."""
project_path = Path(path).resolve()
# Check if indexed
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
console.print("[red]Error:[/red] Project not indexed. Run 'rag-mini init' first.")
sys.exit(1)
try:
# Get statistics
indexer = ProjectIndexer(project_path)
index_stats = indexer.get_statistics()
searcher = CodeSearcher(project_path)
search_stats = searcher.get_statistics()
# Display project info
console.print(f"\n[bold cyan]Project:[/bold cyan] {project_path.name}")
console.print(f"[dim]Path: {project_path}[/dim]\n")
# Index statistics table
table = Table(title="Index Statistics")
table.add_column("Metric", style="cyan")
table.add_column("Value", style="green")
table.add_row("Files Indexed", str(index_stats["file_count"]))
table.add_row("Total Chunks", str(index_stats["chunk_count"]))
table.add_row("Files Indexed", str(index_stats['file_count']))
table.add_row("Total Chunks", str(index_stats['chunk_count']))
table.add_row("Index Size", f"{index_stats['index_size_mb']:.2f} MB")
table.add_row("Last Updated", index_stats["indexed_at"] or "Never")
table.add_row("Last Updated", index_stats['indexed_at'] or "Never")
console.print(table)
# Language distribution
if "languages" in search_stats:
if 'languages' in search_stats:
console.print("\n[bold]Language Distribution:[/bold]")
lang_table = Table()
lang_table.add_column("Language", style="cyan")
lang_table.add_column("Chunks", style="green")
for lang, count in sorted(
search_stats["languages"].items(), key=lambda x: x[1], reverse=True
):
for lang, count in sorted(search_stats['languages'].items(),
key=lambda x: x[1], reverse=True):
lang_table.add_row(lang, str(count))
console.print(lang_table)
# Chunk type distribution
if "chunk_types" in search_stats:
if 'chunk_types' in search_stats:
console.print("\n[bold]Chunk Types:[/bold]")
type_table = Table()
type_table.add_column("Type", style="cyan")
type_table.add_column("Count", style="green")
for chunk_type, count in sorted(
search_stats["chunk_types"].items(), key=lambda x: x[1], reverse=True
):
for chunk_type, count in sorted(search_stats['chunk_types'].items(),
key=lambda x: x[1], reverse=True):
type_table.add_row(chunk_type, str(count))
console.print(type_table)
except Exception as e:
console.print(f"\n[bold red]Error:[/bold red] {e}")
logger.exception("Failed to get statistics")
@ -350,116 +340,101 @@ def stats(path: str):
@cli.command()
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
def debug_schema(path: str):
"""Debug vector database schema and sample data."""
project_path = Path(path).resolve()
try:
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
console.print("[red]No RAG index found. Run 'rag-mini init' first.[/red]")
return
# Connect to database
try:
import lancedb
except ImportError:
console.print(
"[red]LanceDB not available. Install with: pip install lancedb pyarrow[/red]"
)
console.print("[red]LanceDB not available. Install with: pip install lancedb pyarrow[/red]")
return
db = lancedb.connect(rag_dir)
if "code_vectors" not in db.table_names():
console.print("[red]No code_vectors table found.[/red]")
return
table = db.open_table("code_vectors")
# Print schema
console.print("\n[bold cyan] Table Schema:[/bold cyan]")
console.print(table.schema)
# Get sample data
import pandas as pd
df = table.to_pandas()
console.print("\n[bold cyan] Table Statistics:[/bold cyan]")
console.print(f"\n[bold cyan] Table Statistics:[/bold cyan]")
console.print(f"Total rows: {len(df)}")
if len(df) > 0:
# Check embedding column
console.print("\n[bold cyan] Embedding Column Analysis:[/bold cyan]")
first_embedding = df["embedding"].iloc[0]
console.print(f"\n[bold cyan] Embedding Column Analysis:[/bold cyan]")
first_embedding = df['embedding'].iloc[0]
console.print(f"Type: {type(first_embedding)}")
if hasattr(first_embedding, "shape"):
if hasattr(first_embedding, 'shape'):
console.print(f"Shape: {first_embedding.shape}")
if hasattr(first_embedding, "dtype"):
if hasattr(first_embedding, 'dtype'):
console.print(f"Dtype: {first_embedding.dtype}")
# Show first few rows
console.print("\n[bold cyan] Sample Data (first 3 rows):[/bold cyan]")
console.print(f"\n[bold cyan] Sample Data (first 3 rows):[/bold cyan]")
for i in range(min(3, len(df))):
row = df.iloc[i]
console.print(f"\n[yellow]Row {i}:[/yellow]")
console.print(f" chunk_id: {row['chunk_id']}")
console.print(f" file_path: {row['file_path']}")
console.print(f" content: {row['content'][:50]}...")
embed_len = (
len(row["embedding"])
if hasattr(row["embedding"], "__len__")
else "unknown"
)
console.print(f" embedding: {type(row['embedding'])} of length {embed_len}")
console.print(f" embedding: {type(row['embedding'])} of length {len(row['embedding']) if hasattr(row['embedding'], '__len__') else 'unknown'}")
except Exception as e:
logger.error(f"Schema debug failed: {e}")
console.print(f"[red]Error: {e}[/red]")
@cli.command()
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option(
"--delay",
"-d",
type=float,
default=10.0,
help="Update delay in seconds (default: 10s for non-invasive)",
)
@click.option(
"--silent",
"-s",
is_flag=True,
default=False,
help="Run silently in background without output",
)
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
@click.option('--delay', '-d', type=float, default=10.0,
help='Update delay in seconds (default: 10s for non-invasive)')
@click.option('--silent', '-s', is_flag=True, default=False,
help='Run silently in background without output')
def watch(path: str, delay: float, silent: bool):
"""Watch for file changes and update index automatically (non-invasive by default)."""
project_path = Path(path).resolve()
# Check if indexed
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
if not silent:
console.print("[red]Error:[/red] Project not indexed. Run 'rag-mini init' first.")
sys.exit(1)
try:
# Always use non-invasive watcher
watcher = NonInvasiveFileWatcher(project_path)
# Only show startup messages if not silent
if not silent:
console.print(f"\n[bold green]🕊️ Non-Invasive Watcher:[/bold green] {project_path}")
console.print("[dim]Low CPU/memory usage - won't interfere with development[/dim]")
console.print(f"[dim]Update delay: {delay}s[/dim]")
console.print("\n[yellow]Press Ctrl+C to stop watching[/yellow]\n")
# Start watching
watcher.start()
if silent:
# Silent mode: just wait for interrupt without any output
try:
@ -473,10 +448,10 @@ def watch(path: str, delay: float, silent: bool):
while True:
try:
time.sleep(1)
# Get current statistics
stats = watcher.get_statistics()
# Only update display if something changed
if stats != last_stats:
# Clear previous line
@ -484,28 +459,26 @@ def watch(path: str, delay: float, silent: bool):
f"\r[green]✓[/green] Files updated: {stats.get('files_processed', 0)} | "
f"[red]✗[/red] Failed: {stats.get('files_dropped', 0)} | "
f"[cyan]⧗[/cyan] Queue: {stats['queue_size']}",
end="",
end=""
)
last_stats = stats
except KeyboardInterrupt:
break
# Stop watcher
if not silent:
console.print("\n\n[yellow]Stopping watcher...[/yellow]")
watcher.stop()
# Show final stats only if not silent
if not silent:
final_stats = watcher.get_statistics()
console.print("\n[bold green]Watch Summary:[/bold green]")
console.print(f"\n[bold green]Watch Summary:[/bold green]")
console.print(f"Files updated: {final_stats.get('files_processed', 0)}")
console.print(f"Files failed: {final_stats.get('files_dropped', 0)}")
console.print(
f"Total runtime: {final_stats.get('uptime_seconds', 0):.1f} seconds\n"
)
console.print(f"Total runtime: {final_stats.get('uptime_seconds', 0):.1f} seconds\n")
except Exception as e:
console.print(f"\n[bold red]Error:[/bold red] {e}")
logger.exception("Watch failed")
@ -513,81 +486,86 @@ def watch(path: str, delay: float, silent: bool):
@cli.command()
@click.argument("function_name")
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option("--top-k", "-k", type=int, default=5, help="Maximum results")
@click.argument('function_name')
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
@click.option('--top-k', '-k', type=int, default=5,
help='Maximum results')
def find_function(function_name: str, path: str, top_k: int):
"""Find a specific function by name."""
project_path = Path(path).resolve()
try:
searcher = CodeSearcher(project_path)
results = searcher.get_function(function_name, top_k=top_k)
if results:
searcher.display_results(results, show_content=True)
else:
console.print(f"[yellow]No functions found matching: {function_name}[/yellow]")
except Exception as e:
console.print(f"[red]Error:[/red] {e}")
sys.exit(1)
@cli.command()
@click.argument("class_name")
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option("--top-k", "-k", type=int, default=5, help="Maximum results")
@click.argument('class_name')
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
@click.option('--top-k', '-k', type=int, default=5,
help='Maximum results')
def find_class(class_name: str, path: str, top_k: int):
"""Find a specific class by name."""
project_path = Path(path).resolve()
try:
searcher = CodeSearcher(project_path)
results = searcher.get_class(class_name, top_k=top_k)
if results:
searcher.display_results(results, show_content=True)
else:
console.print(f"[yellow]No classes found matching: {class_name}[/yellow]")
except Exception as e:
console.print(f"[red]Error:[/red] {e}")
sys.exit(1)
@cli.command()
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
def update(path: str):
"""Update index for changed files."""
project_path = Path(path).resolve()
# Check if indexed
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
console.print("[red]Error:[/red] Project not indexed. Run 'rag-mini init' first.")
sys.exit(1)
try:
indexer = ProjectIndexer(project_path)
console.print(f"\n[cyan]Checking for changes in {project_path}...[/cyan]\n")
stats = indexer.index_project(force_reindex=False)
if stats["files_indexed"] > 0:
if stats['files_indexed'] > 0:
console.print(f"[green][/green] Updated {stats['files_indexed']} files")
console.print(f"Created {stats['chunks_created']} new chunks")
else:
console.print("[green] All files are up to date![/green]")
except Exception as e:
console.print(f"[red]Error:[/red] {e}")
sys.exit(1)
@cli.command()
@click.option("--show-code", "-c", is_flag=True, help="Show example code")
@click.option('--show-code', '-c', is_flag=True, help='Show example code')
def info(show_code: bool):
"""Show information about Mini RAG."""
# Create info panel
@ -612,13 +590,13 @@ def info(show_code: bool):
• Search: <50ms latency
• Storage: ~200MB for 10k files
"""
panel = Panel(info_text, title="About Mini RAG", border_style="cyan")
console.print(panel)
if show_code:
console.print("\n[bold]Example Usage:[/bold]\n")
code = """# Initialize a project
rag-mini init
@ -635,30 +613,32 @@ rag-mini watch
# Get statistics
rag-mini stats"""
syntax = Syntax(code, "bash", theme="monokai")
console.print(syntax)
@cli.command()
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option("--port", type=int, default=7777, help="Server port")
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
@click.option('--port', type=int, default=7777,
help='Server port')
def server(path: str, port: int):
"""Start persistent RAG server (keeps model loaded)."""
project_path = Path(path).resolve()
# Check if indexed
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
console.print("[red]Error:[/red] Project not indexed. Run 'rag-mini init' first.")
sys.exit(1)
try:
console.print(f"[bold cyan]Starting RAG server for:[/bold cyan] {project_path}")
console.print(f"[dim]Port: {port}[/dim]\n")
start_server(project_path, port)
except KeyboardInterrupt:
console.print("\n[yellow]Server stopped by user[/yellow]")
except Exception as e:
@ -668,67 +648,65 @@ def server(path: str, port: int):
@cli.command()
@click.option("--path", "-p", type=click.Path(exists=True), default=".", help="Project path")
@click.option("--port", type=int, default=7777, help="Server port")
@click.option("--discovery", "-d", is_flag=True, help="Run codebase discovery analysis")
@click.option('--path', '-p', type=click.Path(exists=True), default='.',
help='Project path')
@click.option('--port', type=int, default=7777,
help='Server port')
@click.option('--discovery', '-d', is_flag=True,
help='Run codebase discovery analysis')
def status(path: str, port: int, discovery: bool):
"""Show comprehensive RAG system status with optional codebase discovery."""
project_path = Path(path).resolve()
# Print header
console.print(f"\n[bold cyan]RAG System Status for:[/bold cyan] {project_path.name}")
console.print(f"[dim]Path: {project_path}[/dim]\n")
# Check folder contents
console.print("[bold]📁 Folder Contents:[/bold]")
try:
all_files = list(project_path.rglob("*"))
source_files = [
f
for f in all_files
if f.is_file()
and f.suffix in [".py", ".js", ".ts", ".go", ".java", ".cpp", ".c", ".h"]
]
source_files = [f for f in all_files if f.is_file() and f.suffix in ['.py', '.js', '.ts', '.go', '.java', '.cpp', '.c', '.h']]
console.print(f" • Total files: {len([f for f in all_files if f.is_file()])}")
console.print(f" • Source files: {len(source_files)}")
console.print(f" • Directories: {len([f for f in all_files if f.is_dir()])}")
except Exception as e:
console.print(f" [red]Error reading folder: {e}[/red]")
# Check index status
console.print("\n[bold]🗂️ Index Status:[/bold]")
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if rag_dir.exists():
try:
indexer = ProjectIndexer(project_path)
index_stats = indexer.get_statistics()
console.print(" • Status: [green]✅ Indexed[/green]")
console.print(f" • Status: [green]✅ Indexed[/green]")
console.print(f" • Files indexed: {index_stats['file_count']}")
console.print(f" • Total chunks: {index_stats['chunk_count']}")
console.print(f" • Index size: {index_stats['index_size_mb']:.2f} MB")
console.print(f" • Last updated: {index_stats['indexed_at'] or 'Never'}")
except Exception as e:
console.print(" • Status: [yellow]⚠️ Index exists but has issues[/yellow]")
console.print(f" • Status: [yellow]⚠️ Index exists but has issues[/yellow]")
console.print(f" • Error: {e}")
else:
console.print(" • Status: [red]❌ Not indexed[/red]")
console.print(" • Run 'rag-mini init' to initialize")
# Check server status
console.print("\n[bold]🚀 Server Status:[/bold]")
client = RAGClient(port)
if client.is_running():
console.print(f" • Status: [green]✅ Running on port {port}[/green]")
# Try to get server info
try:
response = client.search("test", top_k=1) # Minimal query to get stats
if response.get("success"):
uptime = response.get("server_uptime", 0)
queries = response.get("total_queries", 0)
if response.get('success'):
uptime = response.get('server_uptime', 0)
queries = response.get('total_queries', 0)
console.print(f" • Uptime: {uptime}s")
console.print(f" • Total queries: {queries}")
except Exception as e:
@ -736,51 +714,47 @@ def status(path: str, port: int, discovery: bool):
else:
console.print(f" • Status: [red]❌ Not running on port {port}[/red]")
console.print(" • Run 'rag-mini server' to start the server")
# Run codebase discovery if requested
if discovery and rag_dir.exists():
console.print("\n[bold]🧠 Codebase Discovery:[/bold]")
try:
# Import and run intelligent discovery
import sys
# Add tools directory to path
# Add tools directory to path
tools_path = Path(__file__).parent.parent.parent / "tools"
if tools_path.exists():
sys.path.insert(0, str(tools_path))
from intelligent_codebase_discovery import IntelligentCodebaseDiscovery
discovery_system = IntelligentCodebaseDiscovery(project_path)
discovery_system.run_lightweight_discovery()
else:
console.print(" [yellow]Discovery system not found[/yellow]")
except Exception as e:
console.print(f" [red]Discovery failed: {e}[/red]")
elif discovery and not rag_dir.exists():
console.print("\n[bold]🧠 Codebase Discovery:[/bold]")
console.print(" [yellow]❌ Cannot run discovery - project not indexed[/yellow]")
console.print(" Run 'rag-mini init' first to initialize the system")
# Show next steps
console.print("\n[bold]📋 Next Steps:[/bold]")
if not rag_dir.exists():
console.print(" 1. Run [cyan]rag-mini init[/cyan] to initialize the RAG system")
console.print(' 2. Use [cyan]rag-mini search "your query"[/cyan] to search code')
console.print(" 2. Use [cyan]rag-mini search \"your query\"[/cyan] to search code")
elif not client.is_running():
console.print(" 1. Run [cyan]rag-mini server[/cyan] to start the server")
console.print(' 2. Use [cyan]rag-mini search "your query"[/cyan] to search code')
console.print(" 2. Use [cyan]rag-mini search \"your query\"[/cyan] to search code")
else:
console.print(
' • System ready! Use [cyan]rag-mini search "your query"[/cyan] to search'
)
console.print(
" • Add [cyan]--discovery[/cyan] flag to run intelligent codebase analysis"
)
console.print(" • System ready! Use [cyan]rag-mini search \"your query\"[/cyan] to search")
console.print(" • Add [cyan]--discovery[/cyan] flag to run intelligent codebase analysis")
console.print()
if __name__ == "__main__":
cli()
if __name__ == '__main__':
cli()

516
mini_rag/config.py
View File

@ -3,14 +3,11 @@ Configuration management for FSS-Mini-RAG.
Handles loading, saving, and validation of YAML config files.
"""
import logging
import re
from dataclasses import asdict, dataclass
from pathlib import Path
from typing import Any, Dict, List, Optional
import yaml
import requests
import logging
from pathlib import Path
from typing import Dict, Any, Optional
from dataclasses import dataclass, asdict
logger = logging.getLogger(__name__)
@ -18,7 +15,6 @@ logger = logging.getLogger(__name__)
@dataclass
class ChunkingConfig:
"""Configuration for text chunking."""
max_size: int = 2000
min_size: int = 150
strategy: str = "semantic" # "semantic" or "fixed"
@ -27,7 +23,6 @@ class ChunkingConfig:
@dataclass
class StreamingConfig:
"""Configuration for large file streaming."""
enabled: bool = True
threshold_bytes: int = 1048576 # 1MB
@ -35,22 +30,21 @@ class StreamingConfig:
@dataclass
class FilesConfig:
"""Configuration for file processing."""
min_file_size: int = 50
exclude_patterns: list = None
include_patterns: list = None
def __post_init__(self):
if self.exclude_patterns is None:
self.exclude_patterns = [
"node_modules/**",
".git/**",
".git/**",
"__pycache__/**",
"*.pyc",
".venv/**",
"venv/**",
"build/**",
"dist/**",
"dist/**"
]
if self.include_patterns is None:
self.include_patterns = ["**/*"] # Include everything by default
@ -59,7 +53,6 @@ class FilesConfig:
@dataclass
class EmbeddingConfig:
"""Configuration for embedding generation."""
preferred_method: str = "ollama" # "ollama", "ml", "hash", "auto"
ollama_model: str = "nomic-embed-text"
ollama_host: str = "localhost:11434"
@ -70,51 +63,52 @@ class EmbeddingConfig:
@dataclass
class SearchConfig:
"""Configuration for search behavior."""
default_top_k: int = 10
enable_bm25: bool = True
similarity_threshold: float = 0.1
expand_queries: bool = False # Enable automatic query expansion
@dataclass
@dataclass
class LLMConfig:
"""Configuration for LLM synthesis and query expansion."""
# Core settings
synthesis_model: str = "auto" # "auto", "qwen3:1.7b", "qwen2.5:1.5b", etc.
expansion_model: str = "auto" # Usually same as synthesis_model
max_expansion_terms: int = 8 # Maximum additional terms to add
enable_synthesis: bool = False # Enable by default when --synthesize used
max_expansion_terms: int = 8 # Maximum additional terms to add
enable_synthesis: bool = False # Enable by default when --synthesize used
synthesis_temperature: float = 0.3
enable_thinking: bool = True # Enable thinking mode for Qwen3 models
cpu_optimized: bool = True # Prefer lightweight models
cpu_optimized: bool = True # Prefer lightweight models
# Context window configuration (critical for RAG performance)
context_window: int = 16384 # Context window size in tokens (16K recommended)
auto_context: bool = True # Auto-adjust context based on model capabilities
context_window: int = 16384 # Context window size in tokens (16K recommended)
auto_context: bool = True # Auto-adjust context based on model capabilities
# Model preference rankings (configurable)
model_rankings: list = None # Will be set in __post_init__
model_rankings: list = None # Will be set in __post_init__
# Provider-specific settings (for different LLM providers)
provider: str = "ollama" # "ollama", "openai", "anthropic"
provider: str = "ollama" # "ollama", "openai", "anthropic"
ollama_host: str = "localhost:11434" # Ollama connection
api_key: Optional[str] = None # API key for cloud providers
api_base: Optional[str] = None # Base URL for API (e.g., OpenRouter)
timeout: int = 20 # Request timeout in seconds
api_base: Optional[str] = None # Base URL for API (e.g., OpenRouter)
timeout: int = 20 # Request timeout in seconds
def __post_init__(self):
if self.model_rankings is None:
# Default model preference rankings (can be overridden in config file)
self.model_rankings = [
# Testing model (prioritized for current testing phase)
"qwen3:1.7b",
# Ultra-efficient models (perfect for CPU-only systems)
"qwen3:0.6b",
"qwen3:0.6b",
# Recommended model (excellent quality but larger)
"qwen3:4b",
# Common fallbacks (prioritize Qwen models)
# Common fallbacks (prioritize Qwen models)
"qwen2.5:1.5b",
"qwen2.5:3b",
]
@ -123,26 +117,24 @@ class LLMConfig:
@dataclass
class UpdateConfig:
"""Configuration for auto-update system."""
auto_check: bool = True # Check for updates automatically
auto_check: bool = True # Check for updates automatically
check_frequency_hours: int = 24 # How often to check (hours)
auto_install: bool = False # Auto-install without asking (not recommended)
backup_before_update: bool = True # Create backup before updating
notify_beta_releases: bool = False # Include beta/pre-releases
auto_install: bool = False # Auto-install without asking (not recommended)
backup_before_update: bool = True # Create backup before updating
notify_beta_releases: bool = False # Include beta/pre-releases
@dataclass
class RAGConfig:
"""Main RAG system configuration."""
chunking: ChunkingConfig = None
streaming: StreamingConfig = None
streaming: StreamingConfig = None
files: FilesConfig = None
embedding: EmbeddingConfig = None
search: SearchConfig = None
llm: LLMConfig = None
updates: UpdateConfig = None
def __post_init__(self):
if self.chunking is None:
self.chunking = ChunkingConfig()
@ -162,227 +154,12 @@ class RAGConfig:
class ConfigManager:
"""Manages configuration loading, saving, and validation."""
def __init__(self, project_path: Path):
self.project_path = Path(project_path)
self.rag_dir = self.project_path / ".mini-rag"
self.config_path = self.rag_dir / "config.yaml"
def get_available_ollama_models(self, ollama_host: str = "localhost:11434") -> List[str]:
"""Get list of available Ollama models for validation with secure connection handling."""
import time
self.rag_dir = self.project_path / '.mini-rag'
self.config_path = self.rag_dir / 'config.yaml'
# Retry logic with exponential backoff
max_retries = 3
for attempt in range(max_retries):
try:
# Use explicit timeout and SSL verification for security
response = requests.get(
f"http://{ollama_host}/api/tags",
timeout=(5, 10), # (connect_timeout, read_timeout)
verify=True, # Explicit SSL verification
allow_redirects=False # Prevent redirect attacks
)
if response.status_code == 200:
data = response.json()
models = [model["name"] for model in data.get("models", [])]
logger.debug(f"Successfully fetched {len(models)} Ollama models")
return models
else:
logger.debug(f"Ollama API returned status {response.status_code}")
except requests.exceptions.SSLError as e:
logger.debug(f"SSL verification failed for Ollama connection: {e}")
# For local Ollama, SSL might not be configured - this is expected
if "localhost" in ollama_host or "127.0.0.1" in ollama_host:
logger.debug("Retrying with local connection (SSL not required for localhost)")
# Local connections don't need SSL verification
try:
response = requests.get(f"http://{ollama_host}/api/tags", timeout=(5, 10))
if response.status_code == 200:
data = response.json()
return [model["name"] for model in data.get("models", [])]
except Exception as local_e:
logger.debug(f"Local Ollama connection also failed: {local_e}")
break # Don't retry SSL errors for remote hosts
except requests.exceptions.Timeout as e:
logger.debug(f"Ollama connection timeout (attempt {attempt + 1}/{max_retries}): {e}")
if attempt < max_retries - 1:
sleep_time = (2 ** attempt) # Exponential backoff
time.sleep(sleep_time)
continue
except requests.exceptions.ConnectionError as e:
logger.debug(f"Ollama connection error (attempt {attempt + 1}/{max_retries}): {e}")
if attempt < max_retries - 1:
time.sleep(1)
continue
except Exception as e:
logger.debug(f"Unexpected error fetching Ollama models: {e}")
break
return []
def _sanitize_model_name(self, model_name: str) -> str:
"""Sanitize model name to prevent injection attacks."""
if not model_name:
return ""
# Allow only alphanumeric, dots, colons, hyphens, underscores
# This covers legitimate model names like qwen3:1.7b-q8_0
sanitized = re.sub(r'[^a-zA-Z0-9\.\:\-\_]', '', model_name)
# Limit length to prevent DoS
if len(sanitized) > 128:
logger.warning(f"Model name too long, truncating: {sanitized[:20]}...")
sanitized = sanitized[:128]
return sanitized
def resolve_model_name(self, configured_model: str, available_models: List[str]) -> Optional[str]:
"""Resolve configured model name to actual available model with input sanitization."""
if not available_models or not configured_model:
return None
# Sanitize input to prevent injection
configured_model = self._sanitize_model_name(configured_model)
if not configured_model:
logger.warning("Model name was empty after sanitization")
return None
# Handle special 'auto' directive
if configured_model.lower() == 'auto':
return available_models[0] if available_models else None
# Direct exact match first (case-insensitive)
for available_model in available_models:
if configured_model.lower() == available_model.lower():
return available_model
# Fuzzy matching for common patterns
model_patterns = self._get_model_patterns(configured_model)
for pattern in model_patterns:
for available_model in available_models:
if pattern.lower() in available_model.lower():
# Additional validation: ensure it's not a partial match of something else
if self._validate_model_match(pattern, available_model):
return available_model
return None # Model not available
def _get_model_patterns(self, configured_model: str) -> List[str]:
"""Generate fuzzy match patterns for common model naming conventions."""
patterns = [configured_model] # Start with exact name
# Common quantization patterns for different models
quantization_patterns = {
'qwen3:1.7b': ['qwen3:1.7b-q8_0', 'qwen3:1.7b-q4_0', 'qwen3:1.7b-q6_k'],
'qwen3:0.6b': ['qwen3:0.6b-q8_0', 'qwen3:0.6b-q4_0', 'qwen3:0.6b-q6_k'],
'qwen3:4b': ['qwen3:4b-q8_0', 'qwen3:4b-q4_0', 'qwen3:4b-q6_k'],
'qwen3:8b': ['qwen3:8b-q8_0', 'qwen3:8b-q4_0', 'qwen3:8b-q6_k'],
'qwen2.5:1.5b': ['qwen2.5:1.5b-q8_0', 'qwen2.5:1.5b-q4_0'],
'qwen2.5:3b': ['qwen2.5:3b-q8_0', 'qwen2.5:3b-q4_0'],
'qwen2.5-coder:1.5b': ['qwen2.5-coder:1.5b-q8_0', 'qwen2.5-coder:1.5b-q4_0'],
'qwen2.5-coder:3b': ['qwen2.5-coder:3b-q8_0', 'qwen2.5-coder:3b-q4_0'],
'qwen2.5-coder:7b': ['qwen2.5-coder:7b-q8_0', 'qwen2.5-coder:7b-q4_0'],
}
# Add specific patterns for the configured model
if configured_model.lower() in quantization_patterns:
patterns.extend(quantization_patterns[configured_model.lower()])
# Generic pattern generation for unknown models
if ':' in configured_model:
base_name, version = configured_model.split(':', 1)
# Add common quantization suffixes
common_suffixes = ['-q8_0', '-q4_0', '-q6_k', '-q4_k_m', '-instruct', '-base']
for suffix in common_suffixes:
patterns.append(f"{base_name}:{version}{suffix}")
# Also try with instruct variants
if 'instruct' not in version.lower():
patterns.append(f"{base_name}:{version}-instruct")
patterns.append(f"{base_name}:{version}-instruct-q8_0")
patterns.append(f"{base_name}:{version}-instruct-q4_0")
return patterns
def _validate_model_match(self, pattern: str, available_model: str) -> bool:
"""Validate that a fuzzy match is actually correct and not a false positive."""
# Convert to lowercase for comparison
pattern_lower = pattern.lower()
available_lower = available_model.lower()
# Ensure the base model name matches
if ':' in pattern_lower and ':' in available_lower:
pattern_base = pattern_lower.split(':')[0]
available_base = available_lower.split(':')[0]
# Base names must match exactly
if pattern_base != available_base:
return False
# Version part should be contained or closely related
pattern_version = pattern_lower.split(':', 1)[1]
available_version = available_lower.split(':', 1)[1]
# The pattern version should be a prefix of the available version
# e.g., "1.7b" should match "1.7b-q8_0" but not "11.7b"
if not available_version.startswith(pattern_version.split('-')[0]):
return False
return True
def validate_and_resolve_models(self, config: RAGConfig) -> RAGConfig:
"""Validate and resolve model names in configuration."""
try:
available_models = self.get_available_ollama_models(config.llm.ollama_host)
if not available_models:
logger.debug("No Ollama models available for validation")
return config
# Resolve synthesis model
if config.llm.synthesis_model != "auto":
resolved = self.resolve_model_name(config.llm.synthesis_model, available_models)
if resolved and resolved != config.llm.synthesis_model:
logger.info(f"Resolved synthesis model: {config.llm.synthesis_model} -> {resolved}")
config.llm.synthesis_model = resolved
elif not resolved:
logger.warning(f"Synthesis model '{config.llm.synthesis_model}' not found, keeping original")
# Resolve expansion model (if different from synthesis)
if (config.llm.expansion_model != "auto" and
config.llm.expansion_model != config.llm.synthesis_model):
resolved = self.resolve_model_name(config.llm.expansion_model, available_models)
if resolved and resolved != config.llm.expansion_model:
logger.info(f"Resolved expansion model: {config.llm.expansion_model} -> {resolved}")
config.llm.expansion_model = resolved
elif not resolved:
logger.warning(f"Expansion model '{config.llm.expansion_model}' not found, keeping original")
# Update model rankings with resolved names
if config.llm.model_rankings:
updated_rankings = []
for model in config.llm.model_rankings:
resolved = self.resolve_model_name(model, available_models)
if resolved:
updated_rankings.append(resolved)
if resolved != model:
logger.debug(f"Updated model ranking: {model} -> {resolved}")
else:
updated_rankings.append(model) # Keep original if not resolved
config.llm.model_rankings = updated_rankings
except Exception as e:
logger.debug(f"Model validation failed: {e}")
return config
def load_config(self) -> RAGConfig:
"""Load configuration from YAML file or create default."""
if not self.config_path.exists():
@ -390,84 +167,57 @@ class ConfigManager:
config = RAGConfig()
self.save_config(config)
return config
try:
with open(self.config_path, "r") as f:
with open(self.config_path, 'r') as f:
data = yaml.safe_load(f)
if not data:
logger.warning("Empty config file, using defaults")
return RAGConfig()
# Convert nested dicts back to dataclass instances
config = RAGConfig()
if "chunking" in data:
config.chunking = ChunkingConfig(**data["chunking"])
if "streaming" in data:
config.streaming = StreamingConfig(**data["streaming"])
if "files" in data:
config.files = FilesConfig(**data["files"])
if "embedding" in data:
config.embedding = EmbeddingConfig(**data["embedding"])
if "search" in data:
config.search = SearchConfig(**data["search"])
if "llm" in data:
config.llm = LLMConfig(**data["llm"])
# Validate and resolve model names if Ollama is available
config = self.validate_and_resolve_models(config)
if 'chunking' in data:
config.chunking = ChunkingConfig(**data['chunking'])
if 'streaming' in data:
config.streaming = StreamingConfig(**data['streaming'])
if 'files' in data:
config.files = FilesConfig(**data['files'])
if 'embedding' in data:
config.embedding = EmbeddingConfig(**data['embedding'])
if 'search' in data:
config.search = SearchConfig(**data['search'])
if 'llm' in data:
config.llm = LLMConfig(**data['llm'])
return config
except yaml.YAMLError as e:
# YAML syntax error - help user fix it instead of silent fallback
error_msg = (
f"⚠️ Config file has YAML syntax error at line "
f"{getattr(e, 'problem_mark', 'unknown')}: {e}"
)
logger.error(error_msg)
print(f"\n{error_msg}")
print(f"Config file: {self.config_path}")
print("💡 Check YAML syntax (indentation, quotes, colons)")
print("💡 Or delete config file to reset to defaults")
return RAGConfig() # Still return defaults but warn user
except Exception as e:
logger.error(f"Failed to load config from {self.config_path}: {e}")
logger.info("Using default configuration")
return RAGConfig()
def save_config(self, config: RAGConfig):
"""Save configuration to YAML file with comments."""
try:
self.rag_dir.mkdir(exist_ok=True)
# Convert to dict for YAML serialization
config_dict = asdict(config)
# Create YAML content with comments
yaml_content = self._create_yaml_with_comments(config_dict)
# Write with basic file locking to prevent corruption
with open(self.config_path, "w") as f:
try:
import fcntl
fcntl.flock(
f.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB
) # Non-blocking exclusive lock
f.write(yaml_content)
fcntl.flock(f.fileno(), fcntl.LOCK_UN) # Unlock
except (OSError, ImportError):
# Fallback for Windows or if fcntl unavailable
f.write(yaml_content)
with open(self.config_path, 'w') as f:
f.write(yaml_content)
logger.info(f"Configuration saved to {self.config_path}")
except Exception as e:
logger.error(f"Failed to save config to {self.config_path}: {e}")
def _create_yaml_with_comments(self, config_dict: Dict[str, Any]) -> str:
"""Create YAML content with helpful comments."""
yaml_lines = [
@ -477,97 +227,89 @@ class ConfigManager:
"",
"# Text chunking settings",
"chunking:",
f" max_size: {config_dict['chunking']['max_size']} # Max chars per chunk",
f" min_size: {config_dict['chunking']['min_size']} # Min chars per chunk",
f" strategy: {config_dict['chunking']['strategy']} # 'semantic' or 'fixed'",
f" max_size: {config_dict['chunking']['max_size']} # Maximum characters per chunk",
f" min_size: {config_dict['chunking']['min_size']} # Minimum characters per chunk",
f" strategy: {config_dict['chunking']['strategy']} # 'semantic' (language-aware) or 'fixed'",
"",
"# Large file streaming settings",
"# Large file streaming settings",
"streaming:",
f" enabled: {str(config_dict['streaming']['enabled']).lower()}",
f" threshold_bytes: {config_dict['streaming']['threshold_bytes']} # Stream files >1MB",
f" threshold_bytes: {config_dict['streaming']['threshold_bytes']} # Files larger than this use streaming (1MB)",
"",
"# File processing settings",
"files:",
f" min_file_size: {config_dict['files']['min_file_size']} # Skip small files",
f" min_file_size: {config_dict['files']['min_file_size']} # Skip files smaller than this",
" exclude_patterns:",
]
for pattern in config_dict["files"]["exclude_patterns"]:
yaml_lines.append(f' - "{pattern}"')
yaml_lines.extend(
[
" include_patterns:",
' - "**/*" # Include all files by default',
"",
"# Embedding generation settings",
"embedding:",
f" preferred_method: {config_dict['embedding']['preferred_method']} # Method",
f" ollama_model: {config_dict['embedding']['ollama_model']}",
f" ollama_host: {config_dict['embedding']['ollama_host']}",
f" ml_model: {config_dict['embedding']['ml_model']}",
f" batch_size: {config_dict['embedding']['batch_size']} # Per batch",
"",
"# Search behavior settings",
"search:",
f" default_top_k: {config_dict['search']['default_top_k']} # Top results",
f" enable_bm25: {str(config_dict['search']['enable_bm25']).lower()} # Keyword boost",
f" similarity_threshold: {config_dict['search']['similarity_threshold']} # Min score",
f" expand_queries: {str(config_dict['search']['expand_queries']).lower()} # Auto expand",
"",
"# LLM synthesis and query expansion settings",
"llm:",
f" ollama_host: {config_dict['llm']['ollama_host']}",
f" synthesis_model: {config_dict['llm']['synthesis_model']} # Model name",
f" expansion_model: {config_dict['llm']['expansion_model']} # Model name",
f" max_expansion_terms: {config_dict['llm']['max_expansion_terms']} # Max terms",
f" enable_synthesis: {str(config_dict['llm']['enable_synthesis']).lower()} # Enable synthesis by default",
f" synthesis_temperature: {config_dict['llm']['synthesis_temperature']} # LLM temperature for analysis",
"",
" # Context window configuration (critical for RAG performance)",
" # 💡 Sizing guide: 2K=1 question, 4K=1-2 questions, 8K=manageable, 16K=most users",
" # 32K=large codebases, 64K+=power users only",
" # ⚠️ Larger contexts use exponentially more CPU/memory - only increase if needed",
" # 🔧 Low context limits? Try smaller topk, better search terms, or archive noise",
f" context_window: {config_dict['llm']['context_window']} # Context size in tokens",
f" auto_context: {str(config_dict['llm']['auto_context']).lower()} # Auto-adjust context based on model capabilities",
"",
" model_rankings: # Preferred model order (edit to change priority)",
]
)
for pattern in config_dict['files']['exclude_patterns']:
yaml_lines.append(f" - \"{pattern}\"")
yaml_lines.extend([
" include_patterns:",
" - \"**/*\" # Include all files by default",
"",
"# Embedding generation settings",
"embedding:",
f" preferred_method: {config_dict['embedding']['preferred_method']} # 'ollama', 'ml', 'hash', or 'auto'",
f" ollama_model: {config_dict['embedding']['ollama_model']}",
f" ollama_host: {config_dict['embedding']['ollama_host']}",
f" ml_model: {config_dict['embedding']['ml_model']}",
f" batch_size: {config_dict['embedding']['batch_size']} # Embeddings processed per batch",
"",
"# Search behavior settings",
"search:",
f" default_top_k: {config_dict['search']['default_top_k']} # Default number of top results",
f" enable_bm25: {str(config_dict['search']['enable_bm25']).lower()} # Enable keyword matching boost",
f" similarity_threshold: {config_dict['search']['similarity_threshold']} # Minimum similarity score",
f" expand_queries: {str(config_dict['search']['expand_queries']).lower()} # Enable automatic query expansion",
"",
"# LLM synthesis and query expansion settings",
"llm:",
f" ollama_host: {config_dict['llm']['ollama_host']}",
f" synthesis_model: {config_dict['llm']['synthesis_model']} # 'auto', 'qwen3:1.7b', etc.",
f" expansion_model: {config_dict['llm']['expansion_model']} # Usually same as synthesis_model",
f" max_expansion_terms: {config_dict['llm']['max_expansion_terms']} # Maximum terms to add to queries",
f" enable_synthesis: {str(config_dict['llm']['enable_synthesis']).lower()} # Enable synthesis by default",
f" synthesis_temperature: {config_dict['llm']['synthesis_temperature']} # LLM temperature for analysis",
"",
" # Context window configuration (critical for RAG performance)",
f" context_window: {config_dict['llm']['context_window']} # Context size in tokens (8K=fast, 16K=balanced, 32K=advanced)",
f" auto_context: {str(config_dict['llm']['auto_context']).lower()} # Auto-adjust context based on model capabilities",
"",
" model_rankings: # Preferred model order (edit to change priority)",
])
# Add model rankings list
if "model_rankings" in config_dict["llm"] and config_dict["llm"]["model_rankings"]:
for model in config_dict["llm"]["model_rankings"][:10]: # Show first 10
yaml_lines.append(f' - "{model}"')
if len(config_dict["llm"]["model_rankings"]) > 10:
if 'model_rankings' in config_dict['llm'] and config_dict['llm']['model_rankings']:
for model in config_dict['llm']['model_rankings'][:10]: # Show first 10
yaml_lines.append(f" - \"{model}\"")
if len(config_dict['llm']['model_rankings']) > 10:
yaml_lines.append(" # ... (edit config to see all options)")
# Add update settings
yaml_lines.extend(
[
"",
"# Auto-update system settings",
"updates:",
f" auto_check: {str(config_dict['updates']['auto_check']).lower()} # Check for updates automatically",
f" check_frequency_hours: {config_dict['updates']['check_frequency_hours']} # Hours between update checks",
f" auto_install: {str(config_dict['updates']['auto_install']).lower()} # Auto-install updates (not recommended)",
f" backup_before_update: {str(config_dict['updates']['backup_before_update']).lower()} # Create backup before updating",
f" notify_beta_releases: {str(config_dict['updates']['notify_beta_releases']).lower()} # Include beta releases in checks",
]
)
return "\n".join(yaml_lines)
yaml_lines.extend([
"",
"# Auto-update system settings",
"updates:",
f" auto_check: {str(config_dict['updates']['auto_check']).lower()} # Check for updates automatically",
f" check_frequency_hours: {config_dict['updates']['check_frequency_hours']} # Hours between update checks",
f" auto_install: {str(config_dict['updates']['auto_install']).lower()} # Auto-install updates (not recommended)",
f" backup_before_update: {str(config_dict['updates']['backup_before_update']).lower()} # Create backup before updating",
f" notify_beta_releases: {str(config_dict['updates']['notify_beta_releases']).lower()} # Include beta releases in checks",
])
return '\n'.join(yaml_lines)
def update_config(self, **kwargs) -> RAGConfig:
"""Update specific configuration values."""
config = self.load_config()
for key, value in kwargs.items():
if hasattr(config, key):
setattr(config, key, value)
else:
logger.warning(f"Unknown config key: {key}")
self.save_config(config)
return config
return config

418
mini_rag/explorer.py
View File

@ -9,173 +9,155 @@ Perfect for exploring codebases with detailed reasoning and follow-up questions.
import json
import logging
import time
from dataclasses import dataclass
from typing import List, Dict, Any, Optional
from pathlib import Path
from typing import Any, Dict, List, Optional
from dataclasses import dataclass
try:
from .config import RAGConfig
from .llm_synthesizer import LLMSynthesizer, SynthesisResult
from .search import CodeSearcher
from .system_context import get_system_context
from .config import RAGConfig
except ImportError:
# For direct testing
from config import RAGConfig
from llm_synthesizer import LLMSynthesizer, SynthesisResult
from search import CodeSearcher
def get_system_context(x=None):
return ""
from config import RAGConfig
logger = logging.getLogger(__name__)
@dataclass
class ExplorationSession:
"""Track an exploration session with context history."""
project_path: Path
conversation_history: List[Dict[str, Any]]
session_id: str
started_at: float
def add_exchange(
self, question: str, search_results: List[Any], response: SynthesisResult
):
def add_exchange(self, question: str, search_results: List[Any], response: SynthesisResult):
"""Add a question/response exchange to the conversation history."""
self.conversation_history.append(
{
"timestamp": time.time(),
"question": question,
"search_results_count": len(search_results),
"response": {
"summary": response.summary,
"key_points": response.key_points,
"code_examples": response.code_examples,
"suggested_actions": response.suggested_actions,
"confidence": response.confidence,
},
self.conversation_history.append({
"timestamp": time.time(),
"question": question,
"search_results_count": len(search_results),
"response": {
"summary": response.summary,
"key_points": response.key_points,
"code_examples": response.code_examples,
"suggested_actions": response.suggested_actions,
"confidence": response.confidence
}
)
})
class CodeExplorer:
"""Interactive code exploration with thinking and context memory."""
def __init__(self, project_path: Path, config: RAGConfig = None):
self.project_path = project_path
self.config = config or RAGConfig()
# Initialize components with thinking enabled
self.searcher = CodeSearcher(project_path)
self.synthesizer = LLMSynthesizer(
ollama_url=f"http://{self.config.llm.ollama_host}",
model=self.config.llm.synthesis_model,
enable_thinking=True, # Always enable thinking in explore mode
config=self.config, # Pass config for model rankings
config=self.config # Pass config for model rankings
)
# Session management
self.current_session: Optional[ExplorationSession] = None
def start_exploration_session(self) -> bool:
"""Start a new exploration session."""
# Simple availability check - don't do complex model restart logic
if not self.synthesizer.is_available():
print("❌ LLM service unavailable. Please check Ollama is running.")
return False
session_id = f"explore_{int(time.time())}"
self.current_session = ExplorationSession(
project_path=self.project_path,
conversation_history=[],
session_id=session_id,
started_at=time.time(),
started_at=time.time()
)
print("🧠 Exploration Mode Started")
print(f"Project: {self.project_path.name}")
return True
def explore_question(self, question: str, context_limit: int = 10) -> Optional[str]:
"""Explore a question with full thinking and context."""
if not self.current_session:
return "❌ No exploration session active. Start one first."
# Search for relevant information
search_start = time.time()
results = self.searcher.search(
question,
question,
top_k=context_limit,
include_context=True,
semantic_weight=0.7,
bm25_weight=0.3,
bm25_weight=0.3
)
search_time = time.time() - search_start
# Build enhanced prompt with conversation context
synthesis_prompt = self._build_contextual_prompt(question, results)
# Get thinking-enabled analysis
synthesis_start = time.time()
synthesis = self._synthesize_with_context(synthesis_prompt, results)
synthesis_time = time.time() - synthesis_start
# Add to conversation history
self.current_session.add_exchange(question, results, synthesis)
# Streaming already displayed the response
# Just return minimal status for caller
session_duration = time.time() - self.current_session.started_at
exchange_count = len(self.current_session.conversation_history)
status = f"\n📊 Session: {session_duration/60:.1f}m | Question #{exchange_count} | Results: {len(results)} | Time: {search_time+synthesis_time:.1f}s"
return status
def _build_contextual_prompt(self, question: str, results: List[Any]) -> str:
"""Build a prompt that includes conversation context."""
# Get recent conversation context (last 3 exchanges)
context_summary = ""
if self.current_session.conversation_history:
recent_exchanges = self.current_session.conversation_history[-3:]
context_parts = []
for i, exchange in enumerate(recent_exchanges, 1):
prev_q = exchange["question"]
prev_summary = exchange["response"]["summary"]
context_parts.append(f"Previous Q{i}: {prev_q}")
context_parts.append(f"Previous A{i}: {prev_summary}")
# "\n".join(context_parts) # Unused variable removed
context_summary = "\n".join(context_parts)
# Build search results context
results_context = []
for i, result in enumerate(results[:8], 1):
# result.file_path if hasattr(result, "file_path") else "unknown" # Unused variable removed
# result.content if hasattr(result, "content") else str(result) # Unused variable removed
# result.score if hasattr(result, "score") else 0.0 # Unused variable removed
results_context.append(
"""
file_path = result.file_path if hasattr(result, 'file_path') else 'unknown'
content = result.content if hasattr(result, 'content') else str(result)
score = result.score if hasattr(result, 'score') else 0.0
results_context.append(f"""
Result {i} (Score: {score:.3f}):
File: {file_path}
Content: {content[:800]}{'...' if len(content) > 800 else ''}
"""
)
# "\n".join(results_context) # Unused variable removed
# Get system context for better responses
# get_system_context(self.project_path) # Unused variable removed
""")
results_text = "\n".join(results_context)
# Create comprehensive exploration prompt with thinking
prompt = """<think>
prompt = f"""<think>
The user asked: "{question}"
System context: {system_context}
Let me analyze what they're asking and look at the information I have available.
From the search results, I can see relevant information about:
@ -208,7 +190,7 @@ Please provide a helpful, natural explanation that answers their question. Write
Structure your response to include:
1. A clear explanation of what you found and how it answers their question
2. The most important insights from the information you discovered
2. The most important insights from the information you discovered
3. Relevant examples or code patterns when helpful
4. Practical next steps they could take
@ -221,43 +203,37 @@ Guidelines:
- Use natural language, not structured formats
- Break complex topics into understandable pieces
"""
return prompt
def _synthesize_with_context(self, prompt: str, results: List[Any]) -> SynthesisResult:
"""Synthesize results with full context and thinking."""
try:
# Use streaming with thinking visible (don't collapse)
response = self.synthesizer._call_ollama(
prompt,
temperature=0.2,
disable_thinking=False,
use_streaming=True,
collapse_thinking=False,
)
# "" # Unused variable removed
response = self.synthesizer._call_ollama(prompt, temperature=0.2, disable_thinking=False, use_streaming=True, collapse_thinking=False)
thinking_stream = ""
# Streaming already shows thinking and response
# No need for additional indicators
if not response:
return SynthesisResult(
summary="Analysis unavailable (LLM service error)",
key_points=[],
code_examples=[],
suggested_actions=["Check LLM service status"],
confidence=0.0,
confidence=0.0
)
# Use natural language response directly
return SynthesisResult(
summary=response.strip(),
key_points=[], # Not used with natural language responses
code_examples=[], # Not used with natural language responses
suggested_actions=[], # Not used with natural language responses
confidence=0.85, # High confidence for natural responses
confidence=0.85 # High confidence for natural responses
)
except Exception as e:
logger.error(f"Context synthesis failed: {e}")
return SynthesisResult(
@ -265,153 +241,124 @@ Guidelines:
key_points=[],
code_examples=[],
suggested_actions=["Check system status and try again"],
confidence=0.0,
confidence=0.0
)
def _format_exploration_response(
self,
question: str,
synthesis: SynthesisResult,
result_count: int,
search_time: float,
synthesis_time: float,
) -> str:
def _format_exploration_response(self, question: str, synthesis: SynthesisResult,
result_count: int, search_time: float, synthesis_time: float) -> str:
"""Format exploration response with context indicators."""
output = []
# Header with session context
session_duration = time.time() - self.current_session.started_at
exchange_count = len(self.current_session.conversation_history)
output.append(f"🧠 EXPLORATION ANALYSIS (Question #{exchange_count})")
output.append(
f"Session: {session_duration/60:.1f}m | Results: {result_count} | "
f"Time: {search_time+synthesis_time:.1f}s"
)
output.append(f"Session: {session_duration/60:.1f}m | Results: {result_count} | "
f"Time: {search_time+synthesis_time:.1f}s")
output.append("=" * 60)
output.append("")
# Response was already displayed via streaming
# Just show completion status
output.append("✅ Analysis complete")
output.append("")
output.append("")
# Confidence and context indicator
confidence_emoji = (
"🟢"
if synthesis.confidence > 0.7
else "🟡" if synthesis.confidence > 0.4 else "🔴"
)
context_indicator = (
f" | Context: {exchange_count-1} previous questions" if exchange_count > 1 else ""
)
output.append(
f"{confidence_emoji} Confidence: {synthesis.confidence:.1%}{context_indicator}"
)
confidence_emoji = "🟢" if synthesis.confidence > 0.7 else "🟡" if synthesis.confidence > 0.4 else "🔴"
context_indicator = f" | Context: {exchange_count-1} previous questions" if exchange_count > 1 else ""
output.append(f"{confidence_emoji} Confidence: {synthesis.confidence:.1%}{context_indicator}")
return "\n".join(output)
def get_session_summary(self) -> str:
"""Get a summary of the current exploration session."""
if not self.current_session:
return "No active exploration session."
duration = time.time() - self.current_session.started_at
exchange_count = len(self.current_session.conversation_history)
summary = [
"🧠 EXPLORATION SESSION SUMMARY",
"=" * 40,
f"🧠 EXPLORATION SESSION SUMMARY",
f"=" * 40,
f"Project: {self.project_path.name}",
f"Session ID: {self.current_session.session_id}",
f"Duration: {duration/60:.1f} minutes",
f"Questions explored: {exchange_count}",
"",
f"",
]
if exchange_count > 0:
summary.append("📋 Topics explored:")
for i, exchange in enumerate(self.current_session.conversation_history, 1):
question = (
exchange["question"][:50] + "..."
if len(exchange["question"]) > 50
else exchange["question"]
)
question = exchange["question"][:50] + "..." if len(exchange["question"]) > 50 else exchange["question"]
confidence = exchange["response"]["confidence"]
summary.append(f" {i}. {question} (confidence: {confidence:.1%})")
return "\n".join(summary)
def end_session(self) -> str:
"""End the current exploration session."""
if not self.current_session:
return "No active session to end."
summary = self.get_session_summary()
self.current_session = None
return summary + "\n\n✅ Exploration session ended."
def _check_model_restart_needed(self) -> bool:
"""Check if model restart would improve thinking quality."""
try:
# Simple heuristic: if we can detect the model was recently used
# Simple heuristic: if we can detect the model was recently used
# with <no_think>, suggest restart for better thinking quality
# Test with a simple thinking prompt to see response quality
test_response = self.synthesizer._call_ollama(
"Think briefly: what is 2+2?", temperature=0.1, disable_thinking=False
"Think briefly: what is 2+2?",
temperature=0.1,
disable_thinking=False
)
if test_response:
# If response is suspiciously short or shows signs of no-think behavior
if len(test_response.strip()) < 10 or "4" == test_response.strip():
return True
except Exception:
pass
return False
def _handle_model_restart(self) -> bool:
"""Handle user confirmation and model restart."""
try:
print(
"\n🤔 To ensure best thinking quality, exploration mode works best with a fresh model."
)
print("\n🤔 To ensure best thinking quality, exploration mode works best with a fresh model.")
print(f" Currently running: {self.synthesizer.model}")
print(
"\n💡 Stop current model and restart for optimal exploration? (y/N): ",
end="",
flush=True,
)
print("\n💡 Stop current model and restart for optimal exploration? (y/N): ", end="", flush=True)
response = input().strip().lower()
if response in ["y", "yes"]:
if response in ['y', 'yes']:
print("\n🔄 Stopping current model...")
# Use ollama stop command for clean model restart
import subprocess
try:
subprocess.run(
["ollama", "stop", self.synthesizer.model],
timeout=10,
capture_output=True,
)
subprocess.run([
"ollama", "stop", self.synthesizer.model
], timeout=10, capture_output=True)
print("✅ Model stopped successfully.")
print(
"🚀 Exploration mode will restart the model with thinking enabled..."
)
print("🚀 Exploration mode will restart the model with thinking enabled...")
# Reset synthesizer initialization to force fresh start
self.synthesizer._initialized = False
return True
except subprocess.TimeoutExpired:
print("⚠️ Model stop timed out, continuing anyway...")
return False
@ -424,18 +371,19 @@ Guidelines:
else:
print("📝 Continuing with current model...")
return False
except KeyboardInterrupt:
print("\n📝 Continuing with current model...")
return False
except EOFError:
print("\n📝 Continuing with current model...")
return False
def _call_ollama_with_thinking(self, prompt: str, temperature: float = 0.3) -> tuple:
"""Call Ollama with streaming for fast time-to-first-token."""
import requests
import json
try:
# Use the synthesizer's model and connection
model_to_use = self.synthesizer.model
@ -444,15 +392,14 @@ Guidelines:
model_to_use = self.synthesizer.available_models[0]
else:
return None, None
# Enable thinking by NOT adding <no_think>
final_prompt = prompt
# Get optimal parameters for this model
from .llm_optimization import get_optimal_ollama_parameters
optimal_params = get_optimal_ollama_parameters(model_to_use)
payload = {
"model": model_to_use,
"prompt": final_prompt,
@ -464,102 +411,94 @@ Guidelines:
"num_ctx": self.synthesizer._get_optimal_context_size(model_to_use),
"num_predict": optimal_params.get("num_predict", 2000),
"repeat_penalty": optimal_params.get("repeat_penalty", 1.1),
"presence_penalty": optimal_params.get("presence_penalty", 1.0),
},
"presence_penalty": optimal_params.get("presence_penalty", 1.0)
}
}
response = requests.post(
f"{self.synthesizer.ollama_url}/api/generate",
json=payload,
stream=True,
timeout=65,
timeout=65
)
if response.status_code == 200:
# Collect streaming response
raw_response = ""
thinking_displayed = False
for line in response.iter_lines():
if line:
try:
chunk_data = json.loads(line.decode("utf-8"))
chunk_text = chunk_data.get("response", "")
chunk_data = json.loads(line.decode('utf-8'))
chunk_text = chunk_data.get('response', '')
if chunk_text:
raw_response += chunk_text
# Display thinking stream as it comes in
if not thinking_displayed and "<think>" in raw_response:
if not thinking_displayed and '<think>' in raw_response:
# Start displaying thinking
self._start_thinking_display()
thinking_displayed = True
if thinking_displayed:
self._stream_thinking_chunk(chunk_text)
if chunk_data.get("done", False):
if chunk_data.get('done', False):
break
except json.JSONDecodeError:
continue
# Finish thinking display if it was shown
if thinking_displayed:
self._end_thinking_display()
# Extract thinking stream and final response
thinking_stream, final_response = self._extract_thinking(raw_response)
return final_response, thinking_stream
else:
return None, None
except Exception as e:
logger.error(f"Thinking-enabled Ollama call failed: {e}")
return None, None
def _extract_thinking(self, raw_response: str) -> tuple:
"""Extract thinking content from response."""
thinking_stream = ""
final_response = raw_response
# Look for thinking patterns
if "<think>" in raw_response and "</think>" in raw_response:
# Extract thinking content between tags
start_tag = raw_response.find("<think>")
end_tag = raw_response.find("</think>") + len("</think>")
if start_tag != -1 and end_tag != -1:
thinking_content = raw_response[start_tag + 7 : end_tag - 8] # Remove tags
thinking_content = raw_response[start_tag + 7:end_tag - 8] # Remove tags
thinking_stream = thinking_content.strip()
# Remove thinking from final response
final_response = (raw_response[:start_tag] + raw_response[end_tag:]).strip()
# Alternative patterns for models that use different thinking formats
elif "Let me think" in raw_response or "I need to analyze" in raw_response:
# Simple heuristic: first paragraph might be thinking
lines = raw_response.split("\n")
lines = raw_response.split('\n')
potential_thinking = []
final_lines = []
thinking_indicators = [
"Let me think",
"I need to",
"First, I'll",
"Looking at",
"Analyzing",
]
thinking_indicators = ["Let me think", "I need to", "First, I'll", "Looking at", "Analyzing"]
in_thinking = False
for line in lines:
if any(indicator in line for indicator in thinking_indicators):
in_thinking = True
potential_thinking.append(line)
elif in_thinking and (
line.startswith("{") or line.startswith("**") or line.startswith("#")
):
elif in_thinking and (line.startswith('{') or line.startswith('**') or line.startswith('#')):
# Likely end of thinking, start of structured response
in_thinking = False
final_lines.append(line)
@ -567,87 +506,84 @@ Guidelines:
potential_thinking.append(line)
else:
final_lines.append(line)
if potential_thinking:
thinking_stream = "\n".join(potential_thinking).strip()
final_response = "\n".join(final_lines).strip()
thinking_stream = '\n'.join(potential_thinking).strip()
final_response = '\n'.join(final_lines).strip()
return thinking_stream, final_response
def _start_thinking_display(self):
"""Start the thinking stream display."""
print("\n\033[2m\033[3m💭 AI Thinking:\033[0m")
print("\033[2m\033[3m" + "─" * 40 + "\033[0m")
self._thinking_buffer = ""
self._in_thinking_tags = False
def _stream_thinking_chunk(self, chunk: str):
"""Stream a chunk of thinking as it arrives."""
import sys
self._thinking_buffer += chunk
# Check if we're in thinking tags
if "<think>" in self._thinking_buffer and not self._in_thinking_tags:
if '<think>' in self._thinking_buffer and not self._in_thinking_tags:
self._in_thinking_tags = True
# Display everything after <think>
start_idx = self._thinking_buffer.find("<think>") + 7
start_idx = self._thinking_buffer.find('<think>') + 7
thinking_content = self._thinking_buffer[start_idx:]
if thinking_content:
print(f"\033[2m\033[3m{thinking_content}\033[0m", end="", flush=True)
elif self._in_thinking_tags and "</think>" not in chunk:
print(f"\033[2m\033[3m{thinking_content}\033[0m", end='', flush=True)
elif self._in_thinking_tags and '</think>' not in chunk:
# We're in thinking mode, display the chunk
print(f"\033[2m\033[3m{chunk}\033[0m", end="", flush=True)
elif "</think>" in self._thinking_buffer:
print(f"\033[2m\033[3m{chunk}\033[0m", end='', flush=True)
elif '</think>' in self._thinking_buffer:
# End of thinking
self._in_thinking_tags = False
def _end_thinking_display(self):
"""End the thinking stream display."""
print("\n\033[2m\033[3m" + "─" * 40 + "\033[0m")
print(f"\n\033[2m\033[3m" + "─" * 40 + "\033[0m")
print()
def _display_thinking_stream(self, thinking_stream: str):
"""Display thinking stream in light gray and italic (fallback for non-streaming)."""
if not thinking_stream:
return
print("\n\033[2m\033[3m💭 AI Thinking:\033[0m")
print("\033[2m\033[3m" + "─" * 40 + "\033[0m")
# Split into paragraphs and display with proper formatting
paragraphs = thinking_stream.split("\n\n")
paragraphs = thinking_stream.split('\n\n')
for para in paragraphs:
if para.strip():
# Wrap long lines nicely
lines = para.strip().split("\n")
lines = para.strip().split('\n')
for line in lines:
if line.strip():
# Light gray and italic
print(f"\033[2m\033[3m{line}\033[0m")
print() # Paragraph spacing
print("\033[2m\033[3m" + "─" * 40 + "\033[0m")
print()
# Quick test function
def test_explorer():
"""Test the code explorer."""
explorer = CodeExplorer(Path("."))
if not explorer.start_exploration_session():
print("❌ Could not start exploration session")
return
# Test question
response = explorer.explore_question("How does authentication work in this codebase?")
if response:
print(response)
print("\n" + explorer.end_session())
if __name__ == "__main__":
test_explorer()
test_explorer()

591
mini_rag/fast_server.py
View File

File diff suppressed because it is too large Load Diff

793
mini_rag/indexer.py
View File

File diff suppressed because it is too large Load Diff

261
mini_rag/llm_safeguards.py
View File

@ -6,173 +6,163 @@ Provides runaway prevention, context management, and intelligent detection
of problematic model behaviors to ensure reliable user experience.
"""
import logging
import re
import time
import logging
from typing import Optional, Dict, List, Tuple
from dataclasses import dataclass
from typing import Dict, List, Optional, Tuple
logger = logging.getLogger(__name__)
@dataclass
class SafeguardConfig:
"""Configuration for LLM safeguards - gentle and educational."""
max_output_tokens: int = 4000 # Allow longer responses for learning
max_repetition_ratio: float = 0.7 # Be very permissive - only catch extreme repetition
max_response_time: int = 120 # Allow 2 minutes for complex thinking
min_useful_length: int = 10 # Lower threshold - short answers can be useful
context_window: int = 32000 # Match Qwen3 context length (32K token limit)
max_output_tokens: int = 4000 # Allow longer responses for learning
max_repetition_ratio: float = 0.7 # Be very permissive - only catch extreme repetition
max_response_time: int = 120 # Allow 2 minutes for complex thinking
min_useful_length: int = 10 # Lower threshold - short answers can be useful
context_window: int = 32000 # Match Qwen3 context length (32K token limit)
enable_thinking_detection: bool = True # Detect thinking patterns
class ModelRunawayDetector:
"""Detects and prevents model runaway behaviors."""
def __init__(self, config: SafeguardConfig = None):
self.config = config or SafeguardConfig()
self.response_patterns = self._compile_patterns()
def _compile_patterns(self) -> Dict[str, re.Pattern]:
"""Compile regex patterns for runaway detection."""
return {
# Excessive repetition patterns
"word_repetition": re.compile(r"\b(\w+)\b(?:\s+\1\b){3,}", re.IGNORECASE),
"phrase_repetition": re.compile(r"(.{10,50}?)\1{2,}", re.DOTALL),
'word_repetition': re.compile(r'\b(\w+)\b(?:\s+\1\b){3,}', re.IGNORECASE),
'phrase_repetition': re.compile(r'(.{10,50}?)\1{2,}', re.DOTALL),
# Thinking loop patterns (small models get stuck)
"thinking_loop": re.compile(
r"(let me think|i think|thinking|consider|actually|wait|hmm|well)\s*[.,:]*\s*\1",
re.IGNORECASE,
),
'thinking_loop': re.compile(r'(let me think|i think|thinking|consider|actually|wait|hmm|well)\s*[.,:]*\s*\1', re.IGNORECASE),
# Rambling patterns
"excessive_filler": re.compile(
r"\b(um|uh|well|you know|like|basically|actually|so|then|and|but|however)\b(?:\s+[^.!?]*){5,}",
re.IGNORECASE,
),
'excessive_filler': re.compile(r'\b(um|uh|well|you know|like|basically|actually|so|then|and|but|however)\b(?:\s+[^.!?]*){5,}', re.IGNORECASE),
# JSON corruption patterns
"broken_json": re.compile(r"\{[^}]*\{[^}]*\{"), # Nested broken JSON
"json_repetition": re.compile(
r'("[\w_]+"\s*:\s*"[^"]*",?\s*){4,}'
), # Repeated JSON fields
'broken_json': re.compile(r'\{[^}]*\{[^}]*\{'), # Nested broken JSON
'json_repetition': re.compile(r'("[\w_]+"\s*:\s*"[^"]*",?\s*){4,}'), # Repeated JSON fields
}
def check_response_quality(
self, response: str, query: str, start_time: float
) -> Tuple[bool, Optional[str], Optional[str]]:
def check_response_quality(self, response: str, query: str, start_time: float) -> Tuple[bool, Optional[str], Optional[str]]:
"""
Check response quality and detect runaway behaviors.
Returns:
(is_valid, issue_type, user_explanation)
"""
if not response or len(response.strip()) < self.config.min_useful_length:
return False, "too_short", self._explain_too_short()
# Check response time
elapsed = time.time() - start_time
if elapsed > self.config.max_response_time:
return False, "timeout", self._explain_timeout()
# Check for repetition issues
repetition_issue = self._check_repetition(response)
if repetition_issue:
return False, repetition_issue, self._explain_repetition(repetition_issue)
# Check for thinking loops
if self.config.enable_thinking_detection:
thinking_issue = self._check_thinking_loops(response)
if thinking_issue:
return False, thinking_issue, self._explain_thinking_loop()
# Check for rambling
rambling_issue = self._check_rambling(response)
if rambling_issue:
return False, rambling_issue, self._explain_rambling()
# Check JSON corruption (for structured responses)
if "{" in response and "}" in response:
if '{' in response and '}' in response:
json_issue = self._check_json_corruption(response)
if json_issue:
return False, json_issue, self._explain_json_corruption()
return True, None, None
def _check_repetition(self, response: str) -> Optional[str]:
"""Check for excessive repetition."""
# Word repetition
if self.response_patterns["word_repetition"].search(response):
if self.response_patterns['word_repetition'].search(response):
return "word_repetition"
# Phrase repetition
if self.response_patterns["phrase_repetition"].search(response):
# Phrase repetition
if self.response_patterns['phrase_repetition'].search(response):
return "phrase_repetition"
# Calculate repetition ratio (excluding Qwen3 thinking blocks)
analysis_text = response
if "<think>" in response and "</think>" in response:
# Extract only the actual response (after thinking) for repetition analysis
thinking_end = response.find("</think>")
if thinking_end != -1:
analysis_text = response[thinking_end + 8 :].strip()
analysis_text = response[thinking_end + 8:].strip()
# If the actual response (excluding thinking) is short, don't penalize
if len(analysis_text.split()) < 20:
return None
words = analysis_text.split()
if len(words) > 10:
unique_words = set(words)
repetition_ratio = 1 - (len(unique_words) / len(words))
if repetition_ratio > self.config.max_repetition_ratio:
return "high_repetition_ratio"
return None
def _check_thinking_loops(self, response: str) -> Optional[str]:
"""Check for thinking loops (common in small models)."""
if self.response_patterns["thinking_loop"].search(response):
if self.response_patterns['thinking_loop'].search(response):
return "thinking_loop"
# Check for excessive meta-commentary
thinking_words = ["think", "considering", "actually", "wait", "hmm", "let me"]
thinking_words = ['think', 'considering', 'actually', 'wait', 'hmm', 'let me']
thinking_count = sum(response.lower().count(word) for word in thinking_words)
if thinking_count > 5 and len(response.split()) < 200:
return "excessive_thinking"
return None
def _check_rambling(self, response: str) -> Optional[str]:
"""Check for rambling or excessive filler."""
if self.response_patterns["excessive_filler"].search(response):
if self.response_patterns['excessive_filler'].search(response):
return "excessive_filler"
# Check for extremely long sentences (sign of rambling)
sentences = re.split(r"[.!?]+", response)
sentences = re.split(r'[.!?]+', response)
long_sentences = [s for s in sentences if len(s.split()) > 50]
if len(long_sentences) > 2:
return "excessive_rambling"
return None
def _check_json_corruption(self, response: str) -> Optional[str]:
"""Check for JSON corruption in structured responses."""
if self.response_patterns["broken_json"].search(response):
if self.response_patterns['broken_json'].search(response):
return "broken_json"
if self.response_patterns["json_repetition"].search(response):
if self.response_patterns['json_repetition'].search(response):
return "json_repetition"
return None
def _explain_too_short(self) -> str:
return """🤔 The AI response was too short to be helpful.
**Why this happens:**
• The model might be confused by the query
• Context might be insufficient
• Context might be insufficient
• Model might be overloaded
**What to try:**
@ -190,11 +180,11 @@ class ModelRunawayDetector:
**What to try:**
• Try a simpler, more direct question
• Use synthesis mode for faster responses: `--synthesize`
• Use synthesis mode for faster responses: `--synthesize`
• Consider using a larger model if available"""
def _explain_repetition(self, issue_type: str) -> str:
return """🔄 The AI got stuck in repetition loops ({issue_type}).
return f"""🔄 The AI got stuck in repetition loops ({issue_type}).
**Why this happens:**
• Small models sometimes repeat when uncertain
@ -226,7 +216,7 @@ class ModelRunawayDetector:
**Why this happens:**
• Small models sometimes lose focus on complex topics
• Query might be too broad or vague
• Query might be too broad or vague
• Model trying to cover too much at once
**What to try:**
@ -243,7 +233,7 @@ class ModelRunawayDetector:
• Context limits can cause format errors
• Complex analysis might overwhelm formatting
**What to try:**
**What to try:**
• Try the question again (often resolves itself)
• Use simpler questions for better formatting
• Synthesis mode sometimes gives cleaner output
@ -252,109 +242,90 @@ class ModelRunawayDetector:
def get_recovery_suggestions(self, issue_type: str, query: str) -> List[str]:
"""Get specific recovery suggestions based on the issue."""
suggestions = []
if issue_type in ["thinking_loop", "excessive_thinking"]:
suggestions.extend(
[
f'Try synthesis mode: `rag-mini search . "{query}" --synthesize`',
"Ask more direct questions without 'why' or 'how'",
"Break complex questions into smaller parts",
]
)
elif issue_type in [
"word_repetition",
"phrase_repetition",
"high_repetition_ratio",
]:
suggestions.extend(
[
"Try rephrasing your question completely",
"Use more specific technical terms",
"Try exploration mode: `rag-mini explore .`",
]
)
elif issue_type == "timeout":
suggestions.extend(
[
"Try a simpler version of your question",
"Use synthesis mode for faster responses",
"Check if Ollama is under heavy load",
]
)
if issue_type in ['thinking_loop', 'excessive_thinking']:
suggestions.extend([
f"Try synthesis mode: `rag-mini search . \"{query}\" --synthesize`",
"Ask more direct questions without 'why' or 'how'",
"Break complex questions into smaller parts"
])
elif issue_type in ['word_repetition', 'phrase_repetition', 'high_repetition_ratio']:
suggestions.extend([
"Try rephrasing your question completely",
"Use more specific technical terms",
f"Try exploration mode: `rag-mini explore .`"
])
elif issue_type == 'timeout':
suggestions.extend([
"Try a simpler version of your question",
"Use synthesis mode for faster responses",
"Check if Ollama is under heavy load"
])
# Universal suggestions
suggestions.extend(
[
"Consider using a larger model if available (qwen3:1.7b or qwen3:4b)",
"Check model status: `ollama list`",
]
)
suggestions.extend([
"Consider using a larger model if available (qwen3:1.7b or qwen3:4b)",
"Check model status: `ollama list`"
])
return suggestions
def get_optimal_ollama_parameters(model_name: str) -> Dict[str, any]:
"""Get optimal parameters for different Ollama models."""
base_params = {
"num_ctx": 32768, # Good context window for most uses
"num_predict": 2000, # Reasonable response length
"temperature": 0.3, # Balanced creativity/consistency
"num_ctx": 32768, # Good context window for most uses
"num_predict": 2000, # Reasonable response length
"temperature": 0.3, # Balanced creativity/consistency
}
# Model-specific optimizations
if "qwen3:0.6b" in model_name.lower():
return {
**base_params,
"repeat_penalty": 1.15, # Prevent repetition in small model
"presence_penalty": 1.5, # Suppress repetitive outputs
"top_p": 0.8, # Focused sampling
"top_k": 20, # Limit choices
"num_predict": 1500, # Shorter responses for reliability
"repeat_penalty": 1.15, # Prevent repetition in small model
"presence_penalty": 1.5, # Suppress repetitive outputs
"top_p": 0.8, # Focused sampling
"top_k": 20, # Limit choices
"num_predict": 1500, # Shorter responses for reliability
}
elif "qwen3:1.7b" in model_name.lower():
return {
**base_params,
"repeat_penalty": 1.1, # Less aggressive for larger model
"presence_penalty": 1.0, # Balanced
"top_p": 0.9, # More creative
"top_k": 40, # More choices
"repeat_penalty": 1.1, # Less aggressive for larger model
"presence_penalty": 1.0, # Balanced
"top_p": 0.9, # More creative
"top_k": 40, # More choices
}
elif any(size in model_name.lower() for size in ["3b", "7b", "8b"]):
return {
**base_params,
"repeat_penalty": 1.05, # Minimal for larger models
"presence_penalty": 0.5, # Light touch
"top_p": 0.95, # High creativity
"top_k": 50, # Many choices
"num_predict": 3000, # Longer responses OK
"repeat_penalty": 1.05, # Minimal for larger models
"presence_penalty": 0.5, # Light touch
"top_p": 0.95, # High creativity
"top_k": 50, # Many choices
"num_predict": 3000, # Longer responses OK
}
return base_params
# Quick test
def test_safeguards():
"""Test the safeguard system."""
detector = ModelRunawayDetector()
# Test repetition detection
bad_response = "The user authentication system works by checking user credentials. The user authentication system works by checking user credentials. The user authentication system works by checking user credentials."
is_valid, issue, explanation = detector.check_response_quality(
bad_response, "auth", time.time()
)
is_valid, issue, explanation = detector.check_response_quality(bad_response, "auth", time.time())
print(f"Repetition test: Valid={is_valid}, Issue={issue}")
if explanation:
print(explanation)
if __name__ == "__main__":
test_safeguards()
test_safeguards()

759
mini_rag/llm_synthesizer.py
View File

File diff suppressed because it is too large Load Diff

259
mini_rag/non_invasive_watcher.py
View File

@ -3,16 +3,16 @@ Non-invasive file watcher designed to not interfere with development workflows.
Uses minimal resources and gracefully handles high-load scenarios.
"""
import logging
import queue
import threading
import os
import time
from datetime import datetime
import logging
import threading
import queue
from pathlib import Path
from typing import Optional, Set
from watchdog.events import DirModifiedEvent, FileSystemEventHandler
from datetime import datetime
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler, DirModifiedEvent
from .indexer import ProjectIndexer
@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
class NonInvasiveQueue:
"""Ultra-lightweight queue with aggressive deduplication and backoff."""
def __init__(self, delay: float = 5.0, max_queue_size: int = 100):
self.queue = queue.Queue(maxsize=max_queue_size)
self.pending = set()
@ -29,28 +29,28 @@ class NonInvasiveQueue:
self.delay = delay
self.last_update = {}
self.dropped_count = 0
def add(self, file_path: Path) -> bool:
"""Add file to queue with aggressive filtering."""
with self.lock:
file_str = str(file_path)
current_time = time.time()
# Skip if recently processed
if file_str in self.last_update:
if current_time - self.last_update[file_str] < self.delay:
return False
# Skip if already pending
if file_str in self.pending:
return False
# Skip if queue is getting full (backpressure)
if self.queue.qsize() > self.queue.maxsize * 0.8:
self.dropped_count += 1
logger.debug(f"Dropping update for {file_str} - queue overloaded")
return False
try:
self.queue.put_nowait(file_path)
self.pending.add(file_str)
@ -59,7 +59,7 @@ class NonInvasiveQueue:
except queue.Full:
self.dropped_count += 1
return False
def get(self, timeout: float = 0.1) -> Optional[Path]:
"""Get next file with very short timeout."""
try:
@ -73,87 +73,77 @@ class NonInvasiveQueue:
class MinimalEventHandler(FileSystemEventHandler):
"""Minimal event handler that only watches for meaningful changes."""
def __init__(
self,
update_queue: NonInvasiveQueue,
include_patterns: Set[str],
exclude_patterns: Set[str],
):
def __init__(self,
update_queue: NonInvasiveQueue,
include_patterns: Set[str],
exclude_patterns: Set[str]):
self.update_queue = update_queue
self.include_patterns = include_patterns
self.exclude_patterns = exclude_patterns
self.last_event_time = {}
def _should_process(self, file_path: str) -> bool:
"""Ultra-conservative file filtering."""
path = Path(file_path)
# Only process files, not directories
if not path.is_file():
return False
# Skip if too large (>1MB)
try:
if path.stat().st_size > 1024 * 1024:
return False
except (OSError, PermissionError):
return False
# Skip temporary and system files
name = path.name
if (
name.startswith(".")
or name.startswith("~")
or name.endswith(".tmp")
or name.endswith(".swp")
or name.endswith(".lock")
):
if (name.startswith('.') or
name.startswith('~') or
name.endswith('.tmp') or
name.endswith('.swp') or
name.endswith('.lock')):
return False
# Check exclude patterns first (faster)
path_str = str(path)
for pattern in self.exclude_patterns:
if pattern in path_str:
return False
# Check include patterns
for pattern in self.include_patterns:
if path.match(pattern):
return True
return False
def _rate_limit_event(self, file_path: str) -> bool:
"""Rate limit events per file."""
current_time = time.time()
if file_path in self.last_event_time:
if (
current_time - self.last_event_time[file_path] < 2.0
): # 2 second cooldown per file
if current_time - self.last_event_time[file_path] < 2.0: # 2 second cooldown per file
return False
self.last_event_time[file_path] = current_time
return True
def on_modified(self, event):
"""Handle file modifications with minimal overhead."""
if (
not event.is_directory
and self._should_process(event.src_path)
and self._rate_limit_event(event.src_path)
):
if (not event.is_directory and
self._should_process(event.src_path) and
self._rate_limit_event(event.src_path)):
self.update_queue.add(Path(event.src_path))
def on_created(self, event):
"""Handle file creation."""
if (
not event.is_directory
and self._should_process(event.src_path)
and self._rate_limit_event(event.src_path)
):
if (not event.is_directory and
self._should_process(event.src_path) and
self._rate_limit_event(event.src_path)):
self.update_queue.add(Path(event.src_path))
def on_deleted(self, event):
"""Handle file deletion."""
if not event.is_directory and self._rate_limit_event(event.src_path):
@ -167,17 +157,15 @@ class MinimalEventHandler(FileSystemEventHandler):
class NonInvasiveFileWatcher:
"""Non-invasive file watcher that prioritizes system stability."""
def __init__(
self,
project_path: Path,
indexer: Optional[ProjectIndexer] = None,
cpu_limit: float = 0.1, # Max 10% CPU usage
max_memory_mb: int = 50,
): # Max 50MB memory
def __init__(self,
project_path: Path,
indexer: Optional[ProjectIndexer] = None,
cpu_limit: float = 0.1, # Max 10% CPU usage
max_memory_mb: int = 50): # Max 50MB memory
"""
Initialize non-invasive watcher.
Args:
project_path: Path to watch
indexer: ProjectIndexer instance
@ -188,173 +176,158 @@ class NonInvasiveFileWatcher:
self.indexer = indexer or ProjectIndexer(self.project_path)
self.cpu_limit = cpu_limit
self.max_memory_mb = max_memory_mb
# Initialize components with conservative settings
self.update_queue = NonInvasiveQueue(
delay=10.0, max_queue_size=50
) # Very conservative
self.update_queue = NonInvasiveQueue(delay=10.0, max_queue_size=50) # Very conservative
self.observer = Observer()
self.worker_thread = None
self.running = False
# Get patterns from indexer
self.include_patterns = set(self.indexer.include_patterns)
self.exclude_patterns = set(self.indexer.exclude_patterns)
# Add more aggressive exclusions
self.exclude_patterns.update(
{
"__pycache__",
".git",
"node_modules",
".venv",
"venv",
"dist",
"build",
"target",
".idea",
".vscode",
".pytest_cache",
"coverage",
"htmlcov",
".coverage",
".mypy_cache",
".tox",
"logs",
"log",
"tmp",
"temp",
".DS_Store",
}
)
self.exclude_patterns.update({
'__pycache__', '.git', 'node_modules', '.venv', 'venv',
'dist', 'build', 'target', '.idea', '.vscode', '.pytest_cache',
'coverage', 'htmlcov', '.coverage', '.mypy_cache', '.tox',
'logs', 'log', 'tmp', 'temp', '.DS_Store'
})
# Stats
self.stats = {
"files_processed": 0,
"files_dropped": 0,
"cpu_throttle_count": 0,
"started_at": None,
'files_processed': 0,
'files_dropped': 0,
'cpu_throttle_count': 0,
'started_at': None,
}
def start(self):
"""Start non-invasive watching."""
if self.running:
return
logger.info(f"Starting non-invasive file watcher for {self.project_path}")
# Set up minimal event handler
event_handler = MinimalEventHandler(
self.update_queue, self.include_patterns, self.exclude_patterns
self.update_queue,
self.include_patterns,
self.exclude_patterns
)
# Schedule with recursive watching
self.observer.schedule(event_handler, str(self.project_path), recursive=True)
self.observer.schedule(
event_handler,
str(self.project_path),
recursive=True
)
# Start low-priority worker thread
self.running = True
self.worker_thread = threading.Thread(
target=self._process_updates_gently, daemon=True, name="RAG-FileWatcher"
target=self._process_updates_gently,
daemon=True,
name="RAG-FileWatcher"
)
# Set lowest priority
self.worker_thread.start()
# Start observer
self.observer.start()
self.stats["started_at"] = datetime.now()
self.stats['started_at'] = datetime.now()
logger.info("Non-invasive file watcher started")
def stop(self):
"""Stop watching gracefully."""
if not self.running:
return
logger.info("Stopping non-invasive file watcher...")
# Stop observer first
self.observer.stop()
self.observer.join(timeout=2.0) # Don't wait too long
# Stop worker thread
self.running = False
if self.worker_thread and self.worker_thread.is_alive():
self.worker_thread.join(timeout=3.0) # Don't block shutdown
logger.info("Non-invasive file watcher stopped")
def _process_updates_gently(self):
"""Process updates with extreme care not to interfere."""
logger.debug("Non-invasive update processor started")
process_start_time = time.time()
while self.running:
try:
# Yield CPU frequently
time.sleep(0.5) # Always sleep between operations
# Get next file with very short timeout
file_path = self.update_queue.get(timeout=0.1)
if file_path:
# Check CPU usage before processing
current_time = time.time()
elapsed = current_time - process_start_time
# Simple CPU throttling: if we've been working too much, back off
if elapsed > 0:
# If we're consuming too much time, throttle aggressively
work_ratio = 0.1 # Assume we use 10% of time in this check
if work_ratio > self.cpu_limit:
self.stats["cpu_throttle_count"] += 1
self.stats['cpu_throttle_count'] += 1
time.sleep(2.0) # Back off significantly
continue
# Process single file with error isolation
try:
if file_path.exists():
success = self.indexer.update_file(file_path)
else:
success = self.indexer.delete_file(file_path)
if success:
self.stats["files_processed"] += 1
self.stats['files_processed'] += 1
# Always yield CPU after processing
time.sleep(0.1)
except Exception as e:
logger.debug(
f"Non-invasive watcher: failed to process {file_path}: {e}"
)
logger.debug(f"Non-invasive watcher: failed to process {file_path}: {e}")
# Don't let errors propagate - just continue
continue
# Update dropped count from queue
self.stats["files_dropped"] = self.update_queue.dropped_count
self.stats['files_dropped'] = self.update_queue.dropped_count
except Exception as e:
logger.debug(f"Non-invasive watcher error: {e}")
time.sleep(1.0) # Back off on errors
logger.debug("Non-invasive update processor stopped")
def get_statistics(self) -> dict:
"""Get non-invasive watcher statistics."""
stats = self.stats.copy()
stats["queue_size"] = self.update_queue.queue.qsize()
stats["running"] = self.running
if stats["started_at"]:
uptime = datetime.now() - stats["started_at"]
stats["uptime_seconds"] = uptime.total_seconds()
stats['queue_size'] = self.update_queue.queue.qsize()
stats['running'] = self.running
if stats['started_at']:
uptime = datetime.now() - stats['started_at']
stats['uptime_seconds'] = uptime.total_seconds()
return stats
def __enter__(self):
self.start()
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.stop()
self.stop()

317
mini_rag/ollama_embeddings.py
View File

@ -3,14 +3,15 @@ Hybrid code embedding module - Ollama primary with ML fallback.
Tries Ollama first, falls back to local ML stack if needed.
"""
import logging
import time
from concurrent.futures import ThreadPoolExecutor
from functools import lru_cache
from typing import Any, Dict, List, Optional, Union
import numpy as np
import requests
import numpy as np
from typing import List, Union, Optional, Dict, Any
import logging
from functools import lru_cache
import time
import json
from concurrent.futures import ThreadPoolExecutor
import threading
logger = logging.getLogger(__name__)
@ -18,9 +19,8 @@ logger = logging.getLogger(__name__)
FALLBACK_AVAILABLE = False
try:
import torch
from transformers import AutoTokenizer, AutoModel
from sentence_transformers import SentenceTransformer
from transformers import AutoModel, AutoTokenizer
FALLBACK_AVAILABLE = True
logger.debug("ML fallback dependencies available")
except ImportError:
@ -29,16 +29,12 @@ except ImportError:
class OllamaEmbedder:
"""Hybrid embeddings: Ollama primary with ML fallback."""
def __init__(
self,
model_name: str = "nomic-embed-text:latest",
base_url: str = "http://localhost:11434",
enable_fallback: bool = True,
):
def __init__(self, model_name: str = "nomic-embed-text:latest", base_url: str = "http://localhost:11434",
enable_fallback: bool = True):
"""
Initialize the hybrid embedder.
Args:
model_name: Ollama model to use for embeddings
base_url: Base URL for Ollama API
@ -48,15 +44,15 @@ class OllamaEmbedder:
self.base_url = base_url
self.embedding_dim = 768 # Standard for nomic-embed-text
self.enable_fallback = enable_fallback and FALLBACK_AVAILABLE
# State tracking
self.ollama_available = False
self.fallback_embedder = None
self.mode = "unknown" # "ollama", "fallback", or "hash"
# Try to initialize Ollama first
self._initialize_providers()
def _initialize_providers(self):
"""Initialize embedding providers in priority order."""
# Try Ollama first
@ -68,15 +64,13 @@ class OllamaEmbedder:
except Exception as e:
logger.debug(f"Ollama not available: {e}")
self.ollama_available = False
# Try ML fallback
if self.enable_fallback:
try:
self._initialize_fallback_embedder()
self.mode = "fallback"
logger.info(
f"✅ ML fallback active: {self.fallback_embedder.model_type if hasattr(self.fallback_embedder, 'model_type') else 'transformer'}"
)
logger.info(f"✅ ML fallback active: {self.fallback_embedder.model_type if hasattr(self.fallback_embedder, 'model_type') else 'transformer'}")
except Exception as fallback_error:
logger.warning(f"ML fallback failed: {fallback_error}")
self.mode = "hash"
@ -84,7 +78,7 @@ class OllamaEmbedder:
else:
self.mode = "hash"
logger.info("⚠️ Using hash-based embeddings (no fallback enabled)")
def _verify_ollama_connection(self):
"""Verify Ollama server is running and model is available."""
try:
@ -99,17 +93,17 @@ class OllamaEmbedder:
print()
raise ConnectionError("Ollama service not running. Start with: ollama serve")
except requests.exceptions.Timeout:
print("⏱️ Ollama Service Timeout")
print("⏱️ Ollama Service Timeout")
print(" Ollama is taking too long to respond")
print(" Check if Ollama is overloaded: ollama ps")
print(" Restart if needed: killall ollama && ollama serve")
print()
raise ConnectionError("Ollama service timeout")
# Check if our model is available
models = response.json().get("models", [])
model_names = [model["name"] for model in models]
models = response.json().get('models', [])
model_names = [model['name'] for model in models]
if self.model_name not in model_names:
print(f"📦 Model '{self.model_name}' Not Found")
print(" Embedding models convert text into searchable vectors")
@ -119,23 +113,19 @@ class OllamaEmbedder:
print()
# Try to pull the model
self._pull_model()
def _initialize_fallback_embedder(self):
"""Initialize the ML fallback embedder."""
if not FALLBACK_AVAILABLE:
raise RuntimeError("ML dependencies not available for fallback")
# Try lightweight models first for better compatibility
fallback_models = [
(
"sentence-transformers/all-MiniLM-L6-v2",
384,
self._init_sentence_transformer,
),
("sentence-transformers/all-MiniLM-L6-v2", 384, self._init_sentence_transformer),
("microsoft/codebert-base", 768, self._init_transformer_model),
("microsoft/unixcoder-base", 768, self._init_transformer_model),
]
for model_name, dim, init_func in fallback_models:
try:
init_func(model_name)
@ -145,33 +135,31 @@ class OllamaEmbedder:
except Exception as e:
logger.debug(f"Failed to load {model_name}: {e}")
continue
raise RuntimeError("Could not initialize any fallback embedding model")
def _init_sentence_transformer(self, model_name: str):
"""Initialize sentence-transformers model."""
self.fallback_embedder = SentenceTransformer(model_name)
self.fallback_embedder.model_type = "sentence_transformer"
self.fallback_embedder.model_type = 'sentence_transformer'
def _init_transformer_model(self, model_name: str):
"""Initialize transformer model."""
device = "cuda" if torch.cuda.is_available() else "cpu"
device = 'cuda' if torch.cuda.is_available() else 'cpu'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name).to(device)
model.eval()
# Create a simple wrapper
class TransformerWrapper:
def __init__(self, model, tokenizer, device):
self.model = model
self.tokenizer = tokenizer
self.device = device
self.model_type = "transformer"
self.model_type = 'transformer'
self.fallback_embedder = TransformerWrapper(model, tokenizer, device)
def _pull_model(self):
"""Pull the embedding model if not available."""
logger.info(f"Pulling model {self.model_name}...")
@ -179,13 +167,13 @@ class OllamaEmbedder:
response = requests.post(
f"{self.base_url}/api/pull",
json={"name": self.model_name},
timeout=300, # 5 minutes for model download
timeout=300 # 5 minutes for model download
)
response.raise_for_status()
logger.info(f"Successfully pulled {self.model_name}")
except requests.exceptions.RequestException as e:
raise RuntimeError(f"Failed to pull model {self.model_name}: {e}")
def _get_embedding(self, text: str) -> np.ndarray:
"""Get embedding using the best available provider."""
if self.mode == "ollama" and self.ollama_available:
@ -195,25 +183,28 @@ class OllamaEmbedder:
else:
# Hash fallback
return self._hash_embedding(text)
def _get_ollama_embedding(self, text: str) -> np.ndarray:
"""Get embedding from Ollama API."""
try:
response = requests.post(
f"{self.base_url}/api/embeddings",
json={"model": self.model_name, "prompt": text},
timeout=30,
json={
"model": self.model_name,
"prompt": text
},
timeout=30
)
response.raise_for_status()
result = response.json()
embedding = result.get("embedding", [])
embedding = result.get('embedding', [])
if not embedding:
raise ValueError("No embedding returned from Ollama")
return np.array(embedding, dtype=np.float32)
except requests.exceptions.RequestException as e:
logger.error(f"Ollama API request failed: {e}")
# Degrade gracefully - try fallback if available
@ -225,88 +216,82 @@ class OllamaEmbedder:
except (ValueError, KeyError) as e:
logger.error(f"Invalid response from Ollama: {e}")
return self._hash_embedding(text)
def _get_fallback_embedding(self, text: str) -> np.ndarray:
"""Get embedding from ML fallback."""
try:
if self.fallback_embedder.model_type == "sentence_transformer":
if self.fallback_embedder.model_type == 'sentence_transformer':
embedding = self.fallback_embedder.encode([text], convert_to_numpy=True)[0]
return embedding.astype(np.float32)
elif self.fallback_embedder.model_type == "transformer":
elif self.fallback_embedder.model_type == 'transformer':
# Tokenize and generate embedding
inputs = self.fallback_embedder.tokenizer(
text,
padding=True,
truncation=True,
text,
padding=True,
truncation=True,
max_length=512,
return_tensors="pt",
return_tensors="pt"
).to(self.fallback_embedder.device)
with torch.no_grad():
outputs = self.fallback_embedder.model(**inputs)
# Use pooler output if available, otherwise mean pooling
if hasattr(outputs, "pooler_output") and outputs.pooler_output is not None:
if hasattr(outputs, 'pooler_output') and outputs.pooler_output is not None:
embedding = outputs.pooler_output[0]
else:
# Mean pooling over sequence length
attention_mask = inputs["attention_mask"]
attention_mask = inputs['attention_mask']
token_embeddings = outputs.last_hidden_state[0]
# Mask and average
input_mask_expanded = (
attention_mask.unsqueeze(-1)
.expand(token_embeddings.size())
.float()
)
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 0)
sum_mask = torch.clamp(input_mask_expanded.sum(0), min=1e-9)
embedding = sum_embeddings / sum_mask
return embedding.cpu().numpy().astype(np.float32)
else:
raise ValueError(
f"Unknown fallback model type: {self.fallback_embedder.model_type}"
)
raise ValueError(f"Unknown fallback model type: {self.fallback_embedder.model_type}")
except Exception as e:
logger.error(f"Fallback embedding failed: {e}")
return self._hash_embedding(text)
def _hash_embedding(self, text: str) -> np.ndarray:
"""Generate deterministic hash-based embedding as fallback."""
import hashlib
# Create deterministic hash
hash_obj = hashlib.sha256(text.encode("utf-8"))
hash_obj = hashlib.sha256(text.encode('utf-8'))
hash_bytes = hash_obj.digest()
# Convert to numbers and normalize
hash_nums = np.frombuffer(hash_bytes, dtype=np.uint8)
# Expand to target dimension using repetition
while len(hash_nums) < self.embedding_dim:
hash_nums = np.concatenate([hash_nums, hash_nums])
# Take exactly the dimension we need
embedding = hash_nums[: self.embedding_dim].astype(np.float32)
embedding = hash_nums[:self.embedding_dim].astype(np.float32)
# Normalize to [-1, 1] range
embedding = (embedding / 127.5) - 1.0
logger.debug(f"Using hash fallback embedding for text: {text[:50]}...")
return embedding
def embed_code(self, code: Union[str, List[str]], language: str = "python") -> np.ndarray:
"""
Generate embeddings for code snippet(s).
Args:
code: Single code string or list of code strings
language: Programming language (used for context)
Returns:
Embedding vector(s) as numpy array
"""
@ -315,22 +300,22 @@ class OllamaEmbedder:
single_input = True
else:
single_input = False
# Preprocess code for better embeddings
processed_code = [self._preprocess_code(c, language) for c in code]
# Generate embeddings
embeddings = []
for text in processed_code:
embedding = self._get_embedding(text)
embeddings.append(embedding)
embeddings = np.array(embeddings, dtype=np.float32)
if single_input:
return embeddings[0]
return embeddings
def _preprocess_code(self, code: str, language: str = "python") -> str:
"""
Preprocess code for better embedding quality.
@ -338,25 +323,25 @@ class OllamaEmbedder:
"""
# Remove leading/trailing whitespace
code = code.strip()
# Normalize whitespace but preserve structure
lines = code.split("\n")
lines = code.split('\n')
processed_lines = []
for line in lines:
# Remove trailing whitespace
line = line.rstrip()
# Keep non-empty lines
if line:
processed_lines.append(line)
cleaned_code = "\n".join(processed_lines)
cleaned_code = '\n'.join(processed_lines)
# Add language context for better embeddings
if language and cleaned_code:
return f"```{language}\n{cleaned_code}\n```"
return cleaned_code
@lru_cache(maxsize=1000)
def embed_query(self, query: str) -> np.ndarray:
"""
@ -366,151 +351,149 @@ class OllamaEmbedder:
# Enhance query for code search
enhanced_query = f"Search for code related to: {query}"
return self._get_embedding(enhanced_query)
def batch_embed_files(self, file_contents: List[dict], max_workers: int = 4) -> List[dict]:
"""
Embed multiple files efficiently using concurrent requests to Ollama.
Args:
file_contents: List of dicts with 'content' and optionally 'language' keys
max_workers: Maximum number of concurrent Ollama requests
Returns:
List of dicts with added 'embedding' key (preserves original order)
"""
if not file_contents:
return []
# For small batches, use sequential processing to avoid overhead
if len(file_contents) <= 2:
return self._batch_embed_sequential(file_contents)
# For very large batches, use chunked processing to prevent memory issues
if len(file_contents) > 500: # Process in chunks to manage memory
return self._batch_embed_chunked(file_contents, max_workers)
return self._batch_embed_concurrent(file_contents, max_workers)
def _batch_embed_sequential(self, file_contents: List[dict]) -> List[dict]:
"""Sequential processing for small batches."""
results = []
for file_dict in file_contents:
content = file_dict["content"]
language = file_dict.get("language", "python")
content = file_dict['content']
language = file_dict.get('language', 'python')
embedding = self.embed_code(content, language)
result = file_dict.copy()
result["embedding"] = embedding
result['embedding'] = embedding
results.append(result)
return results
def _batch_embed_concurrent(
self, file_contents: List[dict], max_workers: int
) -> List[dict]:
def _batch_embed_concurrent(self, file_contents: List[dict], max_workers: int) -> List[dict]:
"""Concurrent processing for larger batches."""
def embed_single(item_with_index):
index, file_dict = item_with_index
content = file_dict["content"]
language = file_dict.get("language", "python")
content = file_dict['content']
language = file_dict.get('language', 'python')
try:
embedding = self.embed_code(content, language)
result = file_dict.copy()
result["embedding"] = embedding
result['embedding'] = embedding
return index, result
except Exception as e:
logger.error(f"Failed to embed content at index {index}: {e}")
# Return with hash fallback
result = file_dict.copy()
result["embedding"] = self._hash_embedding(content)
result['embedding'] = self._hash_embedding(content)
return index, result
# Create indexed items to preserve order
indexed_items = list(enumerate(file_contents))
# Process concurrently
with ThreadPoolExecutor(max_workers=max_workers) as executor:
indexed_results = list(executor.map(embed_single, indexed_items))
# Sort by original index and extract results
indexed_results.sort(key=lambda x: x[0])
return [result for _, result in indexed_results]
def _batch_embed_chunked(
self, file_contents: List[dict], max_workers: int, chunk_size: int = 200
) -> List[dict]:
def _batch_embed_chunked(self, file_contents: List[dict], max_workers: int, chunk_size: int = 200) -> List[dict]:
"""
Process very large batches in smaller chunks to prevent memory issues.
This is important for beginners who might try to index huge projects.
"""
results = []
total_chunks = len(file_contents)
# Process in chunks
for i in range(0, len(file_contents), chunk_size):
chunk = file_contents[i : i + chunk_size]
chunk = file_contents[i:i + chunk_size]
# Log progress for large operations
if total_chunks > chunk_size:
chunk_num = i // chunk_size + 1
total_chunk_count = (total_chunks + chunk_size - 1) // chunk_size
logger.info(
f"Processing chunk {chunk_num}/{total_chunk_count} ({len(chunk)} files)"
)
logger.info(f"Processing chunk {chunk_num}/{total_chunk_count} ({len(chunk)} files)")
# Process this chunk using concurrent method
chunk_results = self._batch_embed_concurrent(chunk, max_workers)
results.extend(chunk_results)
# Brief pause between chunks to prevent overwhelming the system
if i + chunk_size < len(file_contents):
import time
time.sleep(0.1) # 100ms pause between chunks
return results
def get_embedding_dim(self) -> int:
"""Return the dimension of embeddings produced by this model."""
return self.embedding_dim
def get_mode(self) -> str:
"""Return current embedding mode: 'ollama', 'fallback', or 'hash'."""
return self.mode
def get_status(self) -> Dict[str, Any]:
"""Get detailed status of the embedding system."""
return {
"mode": self.mode,
"ollama_available": self.ollama_available,
"fallback_available": FALLBACK_AVAILABLE and self.enable_fallback,
"fallback_model": (
getattr(self.fallback_embedder, "model_type", None)
if self.fallback_embedder
else None
),
"fallback_model": getattr(self.fallback_embedder, 'model_type', None) if self.fallback_embedder else None,
"embedding_dim": self.embedding_dim,
"ollama_model": self.model_name if self.mode == "ollama" else None,
"ollama_url": self.base_url if self.mode == "ollama" else None,
"ollama_url": self.base_url if self.mode == "ollama" else None
}
def get_embedding_info(self) -> Dict[str, str]:
"""Get human-readable embedding system information for installer."""
status = self.get_status()
mode = status.get("mode", "unknown")
if mode == "ollama":
return {"method": f"Ollama ({status['ollama_model']})", "status": "working"}
return {
"method": f"Ollama ({status['ollama_model']})",
"status": "working"
}
# Treat legacy/alternate naming uniformly
if mode in ("fallback", "ml"):
return {
"method": f"ML Fallback ({status['fallback_model']})",
"status": "working",
"status": "working"
}
if mode == "hash":
return {"method": "Hash-based (basic similarity)", "status": "working"}
return {"method": "Unknown", "status": "error"}
return {
"method": "Hash-based (basic similarity)",
"status": "working"
}
return {
"method": "Unknown",
"status": "error"
}
def warmup(self):
"""Warm up the embedding system with a dummy request."""
dummy_code = "def hello(): pass"
@ -520,18 +503,14 @@ class OllamaEmbedder:
# Convenience function for quick embedding
def embed_code(
code: Union[str, List[str]], model_name: str = "nomic-embed-text:latest"
) -> np.ndarray:
def embed_code(code: Union[str, List[str]], model_name: str = "nomic-embed-text:latest") -> np.ndarray:
"""
Quick function to embed code without managing embedder instance.
Args:
code: Code string(s) to embed
model_name: Ollama model name to use
Returns:
Embedding vector(s)
"""
@ -540,4 +519,4 @@ def embed_code(
# Compatibility alias for drop-in replacement
CodeEmbedder = OllamaEmbedder
CodeEmbedder = OllamaEmbedder

55
mini_rag/path_handler.py
View File

@ -4,50 +4,51 @@ Handles forward/backward slashes on any file system.
Robust cross-platform path handling.
"""
import os
import sys
from pathlib import Path
from typing import List, Union
from typing import Union, List
def normalize_path(path: Union[str, Path]) -> str:
"""
Normalize a path to always use forward slashes.
This ensures consistency across platforms in storage.
Args:
path: Path as string or Path object
Returns:
Path string with forward slashes
"""
# Convert to Path object first
path_obj = Path(path)
# Convert to string and replace backslashes
path_str = str(path_obj).replace("\\", "/")
path_str = str(path_obj).replace('\\', '/')
# Handle UNC paths on Windows
if sys.platform == "win32" and path_str.startswith("//"):
if sys.platform == 'win32' and path_str.startswith('//'):
# Keep UNC paths as they are
return path_str
return path_str
def normalize_relative_path(path: Union[str, Path], base: Union[str, Path]) -> str:
"""
Get a normalized relative path.
Args:
path: Path to make relative
base: Base path to be relative to
Returns:
Relative path with forward slashes
"""
path_obj = Path(path).resolve()
base_obj = Path(base).resolve()
try:
rel_path = path_obj.relative_to(base_obj)
return normalize_path(rel_path)
@ -60,10 +61,10 @@ def denormalize_path(path_str: str) -> Path:
"""
Convert a normalized path string back to a Path object.
This handles the conversion from storage format to OS format.
Args:
path_str: Normalized path string with forward slashes
Returns:
Path object appropriate for the OS
"""
@ -74,10 +75,10 @@ def denormalize_path(path_str: str) -> Path:
def join_paths(*parts: Union[str, Path]) -> str:
"""
Join path parts and return normalized result.
Args:
*parts: Path parts to join
Returns:
Normalized joined path
"""
@ -89,46 +90,46 @@ def join_paths(*parts: Union[str, Path]) -> str:
def split_path(path: Union[str, Path]) -> List[str]:
"""
Split a path into its components.
Args:
path: Path to split
Returns:
List of path components
"""
path_obj = Path(path)
parts = []
# Handle drive on Windows
if path_obj.drive:
parts.append(path_obj.drive)
# Add all other parts
parts.extend(path_obj.parts[1:] if path_obj.drive else path_obj.parts)
return parts
def ensure_forward_slashes(path_str: str) -> str:
"""
Quick function to ensure a path string uses forward slashes.
Args:
path_str: Path string
Returns:
Path with forward slashes
"""
return path_str.replace("\\", "/")
return path_str.replace('\\', '/')
def ensure_native_slashes(path_str: str) -> str:
"""
Ensure a path uses the native separator for the OS.
Args:
path_str: Path string
Returns:
Path with native separators
"""
@ -136,8 +137,6 @@ def ensure_native_slashes(path_str: str) -> str:
# Convenience functions for common operations
def storage_path(path: Union[str, Path]) -> str:
"""Convert path to storage format (forward slashes)."""
return normalize_path(path)
@ -150,4 +149,4 @@ def display_path(path: Union[str, Path]) -> str:
def from_storage_path(path_str: str) -> Path:
"""Convert from storage format to Path object."""
return denormalize_path(path_str)
return denormalize_path(path_str)

54
mini_rag/performance.py
View File

@ -3,87 +3,85 @@ Performance monitoring for RAG system.
Track loading times, query times, and resource usage.
"""
import logging
import os
import time
from contextlib import contextmanager
from typing import Any, Dict, Optional
import psutil
import os
from contextlib import contextmanager
from typing import Dict, Any, Optional
import logging
logger = logging.getLogger(__name__)
class PerformanceMonitor:
"""Track performance metrics for RAG operations."""
def __init__(self):
self.metrics = {}
self.process = psutil.Process(os.getpid())
@contextmanager
def measure(self, operation: str):
"""Context manager to measure operation time and memory."""
# Get initial state
start_time = time.time()
start_memory = self.process.memory_info().rss / 1024 / 1024 # MB
try:
yield self
finally:
# Calculate metrics
end_time = time.time()
end_memory = self.process.memory_info().rss / 1024 / 1024 # MB
duration = end_time - start_time
memory_delta = end_memory - start_memory
# Store metrics
self.metrics[operation] = {
"duration_seconds": duration,
"memory_delta_mb": memory_delta,
"final_memory_mb": end_memory,
'duration_seconds': duration,
'memory_delta_mb': memory_delta,
'final_memory_mb': end_memory,
}
logger.info(
f"[PERF] {operation}: {duration:.2f}s, "
f"Memory: {end_memory:.1f}MB (+{memory_delta:+.1f}MB)"
)
def get_summary(self) -> Dict[str, Any]:
"""Get performance summary."""
total_time = sum(m["duration_seconds"] for m in self.metrics.values())
total_time = sum(m['duration_seconds'] for m in self.metrics.values())
return {
"total_time_seconds": total_time,
"operations": self.metrics,
"current_memory_mb": self.process.memory_info().rss / 1024 / 1024,
'total_time_seconds': total_time,
'operations': self.metrics,
'current_memory_mb': self.process.memory_info().rss / 1024 / 1024,
}
def print_summary(self):
"""Print a formatted summary."""
print("\n" + "=" * 50)
print("\n" + "="*50)
print("PERFORMANCE SUMMARY")
print("=" * 50)
print("="*50)
for op, metrics in self.metrics.items():
print(f"\n{op}:")
print(f" Time: {metrics['duration_seconds']:.2f}s")
print(f" Memory: +{metrics['memory_delta_mb']:+.1f}MB")
summary = self.get_summary()
print(f"\nTotal Time: {summary['total_time_seconds']:.2f}s")
print(f"Current Memory: {summary['current_memory_mb']:.1f}MB")
print("=" * 50)
print("="*50)
# Global instance for easy access
_monitor = None
def get_monitor() -> PerformanceMonitor:
"""Get or create global monitor instance."""
global _monitor
if _monitor is None:
_monitor = PerformanceMonitor()
return _monitor
return _monitor

139
mini_rag/query_expander.py
View File

@ -7,7 +7,7 @@ Automatically expands search queries to find more relevant results.
Example: "authentication" becomes "authentication login user verification credentials"
## How It Helps
## How It Helps
- 2-3x more relevant search results
- Works with any content (code, docs, notes, etc.)
- Completely transparent to users
@ -26,25 +26,22 @@ expanded = expander.expand_query("error handling")
# Result: "error handling exception try catch fault tolerance"
```
Perfect for beginners - enable in TUI for exploration,
Perfect for beginners - enable in TUI for exploration,
disable in CLI for maximum speed.
"""
import logging
import re
import threading
from typing import Optional
from typing import List, Optional
import requests
from .config import RAGConfig
logger = logging.getLogger(__name__)
class QueryExpander:
"""Expands search queries using LLM to improve search recall."""
def __init__(self, config: RAGConfig):
self.config = config
self.ollama_url = f"http://{config.llm.ollama_host}"
@ -52,37 +49,37 @@ class QueryExpander:
self.max_terms = config.llm.max_expansion_terms
self.enabled = config.search.expand_queries
self._initialized = False
# Cache for expanded queries to avoid repeated API calls
self._cache = {}
self._cache_lock = threading.RLock() # Thread-safe cache access
def _ensure_initialized(self):
"""Lazy initialization with LLM warmup."""
if self._initialized:
return
# Skip warmup - causes startup delays and unwanted model calls
# Query expansion works fine on first use without warmup
self._initialized = True
def expand_query(self, query: str) -> str:
"""Expand a search query with related terms."""
if not self.enabled or not query.strip():
return query
self._ensure_initialized()
# Check cache first (thread-safe)
with self._cache_lock:
if query in self._cache:
return self._cache[query]
# Don't expand very short queries or obvious keywords
if len(query.split()) <= 1 or len(query) <= 3:
return query
try:
expanded = self._llm_expand_query(query)
if expanded and expanded != query:
@ -94,23 +91,23 @@ class QueryExpander:
self._manage_cache_size()
logger.info(f"Expanded query: '{query}' → '{expanded}'")
return expanded
except Exception as e:
logger.warning(f"Query expansion failed: {e}")
# Return original query if expansion fails
return query
def _llm_expand_query(self, query: str) -> Optional[str]:
"""Use LLM to expand the query with related terms."""
# Use best available model
model_to_use = self._select_expansion_model()
if not model_to_use:
return None
# Create expansion prompt
prompt = """You are a search query expert. Expand the following search query with {self.max_terms} additional related terms that would help find relevant content.
prompt = f"""You are a search query expert. Expand the following search query with {self.max_terms} additional related terms that would help find relevant content.
Original query: "{query}"
@ -137,99 +134,95 @@ Expanded query:"""
"options": {
"temperature": 0.1, # Very low temperature for consistent expansions
"top_p": 0.8,
"max_tokens": 100, # Keep it short
},
"max_tokens": 100 # Keep it short
}
}
response = requests.post(
f"{self.ollama_url}/api/generate",
json=payload,
timeout=10, # Quick timeout for low latency
timeout=10 # Quick timeout for low latency
)
if response.status_code == 200:
result = response.json().get("response", "").strip()
result = response.json().get('response', '').strip()
# Clean up the response - extract just the expanded query
expanded = self._clean_expansion(result, query)
return expanded
except Exception as e:
logger.warning(f"LLM expansion failed: {e}")
return None
def _select_expansion_model(self) -> Optional[str]:
"""Select the best available model for query expansion."""
if self.model != "auto":
return self.model
try:
# Get available models
response = requests.get(f"{self.ollama_url}/api/tags", timeout=5)
if response.status_code == 200:
data = response.json()
available = [model["name"] for model in data.get("models", [])]
available = [model['name'] for model in data.get('models', [])]
# Use same model rankings as main synthesizer for consistency
expansion_preferences = [
"qwen3:1.7b",
"qwen3:0.6b",
"qwen3:4b",
"qwen2.5:3b",
"qwen2.5:1.5b",
"qwen2.5-coder:1.5b",
"qwen3:1.7b", "qwen3:0.6b", "qwen3:4b", "qwen2.5:3b",
"qwen2.5:1.5b", "qwen2.5-coder:1.5b"
]
for preferred in expansion_preferences:
for available_model in available:
if preferred in available_model:
logger.debug(f"Using {available_model} for query expansion")
return available_model
# Fallback to first available model
if available:
return available[0]
except Exception as e:
logger.warning(f"Could not select expansion model: {e}")
return None
def _clean_expansion(self, raw_response: str, original_query: str) -> str:
"""Clean the LLM response to extract just the expanded query."""
# Remove common response artifacts
clean_response = raw_response.strip()
# Remove quotes if the entire response is quoted
if clean_response.startswith('"') and clean_response.endswith('"'):
clean_response = clean_response[1:-1]
# Take only the first line if multiline
clean_response = clean_response.split("\n")[0].strip()
clean_response = clean_response.split('\n')[0].strip()
# Remove excessive punctuation and normalize spaces
clean_response = re.sub(r"[^\w\s-]", " ", clean_response)
clean_response = re.sub(r"\s+", " ", clean_response).strip()
clean_response = re.sub(r'[^\w\s-]', ' ', clean_response)
clean_response = re.sub(r'\s+', ' ', clean_response).strip()
# Ensure it starts with the original query
if not clean_response.lower().startswith(original_query.lower()):
clean_response = f"{original_query} {clean_response}"
# Limit the total length to avoid very long queries
words = clean_response.split()
if len(words) > len(original_query.split()) + self.max_terms:
words = words[: len(original_query.split()) + self.max_terms]
clean_response = " ".join(words)
words = words[:len(original_query.split()) + self.max_terms]
clean_response = ' '.join(words)
return clean_response
def clear_cache(self):
"""Clear the expansion cache (thread-safe)."""
with self._cache_lock:
self._cache.clear()
def _manage_cache_size(self, max_size: int = 1000):
"""Keep cache from growing too large (prevents memory leaks)."""
with self._cache_lock:
@ -239,49 +232,45 @@ Expanded query:"""
keep_count = max_size // 2
self._cache = dict(items[-keep_count:])
logger.debug(f"Cache trimmed from {len(items)} to {len(self._cache)} entries")
def is_available(self) -> bool:
"""Check if query expansion is available."""
if not self.enabled:
return False
self._ensure_initialized()
try:
response = requests.get(f"{self.ollama_url}/api/tags", timeout=5)
return response.status_code == 200
except (ConnectionError, TimeoutError, requests.RequestException):
except:
return False
# Quick test function
def test_expansion():
"""Test the query expander."""
from .config import RAGConfig
config = RAGConfig()
config.search.expand_queries = True
config.llm.max_expansion_terms = 6
expander = QueryExpander(config)
if not expander.is_available():
print("❌ Ollama not available for testing")
return
test_queries = [
"authentication",
"error handling",
"error handling",
"database query",
"user interface",
"user interface"
]
print("🔍 Testing Query Expansion:")
for query in test_queries:
expanded = expander.expand_query(query)
print(f" '{query}' → '{expanded}'")
if __name__ == "__main__":
test_expansion()
test_expansion()

615
mini_rag/search.py
View File

File diff suppressed because it is too large Load Diff

271
mini_rag/server.py
View File

@ -4,30 +4,30 @@ No more loading/unloading madness!
"""
import json
import logging
import os
import socket
import subprocess
import sys
import threading
import time
import subprocess
from pathlib import Path
from typing import Any, Dict, Optional
from typing import Dict, Any, Optional
import logging
import sys
import os
# Fix Windows console
if sys.platform == "win32":
os.environ["PYTHONUTF8"] = "1"
if sys.platform == 'win32':
os.environ['PYTHONUTF8'] = '1'
from .search import CodeSearcher
from .ollama_embeddings import OllamaEmbedder as CodeEmbedder
from .performance import PerformanceMonitor
from .search import CodeSearcher
logger = logging.getLogger(__name__)
class RAGServer:
"""Persistent server that keeps embeddings and DB loaded."""
def __init__(self, project_path: Path, port: int = 7777):
self.project_path = project_path
self.port = port
@ -37,36 +37,37 @@ class RAGServer:
self.socket = None
self.start_time = None
self.query_count = 0
def _kill_existing_server(self):
"""Kill any existing process using our port."""
try:
# Check if port is in use
test_sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
result = test_sock.connect_ex(("localhost", self.port))
result = test_sock.connect_ex(('localhost', self.port))
test_sock.close()
if result == 0: # Port is in use
print(f"️ Port {self.port} is already in use, attempting to free it...")
if sys.platform == "win32":
if sys.platform == 'win32':
# Windows: Find and kill process using netstat
import subprocess
try:
# Get process ID using the port
result = subprocess.run(
["netstat", "-ano"], capture_output=True, text=True
['netstat', '-ano'],
capture_output=True,
text=True
)
for line in result.stdout.split("\n"):
if f":{self.port}" in line and "LISTENING" in line:
for line in result.stdout.split('\n'):
if f':{self.port}' in line and 'LISTENING' in line:
parts = line.split()
pid = parts[-1]
print(f" Found process {pid} using port {self.port}")
# Kill the process
subprocess.run(["taskkill", "//PID", pid, "//F"], check=False)
subprocess.run(['taskkill', '//PID', pid, '//F'], check=False)
print(f" Killed process {pid}")
time.sleep(1) # Give it a moment to release the port
break
@ -75,16 +76,15 @@ class RAGServer:
else:
# Unix/Linux: Use lsof and kill
import subprocess
try:
result = subprocess.run(
["lso", "-ti", f":{self.port}"],
capture_output=True,
text=True,
['lsof', '-ti', f':{self.port}'],
capture_output=True,
text=True
)
if result.stdout.strip():
pid = result.stdout.strip()
subprocess.run(["kill", "-9", pid], check=False)
subprocess.run(['kill', '-9', pid], check=False)
print(f" Killed process {pid}")
time.sleep(1)
except Exception as e:
@ -92,38 +92,38 @@ class RAGServer:
except Exception as e:
# Non-critical error, just log it
logger.debug(f"Error checking port: {e}")
def start(self):
"""Start the RAG server."""
# Kill any existing process on our port first
self._kill_existing_server()
print(f" Starting RAG server on port {self.port}...")
# Load everything once
perf = PerformanceMonitor()
with perf.measure("Load Embedder"):
self.embedder = CodeEmbedder()
with perf.measure("Connect Database"):
self.searcher = CodeSearcher(self.project_path, embedder=self.embedder)
perf.print_summary()
# Start server
self.socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
self.socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
self.socket.bind(("localhost", self.port))
self.socket.bind(('localhost', self.port))
self.socket.listen(5)
self.running = True
self.start_time = time.time()
print(f"\n RAG server ready on localhost:{self.port}")
print(" Model loaded, database connected")
print(" Waiting for queries...\n")
# Handle connections
while self.running:
try:
@ -136,50 +136,50 @@ class RAGServer:
except Exception as e:
if self.running:
logger.error(f"Server error: {e}")
def _handle_client(self, client: socket.socket):
"""Handle a client connection."""
try:
# Receive query with proper message framing
data = self._receive_json(client)
request = json.loads(data)
# Check for shutdown command
if request.get("command") == "shutdown":
if request.get('command') == 'shutdown':
print("\n Shutdown requested")
response = {"success": True, "message": "Server shutting down"}
response = {'success': True, 'message': 'Server shutting down'}
self._send_json(client, response)
self.stop()
return
query = request.get("query", "")
top_k = request.get("top_k", 10)
query = request.get('query', '')
top_k = request.get('top_k', 10)
self.query_count += 1
print(f"[Query #{self.query_count}] {query}")
# Perform search
start = time.time()
results = self.searcher.search(query, top_k=top_k)
search_time = time.time() - start
# Prepare response
response = {
"success": True,
"query": query,
"count": len(results),
"search_time_ms": int(search_time * 1000),
"results": [r.to_dict() for r in results],
"server_uptime": int(time.time() - self.start_time),
"total_queries": self.query_count,
'success': True,
'query': query,
'count': len(results),
'search_time_ms': int(search_time * 1000),
'results': [r.to_dict() for r in results],
'server_uptime': int(time.time() - self.start_time),
'total_queries': self.query_count,
}
# Send response with proper framing
self._send_json(client, response)
print(f" Found {len(results)} results in {search_time*1000:.0f}ms")
except ConnectionError:
except ConnectionError as e:
# Normal disconnection - client closed connection
# This is expected behavior, don't log as error
pass
@ -187,49 +187,52 @@ class RAGServer:
# Only log actual errors, not normal disconnections
if "Connection closed" not in str(e):
logger.error(f"Client handler error: {e}")
error_response = {"success": False, "error": str(e)}
error_response = {
'success': False,
'error': str(e)
}
try:
self._send_json(client, error_response)
except (ConnectionError, OSError, TypeError, ValueError, socket.error):
except:
pass
finally:
client.close()
def _receive_json(self, sock: socket.socket) -> str:
"""Receive a complete JSON message with length prefix."""
# First receive the length (4 bytes)
length_data = b""
length_data = b''
while len(length_data) < 4:
chunk = sock.recv(4 - len(length_data))
if not chunk:
raise ConnectionError("Connection closed while receiving length")
length_data += chunk
length = int.from_bytes(length_data, "big")
length = int.from_bytes(length_data, 'big')
# Now receive the actual data
data = b""
data = b''
while len(data) < length:
chunk = sock.recv(min(65536, length - len(data)))
if not chunk:
raise ConnectionError("Connection closed while receiving data")
data += chunk
return data.decode("utf-8")
return data.decode('utf-8')
def _send_json(self, sock: socket.socket, data: dict):
"""Send a JSON message with length prefix."""
# Sanitize the data to ensure JSON compatibility
json_str = json.dumps(data, ensure_ascii=False, separators=(",", ":"))
json_bytes = json_str.encode("utf-8")
json_str = json.dumps(data, ensure_ascii=False, separators=(',', ':'))
json_bytes = json_str.encode('utf-8')
# Send length prefix (4 bytes)
length = len(json_bytes)
sock.send(length.to_bytes(4, "big"))
sock.send(length.to_bytes(4, 'big'))
# Send the data
sock.sendall(json_bytes)
def stop(self):
"""Stop the server."""
self.running = False
@ -240,89 +243,101 @@ class RAGServer:
class RAGClient:
"""Client to communicate with RAG server."""
def __init__(self, port: int = 7777):
self.port = port
self.use_legacy = False
def search(self, query: str, top_k: int = 10) -> Dict[str, Any]:
"""Send search query to server."""
try:
# Connect to server
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.connect(("localhost", self.port))
sock.connect(('localhost', self.port))
# Send request with proper framing
request = {"query": query, "top_k": top_k}
request = {
'query': query,
'top_k': top_k
}
self._send_json(sock, request)
# Receive response with proper framing
data = self._receive_json(sock)
response = json.loads(data)
sock.close()
return response
except ConnectionRefusedError:
return {
"success": False,
"error": "RAG server not running. Start with: rag-mini server",
'success': False,
'error': 'RAG server not running. Start with: rag-mini server'
}
except ConnectionError as e:
# Try legacy mode without message framing
if not self.use_legacy and "receiving length" in str(e):
self.use_legacy = True
return self._search_legacy(query, top_k)
return {"success": False, "error": str(e)}
return {
'success': False,
'error': str(e)
}
except Exception as e:
return {"success": False, "error": str(e)}
return {
'success': False,
'error': str(e)
}
def _receive_json(self, sock: socket.socket) -> str:
"""Receive a complete JSON message with length prefix."""
# First receive the length (4 bytes)
length_data = b""
length_data = b''
while len(length_data) < 4:
chunk = sock.recv(4 - len(length_data))
if not chunk:
raise ConnectionError("Connection closed while receiving length")
length_data += chunk
length = int.from_bytes(length_data, "big")
length = int.from_bytes(length_data, 'big')
# Now receive the actual data
data = b""
data = b''
while len(data) < length:
chunk = sock.recv(min(65536, length - len(data)))
if not chunk:
raise ConnectionError("Connection closed while receiving data")
data += chunk
return data.decode("utf-8")
return data.decode('utf-8')
def _send_json(self, sock: socket.socket, data: dict):
"""Send a JSON message with length prefix."""
json_str = json.dumps(data, ensure_ascii=False, separators=(",", ":"))
json_bytes = json_str.encode("utf-8")
json_str = json.dumps(data, ensure_ascii=False, separators=(',', ':'))
json_bytes = json_str.encode('utf-8')
# Send length prefix (4 bytes)
length = len(json_bytes)
sock.send(length.to_bytes(4, "big"))
sock.send(length.to_bytes(4, 'big'))
# Send the data
sock.sendall(json_bytes)
def _search_legacy(self, query: str, top_k: int = 10) -> Dict[str, Any]:
"""Legacy search without message framing for old servers."""
try:
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.connect(("localhost", self.port))
sock.connect(('localhost', self.port))
# Send request (old way)
request = {"query": query, "top_k": top_k}
sock.send(json.dumps(request).encode("utf-8"))
request = {
'query': query,
'top_k': top_k
}
sock.send(json.dumps(request).encode('utf-8'))
# Receive response (accumulate until we get valid JSON)
data = b""
data = b''
while True:
chunk = sock.recv(65536)
if not chunk:
@ -330,26 +345,32 @@ class RAGClient:
data += chunk
try:
# Try to decode as JSON
response = json.loads(data.decode("utf-8"))
response = json.loads(data.decode('utf-8'))
sock.close()
return response
except json.JSONDecodeError:
# Keep receiving
continue
sock.close()
return {"success": False, "error": "Incomplete response from server"}
return {
'success': False,
'error': 'Incomplete response from server'
}
except Exception as e:
return {"success": False, "error": str(e)}
return {
'success': False,
'error': str(e)
}
def is_running(self) -> bool:
"""Check if server is running."""
try:
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
result = sock.connect_ex(("localhost", self.port))
result = sock.connect_ex(('localhost', self.port))
sock.close()
return result == 0
except (ConnectionError, OSError, TypeError, ValueError, socket.error):
except:
return False
@ -368,31 +389,23 @@ def auto_start_if_needed(project_path: Path) -> Optional[subprocess.Popen]:
if not client.is_running():
# Start server in background
import subprocess
cmd = [
sys.executable,
"-m",
"mini_rag.cli",
"server",
"--path",
str(project_path),
]
cmd = [sys.executable, "-m", "mini_rag.cli", "server", "--path", str(project_path)]
process = subprocess.Popen(
cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
creationflags=(subprocess.CREATE_NEW_CONSOLE if sys.platform == "win32" else 0),
creationflags=subprocess.CREATE_NEW_CONSOLE if sys.platform == 'win32' else 0
)
# Wait for server to start
for _ in range(30): # 30 second timeout
time.sleep(1)
if client.is_running():
print(" RAG server started automatically")
return process
# Failed to start
process.terminate()
raise RuntimeError("Failed to start RAG server")
return None
return None

156
mini_rag/smart_chunking.py
View File

@ -3,140 +3,148 @@ Smart language-aware chunking strategies for FSS-Mini-RAG.
Automatically adapts chunking based on file type and content patterns.
"""
from typing import Dict, Any, List
from pathlib import Path
from typing import Any, Dict, List
import json
class SmartChunkingStrategy:
"""Intelligent chunking that adapts to file types and content."""
def __init__(self):
self.language_configs = {
"python": {
"max_size": 3000, # Larger for better function context
"min_size": 200,
"strategy": "function",
"prefer_semantic": True,
'python': {
'max_size': 3000, # Larger for better function context
'min_size': 200,
'strategy': 'function',
'prefer_semantic': True
},
"javascript": {
"max_size": 2500,
"min_size": 150,
"strategy": "function",
"prefer_semantic": True,
'javascript': {
'max_size': 2500,
'min_size': 150,
'strategy': 'function',
'prefer_semantic': True
},
"markdown": {
"max_size": 2500,
"min_size": 300, # Larger minimum for complete thoughts
"strategy": "header",
"preserve_structure": True,
'markdown': {
'max_size': 2500,
'min_size': 300, # Larger minimum for complete thoughts
'strategy': 'header',
'preserve_structure': True
},
"json": {
"max_size": 1000, # Smaller for config files
"min_size": 50,
"skip_if_large": True, # Skip huge config JSONs
"max_file_size": 50000, # 50KB limit
'json': {
'max_size': 1000, # Smaller for config files
'min_size': 50,
'skip_if_large': True, # Skip huge config JSONs
'max_file_size': 50000 # 50KB limit
},
"yaml": {"max_size": 1500, "min_size": 100, "strategy": "key_block"},
"text": {"max_size": 2000, "min_size": 200, "strategy": "paragraph"},
"bash": {"max_size": 1500, "min_size": 100, "strategy": "function"},
'yaml': {
'max_size': 1500,
'min_size': 100,
'strategy': 'key_block'
},
'text': {
'max_size': 2000,
'min_size': 200,
'strategy': 'paragraph'
},
'bash': {
'max_size': 1500,
'min_size': 100,
'strategy': 'function'
}
}
# Smart defaults for unknown languages
self.default_config = {
"max_size": 2000,
"min_size": 150,
"strategy": "semantic",
'max_size': 2000,
'min_size': 150,
'strategy': 'semantic'
}
def get_config_for_language(self, language: str, file_size: int = 0) -> Dict[str, Any]:
"""Get optimal chunking config for a specific language."""
config = self.language_configs.get(language, self.default_config).copy()
# Smart adjustments based on file size
if file_size > 0:
if file_size < 500: # Very small files
config["max_size"] = max(config["max_size"] // 2, 200)
config["min_size"] = 50
elif file_size > 20000: # Large files
config["max_size"] = min(config["max_size"] + 1000, 4000)
config['max_size'] = max(config['max_size'] // 2, 200)
config['min_size'] = 50
elif file_size > 20000: # Large files
config['max_size'] = min(config['max_size'] + 1000, 4000)
return config
def should_skip_file(self, language: str, file_size: int) -> bool:
"""Determine if a file should be skipped entirely."""
lang_config = self.language_configs.get(language, {})
# Skip huge JSON config files
if language == "json" and lang_config.get("skip_if_large"):
max_size = lang_config.get("max_file_size", 50000)
if language == 'json' and lang_config.get('skip_if_large'):
max_size = lang_config.get('max_file_size', 50000)
if file_size > max_size:
return True
# Skip tiny files that won't provide good context
if file_size < 30:
return True
return False
def get_smart_defaults(self, project_stats: Dict[str, Any]) -> Dict[str, Any]:
"""Generate smart defaults based on project language distribution."""
languages = project_stats.get("languages", {})
# sum(languages.values()) # Unused variable removed
languages = project_stats.get('languages', {})
total_files = sum(languages.values())
# Determine primary language
primary_lang = max(languages.items(), key=lambda x: x[1])[0] if languages else "python"
primary_lang = max(languages.items(), key=lambda x: x[1])[0] if languages else 'python'
primary_config = self.language_configs.get(primary_lang, self.default_config)
# Smart streaming threshold based on large files
large_files = project_stats.get("large_files", 0)
large_files = project_stats.get('large_files', 0)
streaming_threshold = 5120 if large_files > 5 else 1048576 # 5KB vs 1MB
return {
"chunking": {
"max_size": primary_config["max_size"],
"min_size": primary_config["min_size"],
"strategy": primary_config.get("strategy", "semantic"),
"max_size": primary_config['max_size'],
"min_size": primary_config['min_size'],
"strategy": primary_config.get('strategy', 'semantic'),
"language_specific": {
lang: config
for lang, config in self.language_configs.items()
lang: config for lang, config in self.language_configs.items()
if languages.get(lang, 0) > 0
},
}
},
"streaming": {
"enabled": True,
"threshold_bytes": streaming_threshold,
"chunk_size_kb": 64,
"chunk_size_kb": 64
},
"files": {
"skip_tiny_files": True,
"tiny_threshold": 30,
"smart_json_filtering": True,
},
"smart_json_filtering": True
}
}
# Example usage
def analyze_and_suggest(manifest_data: Dict[str, Any]) -> Dict[str, Any]:
"""Analyze project and suggest optimal configuration."""
from collections import Counter
files = manifest_data.get("files", {})
files = manifest_data.get('files', {})
languages = Counter()
large_files = 0
for info in files.values():
lang = info.get("language", "unknown")
lang = info.get('language', 'unknown')
languages[lang] += 1
if info.get("size", 0) > 10000:
if info.get('size', 0) > 10000:
large_files += 1
stats = {
"languages": dict(languages),
"large_files": large_files,
"total_files": len(files),
'languages': dict(languages),
'large_files': large_files,
'total_files': len(files)
}
strategy = SmartChunkingStrategy()
return strategy.get_smart_defaults(stats)
return strategy.get_smart_defaults(stats)

121
mini_rag/system_context.py
View File

@ -1,121 +0,0 @@
"""
System Context Collection for Enhanced RAG Grounding
Collects minimal system information to help the LLM provide better,
context-aware assistance without compromising privacy.
"""
import platform
import sys
from pathlib import Path
from typing import Dict, Optional
class SystemContextCollector:
"""Collects system context information for enhanced LLM grounding."""
@staticmethod
def get_system_context(project_path: Optional[Path] = None) -> str:
"""
Get concise system context for LLM grounding.
Args:
project_path: Current project directory
Returns:
Formatted system context string (max 200 chars for privacy)
"""
try:
# Basic system info
os_name = platform.system()
python_ver = f"{sys.version_info.major}.{sys.version_info.minor}"
# Simplified OS names
os_short = {"Windows": "Win", "Linux": "Linux", "Darwin": "macOS"}.get(
os_name, os_name
)
# Working directory info
if project_path:
# Use relative or shortened path for privacy
try:
rel_path = project_path.relative_to(Path.home())
path_info = f"~/{rel_path}"
except ValueError:
# If not relative to home, just use folder name
path_info = project_path.name
else:
path_info = Path.cwd().name
# Trim path if too long for our 200-char limit
if len(path_info) > 50:
path_info = f".../{path_info[-45:]}"
# Command style hints
cmd_style = "rag.bat" if os_name == "Windows" else "./rag-mini"
# Format concise context
context = f"[{os_short} {python_ver}, {path_info}, use {cmd_style}]"
# Ensure we stay under 200 chars
if len(context) > 200:
context = context[:197] + "...]"
return context
except Exception:
# Fallback to minimal info if anything fails
return f"[{platform.system()}, Python {sys.version_info.major}.{sys.version_info.minor}]"
@staticmethod
def get_command_context(os_name: Optional[str] = None) -> Dict[str, str]:
"""
Get OS-appropriate command examples.
Returns:
Dictionary with command patterns for the current OS
"""
if os_name is None:
os_name = platform.system()
if os_name == "Windows":
return {
"launcher": "rag.bat",
"index": "rag.bat index C:\\path\\to\\project",
"search": 'rag.bat search C:\\path\\to\\project "query"',
"explore": "rag.bat explore C:\\path\\to\\project",
"path_sep": "\\",
"example_path": "C:\\Users\\username\\Documents\\myproject",
}
else:
return {
"launcher": "./rag-mini",
"index": "./rag-mini index /path/to/project",
"search": './rag-mini search /path/to/project "query"',
"explore": "./rag-mini explore /path/to/project",
"path_sep": "/",
"example_path": "~/Documents/myproject",
}
def get_system_context(project_path: Optional[Path] = None) -> str:
"""Convenience function to get system context."""
return SystemContextCollector.get_system_context(project_path)
def get_command_context() -> Dict[str, str]:
"""Convenience function to get command context."""
return SystemContextCollector.get_command_context()
# Test function
if __name__ == "__main__":
print("System Context Test:")
print(f"Context: {get_system_context()}")
print(f"Context with path: {get_system_context(Path('/tmp/test'))}")
print()
print("Command Context:")
cmds = get_command_context()
for key, value in cmds.items():
print(f" {key}: {value}")

301
mini_rag/updater.py
View File

@ -6,32 +6,30 @@ Provides seamless GitHub-based updates with user-friendly interface.
Checks for new releases, downloads updates, and handles installation safely.
"""
import json
import os
import shutil
import subprocess
import sys
import tempfile
import json
import time
import shutil
import zipfile
from dataclasses import dataclass
from datetime import datetime, timedelta
import tempfile
import subprocess
from pathlib import Path
from typing import Optional, Tuple
from typing import Optional, Dict, Any, Tuple
from datetime import datetime, timedelta
from dataclasses import dataclass
try:
import requests
REQUESTS_AVAILABLE = True
except ImportError:
REQUESTS_AVAILABLE = False
from .config import ConfigManager
@dataclass
class UpdateInfo:
"""Information about an available update."""
version: str
release_url: str
download_url: str
@ -39,45 +37,42 @@ class UpdateInfo:
published_at: str
is_newer: bool
class UpdateChecker:
"""
Handles checking for and applying updates from GitHub releases.
Features:
- Checks GitHub API for latest releases
- Downloads and applies updates safely with backup
- Respects user preferences and rate limiting
- Provides graceful fallbacks if network unavailable
"""
def __init__(
self,
repo_owner: str = "FSSCoding",
repo_name: str = "Fss-Mini-Rag",
current_version: str = "2.1.0",
):
def __init__(self,
repo_owner: str = "FSSCoding",
repo_name: str = "Fss-Mini-Rag",
current_version: str = "2.1.0"):
self.repo_owner = repo_owner
self.repo_name = repo_name
self.current_version = current_version
self.github_api_url = f"https://api.github.com/repos/{repo_owner}/{repo_name}"
self.check_frequency_hours = 24 # Check once per day
# Paths
self.app_root = Path(__file__).parent.parent
self.cache_file = self.app_root / ".update_cache.json"
self.backup_dir = self.app_root / ".backup"
# User preferences (graceful fallback if config unavailable)
try:
self.config = ConfigManager(self.app_root)
except Exception:
self.config = None
def should_check_for_updates(self) -> bool:
"""
Determine if we should check for updates now.
Respects:
- User preference to disable updates
- Rate limiting (once per day by default)
@ -85,74 +80,70 @@ class UpdateChecker:
"""
if not REQUESTS_AVAILABLE:
return False
# Check user preference
if hasattr(self.config, "updates") and not getattr(
self.config.updates, "auto_check", True
):
if hasattr(self.config, 'updates') and not getattr(self.config.updates, 'auto_check', True):
return False
# Check if we've checked recently
if self.cache_file.exists():
try:
with open(self.cache_file, "r") as f:
with open(self.cache_file, 'r') as f:
cache = json.load(f)
last_check = datetime.fromisoformat(cache.get("last_check", "2020-01-01"))
if datetime.now() - last_check < timedelta(
hours=self.check_frequency_hours
):
last_check = datetime.fromisoformat(cache.get('last_check', '2020-01-01'))
if datetime.now() - last_check < timedelta(hours=self.check_frequency_hours):
return False
except (json.JSONDecodeError, ValueError, KeyError):
pass # Ignore cache errors, will check anyway
return True
def check_for_updates(self) -> Optional[UpdateInfo]:
"""
Check GitHub API for the latest release.
Returns:
UpdateInfo if an update is available, None otherwise
"""
if not REQUESTS_AVAILABLE:
return None
try:
# Get latest release from GitHub API
response = requests.get(
f"{self.github_api_url}/releases/latest",
timeout=10,
headers={"Accept": "application/vnd.github.v3+json"},
headers={"Accept": "application/vnd.github.v3+json"}
)
if response.status_code != 200:
return None
release_data = response.json()
# Extract version info
latest_version = release_data.get("tag_name", "").lstrip("v")
release_notes = release_data.get("body", "No release notes available.")
published_at = release_data.get("published_at", "")
release_url = release_data.get("html_url", "")
latest_version = release_data.get('tag_name', '').lstrip('v')
release_notes = release_data.get('body', 'No release notes available.')
published_at = release_data.get('published_at', '')
release_url = release_data.get('html_url', '')
# Find download URL for source code
download_url = None
for asset in release_data.get("assets", []):
if asset.get("name", "").endswith(".zip"):
download_url = asset.get("browser_download_url")
for asset in release_data.get('assets', []):
if asset.get('name', '').endswith('.zip'):
download_url = asset.get('browser_download_url')
break
# Fallback to source code zip
if not download_url:
download_url = f"https://github.com/{self.repo_owner}/{self.repo_name}/archive/refs/tags/v{latest_version}.zip"
# Check if this is a newer version
is_newer = self._is_version_newer(latest_version, self.current_version)
# Update cache
self._update_cache(latest_version, is_newer)
if is_newer:
return UpdateInfo(
version=latest_version,
@ -160,95 +151,92 @@ class UpdateChecker:
download_url=download_url,
release_notes=release_notes,
published_at=published_at,
is_newer=True,
is_newer=True
)
except Exception:
except Exception as e:
# Silently fail for network issues - don't interrupt user experience
pass
return None
def _is_version_newer(self, latest: str, current: str) -> bool:
"""
Compare version strings to determine if latest is newer.
Simple semantic version comparison supporting:
- Major.Minor.Patch (e.g., 2.1.0)
- Major.Minor (e.g., 2.1)
"""
def version_tuple(v):
return tuple(map(int, (v.split("."))))
try:
return version_tuple(latest) > version_tuple(current)
except (ValueError, AttributeError):
# If version parsing fails, assume it's newer to be safe
return latest != current
def _update_cache(self, latest_version: str, is_newer: bool):
"""Update the cache file with check results."""
cache_data = {
"last_check": datetime.now().isoformat(),
"latest_version": latest_version,
"is_newer": is_newer,
'last_check': datetime.now().isoformat(),
'latest_version': latest_version,
'is_newer': is_newer
}
try:
with open(self.cache_file, "w") as f:
with open(self.cache_file, 'w') as f:
json.dump(cache_data, f, indent=2)
except Exception:
pass # Ignore cache write errors
def download_update(
self, update_info: UpdateInfo, progress_callback=None
) -> Optional[Path]:
def download_update(self, update_info: UpdateInfo, progress_callback=None) -> Optional[Path]:
"""
Download the update package to a temporary location.
Args:
update_info: Information about the update to download
progress_callback: Optional callback for progress updates
Returns:
Path to downloaded file, or None if download failed
"""
if not REQUESTS_AVAILABLE:
return None
try:
# Create temporary file for download
with tempfile.NamedTemporaryFile(suffix=".zip", delete=False) as tmp_file:
with tempfile.NamedTemporaryFile(suffix='.zip', delete=False) as tmp_file:
tmp_path = Path(tmp_file.name)
# Download with progress tracking
response = requests.get(update_info.download_url, stream=True, timeout=30)
response.raise_for_status()
total_size = int(response.headers.get("content-length", 0))
total_size = int(response.headers.get('content-length', 0))
downloaded = 0
with open(tmp_path, "wb") as f:
with open(tmp_path, 'wb') as f:
for chunk in response.iter_content(chunk_size=8192):
if chunk:
f.write(chunk)
downloaded += len(chunk)
if progress_callback and total_size > 0:
progress_callback(downloaded, total_size)
return tmp_path
except Exception:
except Exception as e:
# Clean up on error
if "tmp_path" in locals() and tmp_path.exists():
if 'tmp_path' in locals() and tmp_path.exists():
tmp_path.unlink()
return None
def create_backup(self) -> bool:
"""
Create a backup of the current installation.
Returns:
True if backup created successfully
"""
@ -256,22 +244,22 @@ class UpdateChecker:
# Remove old backup if it exists
if self.backup_dir.exists():
shutil.rmtree(self.backup_dir)
# Create new backup
self.backup_dir.mkdir(exist_ok=True)
# Copy key files and directories
important_items = [
"mini_rag",
"rag-mini.py",
"rag-tui.py",
"requirements.txt",
"install_mini_rag.sh",
"install_windows.bat",
"README.md",
"assets",
'mini_rag',
'rag-mini.py',
'rag-tui.py',
'requirements.txt',
'install_mini_rag.sh',
'install_windows.bat',
'README.md',
'assets'
]
for item in important_items:
src = self.app_root / item
if src.exists():
@ -279,20 +267,20 @@ class UpdateChecker:
shutil.copytree(src, self.backup_dir / item)
else:
shutil.copy2(src, self.backup_dir / item)
return True
except Exception:
except Exception as e:
return False
def apply_update(self, update_package_path: Path, update_info: UpdateInfo) -> bool:
"""
Apply the downloaded update.
Args:
update_package_path: Path to the downloaded update package
update_info: Information about the update
Returns:
True if update applied successfully
"""
@ -300,140 +288,133 @@ class UpdateChecker:
# Extract to temporary directory first
with tempfile.TemporaryDirectory() as tmp_dir:
tmp_path = Path(tmp_dir)
# Extract the archive
with zipfile.ZipFile(update_package_path, "r") as zip_ref:
with zipfile.ZipFile(update_package_path, 'r') as zip_ref:
zip_ref.extractall(tmp_path)
# Find the extracted directory (may be nested)
extracted_dirs = [d for d in tmp_path.iterdir() if d.is_dir()]
if not extracted_dirs:
return False
source_dir = extracted_dirs[0]
# Copy files to application directory
important_items = [
"mini_rag",
"rag-mini.py",
"rag-tui.py",
"requirements.txt",
"install_mini_rag.sh",
"install_windows.bat",
"README.md",
'mini_rag',
'rag-mini.py',
'rag-tui.py',
'requirements.txt',
'install_mini_rag.sh',
'install_windows.bat',
'README.md'
]
for item in important_items:
src = source_dir / item
dst = self.app_root / item
if src.exists():
if dst.exists():
if dst.is_dir():
shutil.rmtree(dst)
else:
dst.unlink()
if src.is_dir():
shutil.copytree(src, dst)
else:
shutil.copy2(src, dst)
# Update version info
self._update_version_info(update_info.version)
return True
except Exception:
except Exception as e:
return False
def _update_version_info(self, new_version: str):
"""Update version information in the application."""
# Update __init__.py version
init_file = self.app_root / "mini_rag" / "__init__.py"
init_file = self.app_root / 'mini_rag' / '__init__.py'
if init_file.exists():
try:
content = init_file.read_text()
updated_content = content.replace(
f'__version__ = "{self.current_version}"',
f'__version__ = "{new_version}"',
f'__version__ = "{new_version}"'
)
init_file.write_text(updated_content)
except Exception:
pass
def rollback_update(self) -> bool:
"""
Rollback to the backup version if update failed.
Returns:
True if rollback successful
"""
if not self.backup_dir.exists():
return False
try:
# Restore from backup
for item in self.backup_dir.iterdir():
dst = self.app_root / item.name
if dst.exists():
if dst.is_dir():
shutil.rmtree(dst)
else:
dst.unlink()
if item.is_dir():
shutil.copytree(item, dst)
else:
shutil.copy2(item, dst)
return True
except Exception:
except Exception as e:
return False
def restart_application(self):
"""Restart the application after update."""
try:
# Sanitize arguments to prevent command injection
safe_argv = [sys.executable]
for arg in sys.argv[1:]: # Skip sys.argv[0] (script name)
# Only allow safe arguments - alphanumeric, dashes, dots, slashes
if isinstance(arg, str) and len(arg) < 200: # Reasonable length limit
# Simple whitelist of safe characters
import re
if re.match(r'^[a-zA-Z0-9._/-]+$', arg):
safe_argv.append(arg)
# Restart with sanitized arguments
if sys.platform.startswith("win"):
# Get the current script path
current_script = sys.argv[0]
# Restart with the same arguments
if sys.platform.startswith('win'):
# Windows
subprocess.Popen(safe_argv)
subprocess.Popen([sys.executable] + sys.argv)
else:
# Unix-like systems
os.execv(sys.executable, safe_argv)
except Exception:
os.execv(sys.executable, [sys.executable] + sys.argv)
except Exception as e:
# If restart fails, just exit gracefully
print("\n✅ Update complete! Please restart the application manually.")
print(f"\n✅ Update complete! Please restart the application manually.")
sys.exit(0)
def get_legacy_notification() -> Optional[str]:
"""
Check if this is a legacy version that needs urgent notification.
For users who downloaded before the auto-update system.
"""
try:
# Check if this is a very old version by looking for cache file
# Old versions won't have update cache, so we can detect them
app_root = Path(__file__).parent.parent
# app_root / ".update_cache.json" # Unused variable removed
cache_file = app_root / ".update_cache.json"
# Also check version in __init__.py to see if it's old
init_file = app_root / "mini_rag" / "__init__.py"
init_file = app_root / 'mini_rag' / '__init__.py'
if init_file.exists():
content = init_file.read_text()
if '__version__ = "2.0.' in content or '__version__ = "1.' in content:
@ -443,7 +424,7 @@ def get_legacy_notification() -> Optional[str]:
Your version of FSS-Mini-RAG is missing critical updates!
🔧 Recent improvements include:
• Fixed LLM response formatting issues
• Fixed LLM response formatting issues
• Added context window configuration
• Improved Windows installer reliability
• Added auto-update system (this notification!)
@ -455,28 +436,26 @@ Your version of FSS-Mini-RAG is missing critical updates!
"""
except Exception:
pass
return None
# Global convenience functions
_updater_instance = None
def check_for_updates() -> Optional[UpdateInfo]:
"""Global function to check for updates."""
global _updater_instance
if _updater_instance is None:
_updater_instance = UpdateChecker()
if _updater_instance.should_check_for_updates():
return _updater_instance.check_for_updates()
return None
def get_updater() -> UpdateChecker:
"""Get the global updater instance."""
global _updater_instance
if _updater_instance is None:
_updater_instance = UpdateChecker()
return _updater_instance
return _updater_instance

64
mini_rag/venv_checker.py
View File

@ -4,70 +4,64 @@ Virtual Environment Checker
Ensures scripts run in proper Python virtual environment for consistency and safety.
"""
import os
import sys
import os
import sysconfig
from pathlib import Path
def is_in_virtualenv() -> bool:
"""Check if we're running in a virtual environment."""
# Check for virtual environment indicators
return (
hasattr(sys, "real_prefix")
or (hasattr(sys, "base_prefix") and sys.base_prefix != sys.prefix) # virtualenv
or os.environ.get("VIRTUAL_ENV") is not None # venv/pyvenv # Environment variable
hasattr(sys, 'real_prefix') or # virtualenv
(hasattr(sys, 'base_prefix') and sys.base_prefix != sys.prefix) or # venv/pyvenv
os.environ.get('VIRTUAL_ENV') is not None # Environment variable
)
def get_expected_venv_path() -> Path:
"""Get the expected virtual environment path for this project."""
# Assume .venv in the same directory as the script
script_dir = Path(__file__).parent.parent
return script_dir / ".venv"
return script_dir / '.venv'
def check_correct_venv() -> tuple[bool, str]:
"""
Check if we're in the correct virtual environment.
Returns:
(is_correct, message)
"""
if not is_in_virtualenv():
return False, "not in virtual environment"
expected_venv = get_expected_venv_path()
if not expected_venv.exists():
return False, "expected virtual environment not found"
current_venv = os.environ.get("VIRTUAL_ENV")
current_venv = os.environ.get('VIRTUAL_ENV')
if current_venv:
current_venv_path = Path(current_venv).resolve()
expected_venv_path = expected_venv.resolve()
if current_venv_path != expected_venv_path:
return (
False,
f"wrong virtual environment (using {current_venv_path}, expected {expected_venv_path})",
)
return False, f"wrong virtual environment (using {current_venv_path}, expected {expected_venv_path})"
return True, "correct virtual environment"
def show_venv_warning(script_name: str = "script") -> None:
"""Show virtual environment warning with helpful instructions."""
expected_venv = get_expected_venv_path()
print("⚠️ VIRTUAL ENVIRONMENT WARNING")
print("=" * 50)
print()
print(f"This {script_name} should be run in a Python virtual environment for:")
print(" • Consistent dependencies")
print(" • Isolated package versions")
print(" • Isolated package versions")
print(" • Proper security isolation")
print(" • Reliable functionality")
print()
if expected_venv.exists():
print("✅ Virtual environment found!")
print(f" Location: {expected_venv}")
@ -88,7 +82,7 @@ def show_venv_warning(script_name: str = "script") -> None:
print(f" python3 -m venv {expected_venv}")
print(f" source {expected_venv}/bin/activate")
print(" pip install -r requirements.txt")
print()
print("💡 Why this matters:")
print(" Without a virtual environment, you may experience:")
@ -98,23 +92,22 @@ def show_venv_warning(script_name: str = "script") -> None:
print(" • Potential system-wide package pollution")
print()
def check_and_warn_venv(script_name: str = "script", force_exit: bool = False) -> bool:
"""
Check virtual environment and warn if needed.
Args:
script_name: Name of the script for user-friendly messages
force_exit: Whether to exit if not in correct venv
Returns:
True if in correct venv, False otherwise
"""
is_correct, message = check_correct_venv()
if not is_correct:
show_venv_warning(script_name)
if force_exit:
print(f"⛔ Exiting {script_name} for your safety.")
print(" Please activate the virtual environment and try again.")
@ -123,32 +116,27 @@ def check_and_warn_venv(script_name: str = "script", force_exit: bool = False) -
print(f"⚠️ Continuing anyway, but {script_name} may not work correctly...")
print()
return False
return True
def require_venv(script_name: str = "script") -> None:
"""Require virtual environment or exit."""
check_and_warn_venv(script_name, force_exit=True)
# Quick test function
def main():
"""Test the virtual environment checker."""
print("🧪 Virtual Environment Checker Test")
print("=" * 40)
print(f"In virtual environment: {is_in_virtualenv()}")
print(f"Expected venv path: {get_expected_venv_path()}")
is_correct, message = check_correct_venv()
print(f"Correct venv: {is_correct} ({message})")
if not is_correct:
show_venv_warning("test script")
if __name__ == "__main__":
main()
main()

228
mini_rag/watcher.py
View File

@ -4,21 +4,14 @@ Monitors project files and updates the index incrementally.
"""
import logging
import queue
import threading
import queue
import time
from datetime import datetime
from pathlib import Path
from typing import Callable, Optional, Set
from watchdog.events import (
FileCreatedEvent,
FileDeletedEvent,
FileModifiedEvent,
FileMovedEvent,
FileSystemEventHandler,
)
from typing import Set, Optional, Callable
from datetime import datetime
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler, FileModifiedEvent, FileCreatedEvent, FileDeletedEvent, FileMovedEvent
from .indexer import ProjectIndexer
@ -27,11 +20,11 @@ logger = logging.getLogger(__name__)
class UpdateQueue:
"""Thread-safe queue for file updates with deduplication."""
def __init__(self, delay: float = 1.0):
"""
Initialize update queue.
Args:
delay: Delay in seconds before processing updates (for debouncing)
"""
@ -40,24 +33,24 @@ class UpdateQueue:
self.lock = threading.Lock()
self.delay = delay
self.last_update = {} # Track last update time per file
def add(self, file_path: Path):
"""Add a file to the update queue."""
with self.lock:
file_str = str(file_path)
current_time = time.time()
# Check if we should debounce this update
if file_str in self.last_update:
if current_time - self.last_update[file_str] < self.delay:
return # Skip this update
self.last_update[file_str] = current_time
if file_str not in self.pending:
self.pending.add(file_str)
self.queue.put(file_path)
def get(self, timeout: Optional[float] = None) -> Optional[Path]:
"""Get next file from queue."""
try:
@ -67,11 +60,11 @@ class UpdateQueue:
return file_path
except queue.Empty:
return None
def empty(self) -> bool:
"""Check if queue is empty."""
return self.queue.empty()
def size(self) -> int:
"""Get queue size."""
return self.queue.qsize()
@ -79,17 +72,15 @@ class UpdateQueue:
class CodeFileEventHandler(FileSystemEventHandler):
"""Handles file system events for code files."""
def __init__(
self,
update_queue: UpdateQueue,
include_patterns: Set[str],
exclude_patterns: Set[str],
project_path: Path,
):
def __init__(self,
update_queue: UpdateQueue,
include_patterns: Set[str],
exclude_patterns: Set[str],
project_path: Path):
"""
Initialize event handler.
Args:
update_queue: Queue for file updates
include_patterns: File patterns to include
@ -100,47 +91,47 @@ class CodeFileEventHandler(FileSystemEventHandler):
self.include_patterns = include_patterns
self.exclude_patterns = exclude_patterns
self.project_path = project_path
def _should_process(self, file_path: str) -> bool:
"""Check if file should be processed."""
path = Path(file_path)
# Check if it's a file (not directory)
if not path.is_file():
return False
# Check exclude patterns
path_str = str(path)
for pattern in self.exclude_patterns:
if pattern in path_str:
return False
# Check include patterns
for pattern in self.include_patterns:
if path.match(pattern):
return True
return False
def on_modified(self, event: FileModifiedEvent):
"""Handle file modification."""
if not event.is_directory and self._should_process(event.src_path):
logger.debug(f"File modified: {event.src_path}")
self.update_queue.add(Path(event.src_path))
def on_created(self, event: FileCreatedEvent):
"""Handle file creation."""
if not event.is_directory and self._should_process(event.src_path):
logger.debug(f"File created: {event.src_path}")
self.update_queue.add(Path(event.src_path))
def on_deleted(self, event: FileDeletedEvent):
"""Handle file deletion."""
if not event.is_directory and self._should_process(event.src_path):
logger.debug(f"File deleted: {event.src_path}")
# Add deletion task to queue (we'll handle it differently)
self.update_queue.add(Path(event.src_path))
def on_moved(self, event: FileMovedEvent):
"""Handle file move/rename."""
if not event.is_directory:
@ -154,18 +145,16 @@ class CodeFileEventHandler(FileSystemEventHandler):
class FileWatcher:
"""Watches project files and updates index automatically."""
def __init__(
self,
project_path: Path,
indexer: Optional[ProjectIndexer] = None,
update_delay: float = 1.0,
batch_size: int = 10,
batch_timeout: float = 5.0,
):
def __init__(self,
project_path: Path,
indexer: Optional[ProjectIndexer] = None,
update_delay: float = 1.0,
batch_size: int = 10,
batch_timeout: float = 5.0):
"""
Initialize file watcher.
Args:
project_path: Path to project to watch
indexer: ProjectIndexer instance (creates one if not provided)
@ -178,79 +167,86 @@ class FileWatcher:
self.update_delay = update_delay
self.batch_size = batch_size
self.batch_timeout = batch_timeout
# Initialize components
self.update_queue = UpdateQueue(delay=update_delay)
self.observer = Observer()
self.worker_thread = None
self.running = False
# Get patterns from indexer
self.include_patterns = set(self.indexer.include_patterns)
self.exclude_patterns = set(self.indexer.exclude_patterns)
# Statistics
self.stats = {
"files_updated": 0,
"files_failed": 0,
"started_at": None,
"last_update": None,
'files_updated': 0,
'files_failed': 0,
'started_at': None,
'last_update': None,
}
def start(self):
"""Start watching for file changes."""
if self.running:
logger.warning("Watcher is already running")
return
logger.info(f"Starting file watcher for {self.project_path}")
# Set up file system observer
event_handler = CodeFileEventHandler(
self.update_queue,
self.include_patterns,
self.exclude_patterns,
self.project_path,
self.project_path
)
self.observer.schedule(event_handler, str(self.project_path), recursive=True)
self.observer.schedule(
event_handler,
str(self.project_path),
recursive=True
)
# Start worker thread
self.running = True
self.worker_thread = threading.Thread(target=self._process_updates, daemon=True)
self.worker_thread = threading.Thread(
target=self._process_updates,
daemon=True
)
self.worker_thread.start()
# Start observer
self.observer.start()
self.stats["started_at"] = datetime.now()
self.stats['started_at'] = datetime.now()
logger.info("File watcher started successfully")
def stop(self):
"""Stop watching for file changes."""
if not self.running:
return
logger.info("Stopping file watcher...")
# Stop observer
self.observer.stop()
self.observer.join()
# Stop worker thread
self.running = False
if self.worker_thread:
self.worker_thread.join(timeout=5.0)
logger.info("File watcher stopped")
def _process_updates(self):
"""Worker thread that processes file updates."""
logger.info("Update processor thread started")
batch = []
batch_start_time = None
while self.running:
try:
# Calculate timeout for getting next item
@ -267,46 +263,46 @@ class FileWatcher:
else:
# Wait for more items or timeout
timeout = min(0.1, self.batch_timeout - elapsed)
# Get next file from queue
file_path = self.update_queue.get(timeout=timeout)
if file_path:
# Add to batch
if not batch:
batch_start_time = time.time()
batch.append(file_path)
# Check if batch is full
if len(batch) >= self.batch_size:
self._process_batch(batch)
batch = []
batch_start_time = None
except queue.Empty:
# Check if we have a pending batch that's timed out
if batch and (time.time() - batch_start_time) >= self.batch_timeout:
self._process_batch(batch)
batch = []
batch_start_time = None
except Exception as e:
logger.error(f"Error in update processor: {e}")
time.sleep(1) # Prevent tight loop on error
# Process any remaining items
if batch:
self._process_batch(batch)
logger.info("Update processor thread stopped")
def _process_batch(self, files: list[Path]):
"""Process a batch of file updates."""
if not files:
return
logger.info(f"Processing batch of {len(files)} file updates")
for file_path in files:
try:
if file_path.exists():
@ -317,91 +313,87 @@ class FileWatcher:
# File doesn't exist - delete from index
logger.debug(f"Deleting {file_path} from index - file no longer exists")
success = self.indexer.delete_file(file_path)
if success:
self.stats["files_updated"] += 1
self.stats['files_updated'] += 1
else:
self.stats["files_failed"] += 1
self.stats["last_update"] = datetime.now()
self.stats['files_failed'] += 1
self.stats['last_update'] = datetime.now()
except Exception as e:
logger.error(f"Failed to process {file_path}: {e}")
self.stats["files_failed"] += 1
logger.info(
f"Batch processing complete. Updated: {self.stats['files_updated']}, Failed: {self.stats['files_failed']}"
)
self.stats['files_failed'] += 1
logger.info(f"Batch processing complete. Updated: {self.stats['files_updated']}, Failed: {self.stats['files_failed']}")
def get_statistics(self) -> dict:
"""Get watcher statistics."""
stats = self.stats.copy()
stats["queue_size"] = self.update_queue.size()
stats["is_running"] = self.running
if stats["started_at"]:
uptime = datetime.now() - stats["started_at"]
stats["uptime_seconds"] = uptime.total_seconds()
stats['queue_size'] = self.update_queue.size()
stats['is_running'] = self.running
if stats['started_at']:
uptime = datetime.now() - stats['started_at']
stats['uptime_seconds'] = uptime.total_seconds()
return stats
def wait_for_updates(self, timeout: Optional[float] = None) -> bool:
"""
Wait for pending updates to complete.
Args:
timeout: Maximum time to wait in seconds
Returns:
True if all updates completed, False if timeout
"""
start_time = time.time()
while not self.update_queue.empty():
if timeout and (time.time() - start_time) > timeout:
return False
time.sleep(0.1)
# Wait a bit more to ensure batch processing completes
time.sleep(self.batch_timeout + 0.5)
return True
def __enter__(self):
"""Context manager entry."""
self.start()
return self
def __exit__(self, exc_type, exc_val, exc_tb):
"""Context manager exit."""
self.stop()
# Convenience function
def watch_project(project_path: Path, callback: Optional[Callable] = None):
"""
Watch a project for changes and update index automatically.
Args:
project_path: Path to project
callback: Optional callback function called after each update
"""
watcher = FileWatcher(project_path)
try:
watcher.start()
logger.info(f"Watching {project_path} for changes. Press Ctrl+C to stop.")
while True:
time.sleep(1)
# Call callback if provided
if callback:
stats = watcher.get_statistics()
callback(stats)
except KeyboardInterrupt:
logger.info("Stopping watcher...")
finally:
watcher.stop()
watcher.stop()

45
mini_rag/windows_console_fix.py
View File

@ -3,9 +3,9 @@ Windows Console Unicode/Emoji Fix
Reliable Windows console Unicode/emoji support for 2025.
"""
import io
import os
import sys
import os
import io
def fix_windows_console():
@ -14,33 +14,28 @@ def fix_windows_console():
Call this at the start of any script that needs to output Unicode/emojis.
"""
# Set environment variable for UTF-8 mode
os.environ["PYTHONUTF8"] = "1"
os.environ['PYTHONUTF8'] = '1'
# For Python 3.7+
if hasattr(sys.stdout, "reconfigure"):
sys.stdout.reconfigure(encoding="utf-8")
sys.stderr.reconfigure(encoding="utf-8")
if hasattr(sys.stdin, "reconfigure"):
sys.stdin.reconfigure(encoding="utf-8")
if hasattr(sys.stdout, 'reconfigure'):
sys.stdout.reconfigure(encoding='utf-8')
sys.stderr.reconfigure(encoding='utf-8')
if hasattr(sys.stdin, 'reconfigure'):
sys.stdin.reconfigure(encoding='utf-8')
else:
# For older Python versions
if sys.platform == "win32":
if sys.platform == 'win32':
# Replace streams with UTF-8 versions
sys.stdout = io.TextIOWrapper(
sys.stdout.buffer, encoding="utf-8", line_buffering=True
)
sys.stderr = io.TextIOWrapper(
sys.stderr.buffer, encoding="utf-8", line_buffering=True
)
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', line_buffering=True)
sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8', line_buffering=True)
# Also set the console code page to UTF-8 on Windows
if sys.platform == "win32":
if sys.platform == 'win32':
import subprocess
try:
# Set console to UTF-8 code page
subprocess.run(["chcp", "65001"], shell=True, capture_output=True)
except (OSError, subprocess.SubprocessError):
subprocess.run(['chcp', '65001'], shell=True, capture_output=True)
except:
pass
@ -49,14 +44,12 @@ fix_windows_console()
# Test function to verify it works
def test_emojis():
"""Test that emojis work properly."""
print("Testing emoji output:")
print(" Check mark")
print(" Cross mark")
print(" Rocket")
print(" Rocket")
print(" Fire")
print(" Computer")
print(" Python")
@ -64,7 +57,7 @@ def test_emojis():
print(" Search")
print(" Lightning")
print(" Sparkles")
if __name__ == "__main__":
test_emojis()
test_emojis()

61
pyproject.toml
View File

@ -1,61 +0,0 @@
[tool.isort]
profile = "black"
line_length = 95
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true
src_paths = ["mini_rag", "tests", "examples", "scripts"]
known_first_party = ["mini_rag"]
sections = ["FUTURE", "STDLIB", "THIRDPARTY", "FIRSTPARTY", "LOCALFOLDER"]
skip = [".venv", ".venv-linting", "__pycache__", ".git"]
skip_glob = ["*.egg-info/*", "build/*", "dist/*"]
[tool.black]
line-length = 95
target-version = ['py310']
include = '\.pyi?$'
extend-exclude = '''
/(
# directories
\.eggs
| \.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| \.venv-linting
| _build
| buck-out
| build
| dist
)/
'''
[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "mini-rag"
version = "2.1.0"
dependencies = [
"lancedb>=0.5.0",
"pandas>=2.0.0",
"numpy>=1.24.0",
"pyarrow>=14.0.0",
"watchdog>=3.0.0",
"requests>=2.28.0",
"click>=8.1.0",
"rich>=13.0.0",
"PyYAML>=6.0.0",
"rank-bm25>=0.2.2",
"psutil"
]
[project.scripts]
rag-mini = "mini_rag.cli:cli"
[tool.setuptools]
packages = ["mini_rag"]

3
rag-mini
View File

@ -60,7 +60,6 @@ attempt_auto_setup() {
echo -e "${GREEN}✅ Created virtual environment${NC}" >&2
# Step 2: Install dependencies
echo -e "${YELLOW}📦 Installing dependencies (this may take 1-2 minutes)...${NC}" >&2
if ! "$SCRIPT_DIR/.venv/bin/pip" install -r "$SCRIPT_DIR/requirements.txt" >/dev/null 2>&1; then
return 1 # Dependency installation failed
fi
@ -330,7 +329,7 @@ main() {
;;
"index"|"search"|"explore"|"status"|"update"|"check-update")
# Direct CLI commands - call Python script
exec "$PYTHON" "$SCRIPT_DIR/bin/rag-mini.py" "$@"
exec "$PYTHON" "$SCRIPT_DIR/rag-mini.py" "$@"
;;
*)
# Unknown command - show help

519
bin/rag-mini.py → rag-mini.py
View File

@ -6,32 +6,24 @@ A lightweight, portable RAG system for semantic code search.
Usage: rag-mini <command> <project_path> [options]
"""
import sys
import argparse
from pathlib import Path
import json
import logging
import socket
import sys
from pathlib import Path
# Add parent directory to path so we can import mini_rag
sys.path.insert(0, str(Path(__file__).parent.parent))
import requests
# Add the RAG system to the path
sys.path.insert(0, str(Path(__file__).parent))
try:
from mini_rag.explorer import CodeExplorer
from mini_rag.indexer import ProjectIndexer
from mini_rag.llm_synthesizer import LLMSynthesizer
from mini_rag.ollama_embeddings import OllamaEmbedder
from mini_rag.search import CodeSearcher
from mini_rag.ollama_embeddings import OllamaEmbedder
from mini_rag.llm_synthesizer import LLMSynthesizer
from mini_rag.explorer import CodeExplorer
# Update system (graceful import)
try:
from mini_rag.updater import check_for_updates, get_updater
UPDATER_AVAILABLE = True
except ImportError:
UPDATER_AVAILABLE = False
@ -56,51 +48,50 @@ except ImportError as e:
# Configure logging for user-friendly output
logging.basicConfig(
level=logging.WARNING, # Only show warnings and errors by default
format="%(levelname)s: %(message)s",
format='%(levelname)s: %(message)s'
)
logger = logging.getLogger(__name__)
def index_project(project_path: Path, force: bool = False):
"""Index a project directory."""
try:
# Show what's happening
action = "Re-indexing" if force else "Indexing"
print(f"🚀 {action} {project_path.name}")
# Quick pre-check
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if rag_dir.exists() and not force:
print(" Checking for changes...")
indexer = ProjectIndexer(project_path)
result = indexer.index_project(force_reindex=force)
# Show results with context
files_count = result.get("files_indexed", 0)
chunks_count = result.get("chunks_created", 0)
time_taken = result.get("time_taken", 0)
files_count = result.get('files_indexed', 0)
chunks_count = result.get('chunks_created', 0)
time_taken = result.get('time_taken', 0)
if files_count == 0:
print("✅ Index up to date - no changes detected")
else:
print(f"✅ Indexed {files_count} files in {time_taken:.1f}s")
print(f" Created {chunks_count} chunks")
# Show efficiency
if time_taken > 0:
speed = files_count / time_taken
print(f" Speed: {speed:.1f} files/sec")
# Show warnings if any
failed_count = result.get("files_failed", 0)
failed_count = result.get('files_failed', 0)
if failed_count > 0:
print(f"⚠️ {failed_count} files failed (check logs with --verbose)")
# Quick tip for first-time users
if not (project_path / ".mini-rag" / "last_search").exists():
print(f'\n💡 Try: rag-mini search {project_path} "your search here"')
if not (project_path / '.mini-rag' / 'last_search').exists():
print(f"\n💡 Try: rag-mini search {project_path} \"your search here\"")
except FileNotFoundError:
print(f"📁 Directory Not Found: {project_path}")
print(" Make sure the path exists and you're in the right location")
@ -119,7 +110,7 @@ def index_project(project_path: Path, force: bool = False):
# Connection errors are handled in the embedding module
if "ollama" in str(e).lower() or "connection" in str(e).lower():
sys.exit(1) # Error already displayed
print(f"❌ Indexing failed: {e}")
print()
print("🔧 Common solutions:")
@ -133,44 +124,39 @@ def index_project(project_path: Path, force: bool = False):
print(" Or see: docs/TROUBLESHOOTING.md")
sys.exit(1)
def search_project(project_path: Path, query: str, top_k: int = 10, synthesize: bool = False):
"""Search a project directory."""
try:
# Check if indexed first
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
print(f"❌ Project not indexed: {project_path.name}")
print(f" Run: rag-mini index {project_path}")
sys.exit(1)
print(f'🔍 Searching "{query}" in {project_path.name}')
print(f"🔍 Searching \"{query}\" in {project_path.name}")
searcher = CodeSearcher(project_path)
results = searcher.search(query, top_k=top_k)
if not results:
print("❌ No results found")
print()
print("🔧 Quick fixes to try:")
print(' • Use broader terms: "login" instead of "authenticate_user_session"')
print(' • Try concepts: "database query" instead of specific function names')
print(" • Use broader terms: \"login\" instead of \"authenticate_user_session\"")
print(" • Try concepts: \"database query\" instead of specific function names")
print(" • Check spelling and try simpler words")
print(' • Search for file types: "python class" or "javascript function"')
print(" • Search for file types: \"python class\" or \"javascript function\"")
print()
print("⚙️ Configuration adjustments:")
print(
f' • Lower threshold: ./rag-mini search "{project_path}" "{query}" --threshold 0.05'
)
print(
f' • More results: ./rag-mini search "{project_path}" "{query}" --top-k 20'
)
print(f" • Lower threshold: ./rag-mini search \"{project_path}\" \"{query}\" --threshold 0.05")
print(f" • More results: ./rag-mini search \"{project_path}\" \"{query}\" --top-k 20")
print()
print("📚 Need help? See: docs/TROUBLESHOOTING.md")
return
print(f"✅ Found {len(results)} results:")
print()
for i, result in enumerate(results, 1):
# Clean up file path display
file_path = Path(result.file_path)
@ -179,89 +165,61 @@ def search_project(project_path: Path, query: str, top_k: int = 10, synthesize:
except ValueError:
# If relative_to fails, just show the basename
rel_path = file_path.name
print(f"{i}. {rel_path}")
print(f" Score: {result.score:.3f}")
# Show line info if available
if hasattr(result, "start_line") and result.start_line:
if hasattr(result, 'start_line') and result.start_line:
print(f" Lines: {result.start_line}-{result.end_line}")
# Show content preview
if hasattr(result, "name") and result.name:
# Show content preview
if hasattr(result, 'name') and result.name:
print(f" Context: {result.name}")
# Show full content with proper formatting
print(" Content:")
content_lines = result.content.strip().split("\n")
print(f" Content:")
content_lines = result.content.strip().split('\n')
for line in content_lines[:10]: # Show up to 10 lines
print(f" {line}")
if len(content_lines) > 10:
print(f" ... ({len(content_lines) - 10} more lines)")
print(" Use --verbose or rag-mini-enhanced for full context")
print(f" Use --verbose or rag-mini-enhanced for full context")
print()
# LLM Synthesis if requested
if synthesize:
print("🧠 Generating LLM synthesis...")
# Load config to respect user's model preferences
from mini_rag.config import ConfigManager
config_manager = ConfigManager(project_path)
config = config_manager.load_config()
synthesizer = LLMSynthesizer(
model=(
config.llm.synthesis_model
if config.llm.synthesis_model != "auto"
else None
),
config=config,
)
synthesizer = LLMSynthesizer()
if synthesizer.is_available():
synthesis = synthesizer.synthesize_search_results(query, results, project_path)
print()
print(synthesizer.format_synthesis_output(synthesis, query))
# Add guidance for deeper analysis
if synthesis.confidence < 0.7 or any(
word in query.lower() for word in ["why", "how", "explain", "debug"]
):
if synthesis.confidence < 0.7 or any(word in query.lower() for word in ['why', 'how', 'explain', 'debug']):
print("\n💡 Want deeper analysis with reasoning?")
print(f" Try: rag-mini explore {project_path}")
print(
" Exploration mode enables thinking and remembers conversation context."
)
print(" Exploration mode enables thinking and remembers conversation context.")
else:
print("❌ LLM synthesis unavailable")
print(" • Ensure Ollama is running: ollama serve")
print(" • Install a model: ollama pull qwen3:1.7b")
print(" • Check connection to http://localhost:11434")
# Save last search for potential enhancements
try:
(rag_dir / "last_search").write_text(query)
except (
ConnectionError,
FileNotFoundError,
IOError,
OSError,
TimeoutError,
TypeError,
ValueError,
requests.RequestException,
socket.error,
):
(rag_dir / 'last_search').write_text(query)
except:
pass # Don't fail if we can't save
except Exception as e:
print(f"❌ Search failed: {e}")
print()
if "not indexed" in str(e).lower():
print("🔧 Solution:")
print(f" ./rag-mini index {project_path}")
@ -274,45 +232,44 @@ def search_project(project_path: Path, query: str, top_k: int = 10, synthesize:
print(" • Check available memory and disk space")
print()
print("📚 Get detailed error info:")
print(f' ./rag-mini search {project_path} "{query}" --verbose')
print(f" ./rag-mini search {project_path} \"{query}\" --verbose")
print(" Or see: docs/TROUBLESHOOTING.md")
print()
sys.exit(1)
def status_check(project_path: Path):
"""Show status of RAG system."""
try:
print(f"📊 Status for {project_path.name}")
print()
# Check project indexing status first
rag_dir = project_path / ".mini-rag"
rag_dir = project_path / '.mini-rag'
if not rag_dir.exists():
print("❌ Project not indexed")
print(f" Run: rag-mini index {project_path}")
print()
else:
manifest = rag_dir / "manifest.json"
manifest = rag_dir / 'manifest.json'
if manifest.exists():
try:
with open(manifest) as f:
data = json.load(f)
file_count = data.get("file_count", 0)
chunk_count = data.get("chunk_count", 0)
indexed_at = data.get("indexed_at", "Never")
file_count = data.get('file_count', 0)
chunk_count = data.get('chunk_count', 0)
indexed_at = data.get('indexed_at', 'Never')
print("✅ Project indexed")
print(f" Files: {file_count}")
print(f" Chunks: {chunk_count}")
print(f" Last update: {indexed_at}")
# Show average chunks per file
if file_count > 0:
avg_chunks = chunk_count / file_count
print(f" Avg chunks/file: {avg_chunks:.1f}")
print()
except Exception:
print("⚠️ Index exists but manifest unreadable")
@ -321,166 +278,51 @@ def status_check(project_path: Path):
print("⚠️ Index directory exists but incomplete")
print(f" Try: rag-mini index {project_path} --force")
print()
# Check embedding system status
print("🧠 Embedding System:")
try:
embedder = OllamaEmbedder()
emb_info = embedder.get_status()
method = emb_info.get("method", "unknown")
if method == "ollama":
method = emb_info.get('method', 'unknown')
if method == 'ollama':
print(" ✅ Ollama (high quality)")
elif method == "ml":
elif method == 'ml':
print(" ✅ ML fallback (good quality)")
elif method == "hash":
elif method == 'hash':
print(" ⚠️ Hash fallback (basic quality)")
else:
print(f" ❓ Unknown method: {method}")
# Show additional details if available
if "model" in emb_info:
if 'model' in emb_info:
print(f" Model: {emb_info['model']}")
except Exception as e:
print(f" ❌ Status check failed: {e}")
print()
# Check LLM status and show actual vs configured model
print("🤖 LLM System:")
try:
from mini_rag.config import ConfigManager
config_manager = ConfigManager(project_path)
config = config_manager.load_config()
synthesizer = LLMSynthesizer(
model=(
config.llm.synthesis_model
if config.llm.synthesis_model != "auto"
else None
),
config=config,
)
if synthesizer.is_available():
synthesizer._ensure_initialized()
actual_model = synthesizer.model
config_model = config.llm.synthesis_model
if config_model == "auto":
print(f" ✅ Auto-selected: {actual_model}")
elif config_model == actual_model:
print(f" ✅ Using configured: {actual_model}")
else:
print(" ⚠️ Model mismatch!")
print(f" Configured: {config_model}")
print(f" Actually using: {actual_model}")
print(" (Configured model may not be installed)")
print(f" Config file: {config_manager.config_path}")
else:
print(" ❌ Ollama not available")
print(" Start with: ollama serve")
except Exception as e:
print(f" ❌ LLM status check failed: {e}")
# Show last search if available
last_search_file = rag_dir / "last_search" if rag_dir.exists() else None
last_search_file = rag_dir / 'last_search' if rag_dir.exists() else None
if last_search_file and last_search_file.exists():
try:
last_query = last_search_file.read_text().strip()
print(f'\n🔍 Last search: "{last_query}"')
except (FileNotFoundError, IOError, OSError, TypeError, ValueError):
print(f"\n🔍 Last search: \"{last_query}\"")
except:
pass
except Exception as e:
print(f"❌ Status check failed: {e}")
sys.exit(1)
def show_model_status(project_path: Path):
"""Show detailed model status and selection information."""
from mini_rag.config import ConfigManager
print("🤖 Model Status Report")
print("=" * 50)
try:
# Load config
config_manager = ConfigManager()
config = config_manager.load_config(project_path)
# Create LLM synthesizer to check models
synthesizer = LLMSynthesizer(model=config.llm.synthesis_model, config=config)
# Show configured model
print(f"📋 Configured model: {config.llm.synthesis_model}")
# Show available models
available_models = synthesizer.available_models
if available_models:
print(f"\n📦 Available models ({len(available_models)}):")
# Group models by series
qwen3_models = [m for m in available_models if m.startswith('qwen3:')]
qwen25_models = [m for m in available_models if m.startswith('qwen2.5')]
other_models = [m for m in available_models if not (m.startswith('qwen3:') or m.startswith('qwen2.5'))]
if qwen3_models:
print(" 🟢 Qwen3 series (recommended):")
for model in qwen3_models:
is_selected = synthesizer._resolve_model_name(config.llm.synthesis_model) == model
marker = " ✅" if is_selected else " "
print(f"{marker} {model}")
if qwen25_models:
print(" 🟡 Qwen2.5 series:")
for model in qwen25_models:
is_selected = synthesizer._resolve_model_name(config.llm.synthesis_model) == model
marker = " ✅" if is_selected else " "
print(f"{marker} {model}")
if other_models:
print(" 🔵 Other models:")
for model in other_models[:10]: # Limit to first 10
is_selected = synthesizer._resolve_model_name(config.llm.synthesis_model) == model
marker = " ✅" if is_selected else " "
print(f"{marker} {model}")
else:
print("\n❌ No models available from Ollama")
print(" Make sure Ollama is running: ollama serve")
print(" Install models with: ollama pull qwen3:4b")
# Show resolution result
resolved_model = synthesizer._resolve_model_name(config.llm.synthesis_model)
if resolved_model:
if resolved_model != config.llm.synthesis_model:
print(f"\n🔄 Model resolution: {config.llm.synthesis_model} -> {resolved_model}")
else:
print(f"\n✅ Using exact model match: {resolved_model}")
else:
print(f"\n❌ Model '{config.llm.synthesis_model}' not found!")
print(" Consider changing your model in the config file")
print(f"\n📄 Config file: {config_manager.config_path}")
print(" Edit this file to change your model preference")
except Exception as e:
print(f"❌ Model status check failed: {e}")
sys.exit(1)
def explore_interactive(project_path: Path):
"""Interactive exploration mode with thinking and context memory for any documents."""
try:
explorer = CodeExplorer(project_path)
if not explorer.start_exploration_session():
sys.exit(1)
# Show enhanced first-time guidance
print(f"\n🤔 Ask your first question about {project_path.name}:")
print()
@ -489,12 +331,12 @@ def explore_interactive(project_path: Path):
print()
print("🔧 Quick options:")
print(" 1. Help - Show example questions")
print(" 2. Status - Project information")
print(" 2. Status - Project information")
print(" 3. Suggest - Get a random starter question")
print()
is_first_question = True
while True:
try:
# Get user input with clearer prompt
@ -502,12 +344,12 @@ def explore_interactive(project_path: Path):
question = input("📝 Enter question or option (1-3): ").strip()
else:
question = input("\n> ").strip()
# Handle exit commands
if question.lower() in ["quit", "exit", "q"]:
if question.lower() in ['quit', 'exit', 'q']:
print("\n" + explorer.end_session())
break
# Handle empty input
if not question:
if is_first_question:
@ -515,18 +357,17 @@ def explore_interactive(project_path: Path):
else:
print("Please enter a question or 'quit' to exit.")
continue
# Handle numbered options and special commands
if question in ["1"] or question.lower() in ["help", "h"]:
print(
"""
if question in ['1'] or question.lower() in ['help', 'h']:
print("""
🧠 EXPLORATION MODE HELP:
• Ask any question about your documents or code
• I remember our conversation for follow-up questions
• Use 'why', 'how', 'explain' for detailed reasoning
• Type 'summary' to see session overview
• Type 'quit' or 'exit' to end session
💡 Example questions:
• "How does authentication work?"
• "What are the main components?"
@ -534,40 +375,36 @@ def explore_interactive(project_path: Path):
• "Why is this function slow?"
• "What security measures are in place?"
• "How does data flow through this system?"
"""
)
""")
continue
elif question in ["2"] or question.lower() == "status":
print(
"""
elif question in ['2'] or question.lower() == 'status':
print(f"""
📊 PROJECT STATUS: {project_path.name}
• Location: {project_path}
• Exploration session active
• AI model ready for questions
• Conversation memory enabled
"""
)
""")
continue
elif question in ["3"] or question.lower() == "suggest":
elif question in ['3'] or question.lower() == 'suggest':
# Random starter questions for first-time users
if is_first_question:
import random
starters = [
"What are the main components of this project?",
"How is error handling implemented?",
"How is error handling implemented?",
"Show me the authentication and security logic",
"What are the key functions I should understand first?",
"How does data flow through this system?",
"What configuration options are available?",
"Show me the most important files to understand",
"Show me the most important files to understand"
]
suggested = random.choice(starters)
print(f"\n💡 Suggested question: {suggested}")
print(" Press Enter to use this, or type your own question:")
next_input = input("📝 > ").strip()
if not next_input: # User pressed Enter to use suggestion
question = suggested
@ -580,24 +417,24 @@ def explore_interactive(project_path: Path):
print(' "What are the security implications?"')
print(' "Show me related code examples"')
continue
if question.lower() == "summary":
if question.lower() == 'summary':
print("\n" + explorer.get_session_summary())
continue
# Process the question
print(f"\n🔍 Searching {project_path.name}...")
print("🧠 Thinking with AI model...")
response = explorer.explore_question(question)
# Mark as no longer first question after processing
is_first_question = False
if response:
print(f"\n{response}")
else:
print("❌ Sorry, I couldn't process that question. Please try again.")
except KeyboardInterrupt:
print(f"\n\n{explorer.end_session()}")
break
@ -607,94 +444,88 @@ def explore_interactive(project_path: Path):
except Exception as e:
print(f"❌ Error processing question: {e}")
print("Please try again or type 'quit' to exit.")
except Exception as e:
print(f"❌ Failed to start exploration mode: {e}")
print("Make sure the project is indexed first: rag-mini index <project>")
sys.exit(1)
def show_discrete_update_notice():
"""Show a discrete, non-intrusive update notice for CLI users."""
if not UPDATER_AVAILABLE:
return
try:
update_info = check_for_updates()
if update_info:
# Very discrete notice - just one line
print(
f"🔄 (Update v{update_info.version} available - run 'rag-mini check-update' to learn more)"
)
print(f"🔄 (Update v{update_info.version} available - run 'rag-mini check-update' to learn more)")
except Exception:
# Silently ignore any update check failures
pass
def handle_check_update():
"""Handle the check-update command."""
if not UPDATER_AVAILABLE:
print("❌ Update system not available")
print("💡 Try updating to the latest version manually from GitHub")
return
try:
print("🔍 Checking for updates...")
update_info = check_for_updates()
if update_info:
print(f"\n🎉 Update Available: v{update_info.version}")
print("=" * 50)
print("\n📋 What's New:")
notes_lines = update_info.release_notes.split("\n")[:10] # First 10 lines
notes_lines = update_info.release_notes.split('\n')[:10] # First 10 lines
for line in notes_lines:
if line.strip():
print(f" {line.strip()}")
print(f"\n🔗 Release Page: {update_info.release_url}")
print("\n🚀 To install: rag-mini update")
print(f"\n🚀 To install: rag-mini update")
print("💡 Or update manually from GitHub releases")
else:
print("✅ You're already on the latest version!")
except Exception as e:
print(f"❌ Failed to check for updates: {e}")
print("💡 Try updating manually from GitHub")
def handle_update():
"""Handle the update command."""
if not UPDATER_AVAILABLE:
print("❌ Update system not available")
print("💡 Try updating manually from GitHub")
return
try:
print("🔍 Checking for updates...")
update_info = check_for_updates()
if not update_info:
print("✅ You're already on the latest version!")
return
print(f"\n🎉 Update Available: v{update_info.version}")
print("=" * 50)
# Show brief release notes
notes_lines = update_info.release_notes.split("\n")[:5]
notes_lines = update_info.release_notes.split('\n')[:5]
for line in notes_lines:
if line.strip():
print(f" • {line.strip()}")
# Confirm update
confirm = input(f"\n🚀 Install v{update_info.version}? [Y/n]: ").strip().lower()
if confirm in ["", "y", "yes"]:
if confirm in ['', 'y', 'yes']:
updater = get_updater()
print(f"\n📥 Downloading v{update_info.version}...")
# Progress callback
def show_progress(downloaded, total):
if total > 0:
percent = (downloaded / total) * 100
@ -702,17 +533,17 @@ def handle_update():
filled = int(bar_length * downloaded / total)
bar = "█" * filled + "░" * (bar_length - filled)
print(f"\r [{bar}] {percent:.1f}%", end="", flush=True)
# Download and install
update_package = updater.download_update(update_info, show_progress)
if not update_package:
print("\n❌ Download failed. Please try again later.")
return
print("\n💾 Creating backup...")
if not updater.create_backup():
print("⚠️ Backup failed, but continuing anyway...")
print("🔄 Installing update...")
if updater.apply_update(update_package, update_info):
print("✅ Update successful!")
@ -727,111 +558,91 @@ def handle_update():
print("❌ Rollback failed. You may need to reinstall.")
else:
print("Update cancelled.")
except Exception as e:
print(f"❌ Update failed: {e}")
print("💡 Try updating manually from GitHub")
def main():
"""Main CLI interface."""
# Check virtual environment
try:
from mini_rag.venv_checker import check_and_warn_venv
check_and_warn_venv("rag-mini.py", force_exit=False)
except ImportError:
pass # If venv checker can't be imported, continue anyway
parser = argparse.ArgumentParser(
description="FSS-Mini-RAG - Lightweight semantic code search",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
rag-mini index /path/to/project # Index a project
rag-mini search /path/to/project "query" # Search indexed project
rag-mini search /path/to/project "query" # Search indexed project
rag-mini search /path/to/project "query" -s # Search with LLM synthesis
rag-mini explore /path/to/project # Interactive exploration mode
rag-mini status /path/to/project # Show status
rag-mini models /path/to/project # Show model status and selection
""",
"""
)
parser.add_argument(
"command",
choices=["index", "search", "explore", "status", "models", "update", "check-update"],
help="Command to execute",
)
parser.add_argument(
"project_path",
type=Path,
nargs="?",
help="Path to project directory (REQUIRED except for update commands)",
)
parser.add_argument("query", nargs="?", help="Search query (for search command)")
parser.add_argument("--force", action="store_true", help="Force reindex all files")
parser.add_argument(
"--top-k",
"--limit",
type=int,
default=10,
dest="top_k",
help="Maximum number of search results (top-k)",
)
parser.add_argument("--verbose", "-v", action="store_true", help="Enable verbose logging")
parser.add_argument(
"--synthesize",
"-s",
action="store_true",
help="Generate LLM synthesis of search results (requires Ollama)",
)
parser.add_argument('command', choices=['index', 'search', 'explore', 'status', 'update', 'check-update'],
help='Command to execute')
parser.add_argument('project_path', type=Path, nargs='?',
help='Path to project directory (REQUIRED except for update commands)')
parser.add_argument('query', nargs='?',
help='Search query (for search command)')
parser.add_argument('--force', action='store_true',
help='Force reindex all files')
parser.add_argument('--top-k', '--limit', type=int, default=10, dest='top_k',
help='Maximum number of search results (top-k)')
parser.add_argument('--verbose', '-v', action='store_true',
help='Enable verbose logging')
parser.add_argument('--synthesize', '-s', action='store_true',
help='Generate LLM synthesis of search results (requires Ollama)')
args = parser.parse_args()
# Set logging level
if args.verbose:
logging.getLogger().setLevel(logging.INFO)
# Handle update commands first (don't require project_path)
if args.command == "check-update":
if args.command == 'check-update':
handle_check_update()
return
elif args.command == "update":
elif args.command == 'update':
handle_update()
return
# All other commands require project_path
if not args.project_path:
print("❌ Project path required for this command")
sys.exit(1)
# Validate project path
if not args.project_path.exists():
print(f"❌ Project path does not exist: {args.project_path}")
sys.exit(1)
if not args.project_path.is_dir():
print(f"❌ Project path is not a directory: {args.project_path}")
sys.exit(1)
# Show discrete update notification for regular commands (non-intrusive)
show_discrete_update_notice()
# Execute command
if args.command == "index":
if args.command == 'index':
index_project(args.project_path, args.force)
elif args.command == "search":
elif args.command == 'search':
if not args.query:
print("❌ Search query required")
sys.exit(1)
search_project(args.project_path, args.query, args.top_k, args.synthesize)
elif args.command == "explore":
elif args.command == 'explore':
explore_interactive(args.project_path)
elif args.command == "status":
elif args.command == 'status':
status_check(args.project_path)
elif args.command == "models":
show_model_status(args.project_path)
if __name__ == "__main__":
main()
if __name__ == '__main__':
main()

2
rag-tui
View File

@ -19,4 +19,4 @@ if [ ! -f "$PYTHON" ]; then
fi
# Launch TUI
exec "$PYTHON" "$SCRIPT_DIR/bin/rag-tui.py" "$@"
exec "$PYTHON" "$SCRIPT_DIR/rag-tui.py" "$@"

1400
bin/rag-tui.py → rag-tui.py
View File

File diff suppressed because it is too large Load Diff

200
scripts/setup-github-template.py
View File

@ -6,67 +6,67 @@ Converts a project to use the auto-update template system.
This script helps migrate projects from Gitea to GitHub with auto-update capability.
"""
import argparse
import os
import sys
import json
import shutil
import sys
import argparse
from pathlib import Path
from typing import Dict, Optional
from typing import Dict, Any, Optional
def setup_project_template(
project_path: Path,
repo_owner: str,
repo_name: str,
project_type: str = "python",
include_auto_update: bool = True,
include_auto_update: bool = True
) -> bool:
"""
Setup a project to use the GitHub auto-update template system.
Args:
project_path: Path to the project directory
repo_owner: GitHub username/organization
repo_name: GitHub repository name
repo_name: GitHub repository name
project_type: Type of project (python, general)
include_auto_update: Whether to include auto-update system
Returns:
True if setup successful
"""
print(f"🚀 Setting up GitHub template for: {repo_owner}/{repo_name}")
print(f"📁 Project path: {project_path}")
print(f"🔧 Project type: {project_type}")
print(f"🔄 Auto-update: {'Enabled' if include_auto_update else 'Disabled'}")
print()
try:
# Create .github directory structure
github_dir = project_path / ".github"
workflows_dir = github_dir / "workflows"
templates_dir = github_dir / "ISSUE_TEMPLATE"
# Ensure directories exist
workflows_dir.mkdir(parents=True, exist_ok=True)
templates_dir.mkdir(parents=True, exist_ok=True)
# 1. Setup GitHub Actions workflows
setup_workflows(workflows_dir, repo_owner, repo_name, project_type)
# 2. Setup auto-update system if requested
if include_auto_update:
setup_auto_update_system(project_path, repo_owner, repo_name)
# 3. Create issue templates
setup_issue_templates(templates_dir)
# 4. Create/update project configuration
setup_project_config(project_path, repo_owner, repo_name, include_auto_update)
# 5. Create README template if needed
setup_readme_template(project_path, repo_owner, repo_name)
print("✅ GitHub template setup completed successfully!")
print()
print("📋 Next Steps:")
@ -75,21 +75,20 @@ def setup_project_template(
print("3. Test auto-update system: ./project check-update")
print("4. Enable GitHub Pages for documentation (optional)")
print()
return True
except Exception as e:
print(f"❌ Setup failed: {e}")
return False
def setup_workflows(workflows_dir: Path, repo_owner: str, repo_name: str, project_type: str):
"""Setup GitHub Actions workflow files."""
print("🔧 Setting up GitHub Actions workflows...")
# Release workflow
release_workflow = """name: Auto Release & Update System
release_workflow = f"""name: Auto Release & Update System
on:
push:
tags:
@ -106,18 +105,18 @@ jobs:
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.11'
- name: Extract version
id: version
run: |
@ -128,18 +127,18 @@ jobs:
fi
echo "version=$VERSION" >> $GITHUB_OUTPUT
echo "clean_version=${{VERSION#v}}" >> $GITHUB_OUTPUT
- name: Update version in code
run: |
VERSION="${{{{ steps.version.outputs.clean_version }}}}"
# Update version files
find . -name "__init__.py" -exec sed -i 's/__version__ = ".*"/__version__ = "'$VERSION'"/' {{}} +
- name: Generate release notes
id: release_notes
run: |
VERSION="${{{{ steps.version.outputs.version }}}}"
# Get commits since last tag
LAST_TAG=$(git describe --tags --abbrev=0 HEAD~1 2>/dev/null || echo "")
if [ -n "$LAST_TAG" ]; then
@ -147,28 +146,28 @@ jobs:
else
COMMITS=$(git log --oneline --pretty=format:"• %s" | head -10)
fi
# Create release notes
cat > release_notes.md << EOF
## What's New in $VERSION
### 🚀 Changes
$COMMITS
### 📥 Installation
Download and install the latest version:
```bash
\`\`\`bash
curl -sSL https://github.com/{repo_owner}/{repo_name}/releases/latest/download/install.sh | bash
```
\`\`\`
### 🔄 Auto-Update
If you have auto-update support:
```bash
\`\`\`bash
./{repo_name} check-update
./{repo_name} update
```
\`\`\`
EOF
- name: Create GitHub Release
uses: softprops/action-gh-release@v2
with:
@ -182,12 +181,12 @@ jobs:
*.bat
requirements.txt
"""
(workflows_dir / "release.yml").write_text(release_workflow)
# CI workflow for Python projects
if project_type == "python":
ci_workflow = """name: CI/CD Pipeline
ci_workflow = f"""name: CI/CD Pipeline
on:
push:
branches: [ main, develop ]
@ -202,25 +201,25 @@ jobs:
matrix:
os: [ubuntu-latest, windows-latest, macos-latest]
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python ${{{{ matrix.python-version }}}}
uses: actions/setup-python@v5
with:
python-version: ${{{{ matrix.python-version }}}}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
- name: Run tests
run: |
python -c "import {repo_name.replace('-', '_')}; print('✅ Import successful')"
- name: Test auto-update system
run: |
python -c "
@ -232,38 +231,33 @@ jobs:
"
"""
(workflows_dir / "ci.yml").write_text(ci_workflow)
print(" ✅ GitHub Actions workflows created")
def setup_auto_update_system(project_path: Path, repo_owner: str, repo_name: str):
"""Setup the auto-update system for the project."""
print("🔄 Setting up auto-update system...")
# Copy updater.py from FSS-Mini-RAG as template
template_updater = Path(__file__).parent.parent / "mini_rag" / "updater.py"
if template_updater.exists():
# Create project module directory if needed
module_name = repo_name.replace("-", "_")
module_name = repo_name.replace('-', '_')
module_dir = project_path / module_name
module_dir.mkdir(exist_ok=True)
# Copy and customize updater
target_updater = module_dir / "updater.py"
shutil.copy2(template_updater, target_updater)
# Customize for this project
content = target_updater.read_text()
content = content.replace(
'repo_owner: str = "FSSCoding"', f'repo_owner: str = "{repo_owner}"'
)
content = content.replace(
'repo_name: str = "Fss-Mini-Rag"', f'repo_name: str = "{repo_name}"'
)
content = content.replace('repo_owner: str = "FSSCoding"', f'repo_owner: str = "{repo_owner}"')
content = content.replace('repo_name: str = "Fss-Mini-Rag"', f'repo_name: str = "{repo_name}"')
target_updater.write_text(content)
# Update __init__.py to include updater
init_file = module_dir / "__init__.py"
if init_file.exists():
@ -278,17 +272,16 @@ except ImportError:
pass
"""
init_file.write_text(content)
print(" ✅ Auto-update system configured")
else:
print(" ⚠️ Template updater not found, you'll need to implement manually")
def setup_issue_templates(templates_dir: Path):
"""Setup GitHub issue templates."""
print("📝 Setting up issue templates...")
bug_template = """---
name: Bug Report
about: Create a report to help us improve
@ -319,7 +312,7 @@ A clear and concise description of what you expected to happen.
**Additional context**
Add any other context about the problem here.
"""
feature_template = """---
name: Feature Request
about: Suggest an idea for this project
@ -341,50 +334,46 @@ A clear and concise description of any alternative solutions you've considered.
**Additional context**
Add any other context or screenshots about the feature request here.
"""
(templates_dir / "bug_report.md").write_text(bug_template)
(templates_dir / "feature_request.md").write_text(feature_template)
print(" ✅ Issue templates created")
def setup_project_config(
project_path: Path, repo_owner: str, repo_name: str, include_auto_update: bool
):
def setup_project_config(project_path: Path, repo_owner: str, repo_name: str, include_auto_update: bool):
"""Setup project configuration file."""
print("⚙️ Setting up project configuration...")
config = {
"project": {
"name": repo_name,
"owner": repo_owner,
"github_url": f"https://github.com/{repo_owner}/{repo_name}",
"auto_update_enabled": include_auto_update,
"auto_update_enabled": include_auto_update
},
"github": {
"template_version": "1.0.0",
"last_sync": None,
"workflows_enabled": True,
},
"workflows_enabled": True
}
}
config_file = project_path / ".github" / "project-config.json"
with open(config_file, "w") as f:
with open(config_file, 'w') as f:
json.dump(config, f, indent=2)
print(" ✅ Project configuration created")
def setup_readme_template(project_path: Path, repo_owner: str, repo_name: str):
"""Setup README template if one doesn't exist."""
readme_file = project_path / "README.md"
if not readme_file.exists():
print("📖 Creating README template...")
readme_content = """# {repo_name}
readme_content = f"""# {repo_name}
> A brief description of your project
@ -401,7 +390,7 @@ curl -sSL https://github.com/{repo_owner}/{repo_name}/releases/latest/download/i
## Features
- ✨ Feature 1
- 🚀 Feature 2
- 🚀 Feature 2
- 🔧 Feature 3
## Installation
@ -452,11 +441,10 @@ This project includes automatic update checking:
🤖 **Auto-Update Enabled**: This project will notify you of new versions automatically!
"""
readme_file.write_text(readme_content)
print(" ✅ README template created")
def main():
"""Main entry point."""
parser = argparse.ArgumentParser(
@ -466,38 +454,32 @@ def main():
Examples:
python setup-github-template.py myproject --owner username --name my-project
python setup-github-template.py /path/to/project --owner org --name cool-tool --no-auto-update
""",
"""
)
parser.add_argument("project_path", type=Path, help="Path to project directory")
parser.add_argument("--owner", required=True, help="GitHub username or organization")
parser.add_argument("--name", required=True, help="GitHub repository name")
parser.add_argument(
"--type",
choices=["python", "general"],
default="python",
help="Project type (default: python)",
)
parser.add_argument(
"--no-auto-update", action="store_true", help="Disable auto-update system"
)
parser.add_argument('project_path', type=Path, help='Path to project directory')
parser.add_argument('--owner', required=True, help='GitHub username or organization')
parser.add_argument('--name', required=True, help='GitHub repository name')
parser.add_argument('--type', choices=['python', 'general'], default='python',
help='Project type (default: python)')
parser.add_argument('--no-auto-update', action='store_true',
help='Disable auto-update system')
args = parser.parse_args()
if not args.project_path.exists():
print(f"❌ Project path does not exist: {args.project_path}")
sys.exit(1)
success = setup_project_template(
project_path=args.project_path,
repo_owner=args.owner,
repo_name=args.name,
project_type=args.type,
include_auto_update=not args.no_auto_update,
include_auto_update=not args.no_auto_update
)
sys.exit(0 if success else 1)
if __name__ == "__main__":
main()
main()

95
scripts/test-configs.py
View File

@ -4,87 +4,80 @@ Test script to validate all config examples are syntactically correct
and contain required fields for FSS-Mini-RAG.
"""
import yaml
import sys
from pathlib import Path
from typing import Any, Dict, List
import yaml
from typing import Dict, Any, List
def validate_config_structure(config: Dict[str, Any], config_name: str) -> List[str]:
"""Validate that config has required structure."""
errors = []
# Required sections
required_sections = ["chunking", "streaming", "files", "embedding", "search"]
required_sections = ['chunking', 'streaming', 'files', 'embedding', 'search']
for section in required_sections:
if section not in config:
errors.append(f"{config_name}: Missing required section '{section}'")
# Validate chunking section
if "chunking" in config:
chunking = config["chunking"]
required_chunking = ["max_size", "min_size", "strategy"]
if 'chunking' in config:
chunking = config['chunking']
required_chunking = ['max_size', 'min_size', 'strategy']
for field in required_chunking:
if field not in chunking:
errors.append(f"{config_name}: Missing chunking.{field}")
# Validate types and ranges
if "max_size" in chunking and not isinstance(chunking["max_size"], int):
if 'max_size' in chunking and not isinstance(chunking['max_size'], int):
errors.append(f"{config_name}: chunking.max_size must be integer")
if "min_size" in chunking and not isinstance(chunking["min_size"], int):
if 'min_size' in chunking and not isinstance(chunking['min_size'], int):
errors.append(f"{config_name}: chunking.min_size must be integer")
if "strategy" in chunking and chunking["strategy"] not in ["semantic", "fixed"]:
if 'strategy' in chunking and chunking['strategy'] not in ['semantic', 'fixed']:
errors.append(f"{config_name}: chunking.strategy must be 'semantic' or 'fixed'")
# Validate embedding section
if "embedding" in config:
embedding = config["embedding"]
if "preferred_method" in embedding:
valid_methods = ["ollama", "ml", "hash", "auto"]
if embedding["preferred_method"] not in valid_methods:
errors.append(
f"{config_name}: embedding.preferred_method must be one of {valid_methods}"
)
if 'embedding' in config:
embedding = config['embedding']
if 'preferred_method' in embedding:
valid_methods = ['ollama', 'ml', 'hash', 'auto']
if embedding['preferred_method'] not in valid_methods:
errors.append(f"{config_name}: embedding.preferred_method must be one of {valid_methods}")
# Validate LLM section (if present)
if "llm" in config:
llm = config["llm"]
if "synthesis_temperature" in llm:
temp = llm["synthesis_temperature"]
if 'llm' in config:
llm = config['llm']
if 'synthesis_temperature' in llm:
temp = llm['synthesis_temperature']
if not isinstance(temp, (int, float)) or temp < 0 or temp > 1:
errors.append(
f"{config_name}: llm.synthesis_temperature must be number between 0-1"
)
errors.append(f"{config_name}: llm.synthesis_temperature must be number between 0-1")
return errors
def test_config_file(config_path: Path) -> bool:
"""Test a single config file."""
print(f"Testing {config_path.name}...")
try:
# Test YAML parsing
with open(config_path, "r") as f:
with open(config_path, 'r') as f:
config = yaml.safe_load(f)
if not config:
print(f" ❌ {config_path.name}: Empty or invalid YAML")
return False
# Test structure
errors = validate_config_structure(config, config_path.name)
if errors:
print(f" ❌ {config_path.name}: Structure errors:")
for error in errors:
print(f" • {error}")
return False
print(f" ✅ {config_path.name}: Valid")
return True
except yaml.YAMLError as e:
print(f" ❌ {config_path.name}: YAML parsing error: {e}")
return False
@ -92,32 +85,31 @@ def test_config_file(config_path: Path) -> bool:
print(f" ❌ {config_path.name}: Unexpected error: {e}")
return False
def main():
"""Test all config examples."""
script_dir = Path(__file__).parent
project_root = script_dir.parent
examples_dir = project_root / "examples"
examples_dir = project_root / 'examples'
if not examples_dir.exists():
print(f"❌ Examples directory not found: {examples_dir}")
sys.exit(1)
# Find all config files
config_files = list(examples_dir.glob("config*.yaml"))
config_files = list(examples_dir.glob('config*.yaml'))
if not config_files:
print(f"❌ No config files found in {examples_dir}")
sys.exit(1)
print(f"🧪 Testing {len(config_files)} config files...\n")
all_passed = True
for config_file in sorted(config_files):
passed = test_config_file(config_file)
if not passed:
all_passed = False
print(f"\n{'='*50}")
if all_passed:
print("✅ All config files are valid!")
@ -128,6 +120,5 @@ def main():
print("❌ Some config files have issues - please fix before release")
sys.exit(1)
if __name__ == "__main__":
main()
if __name__ == '__main__':
main()

124
tests/test_fixes.py → test_fixes.py
View File

@ -10,61 +10,55 @@ Or run directly with venv:
source .venv/bin/activate && python test_fixes.py
"""
import os
import sys
import os
import tempfile
from pathlib import Path
# Check if virtual environment is activated
def check_venv():
if "VIRTUAL_ENV" not in os.environ:
if 'VIRTUAL_ENV' not in os.environ:
print("⚠️ WARNING: Virtual environment not detected!")
print(" This test requires the virtual environment to be activated.")
print(" Run: source .venv/bin/activate && python test_fixes.py")
print(" Continuing anyway...\n")
check_venv()
# Add current directory to Python path
sys.path.insert(0, ".")
sys.path.insert(0, '.')
def test_config_model_rankings():
"""Test that model rankings are properly configured."""
print("=" * 60)
print("TESTING CONFIG AND MODEL RANKINGS")
print("=" * 60)
try:
# Test config loading without heavy dependencies
from mini_rag.config import ConfigManager, LLMConfig
# Create a temporary directory for testing
with tempfile.TemporaryDirectory() as tmpdir:
config_manager = ConfigManager(tmpdir)
config = config_manager.load_config()
print("✓ Config loads successfully")
# Check LLM config and model rankings
if hasattr(config, "llm"):
if hasattr(config, 'llm'):
llm_config = config.llm
print(f"✓ LLM config found: {type(llm_config)}")
if hasattr(llm_config, "model_rankings"):
if hasattr(llm_config, 'model_rankings'):
rankings = llm_config.model_rankings
print(f"✓ Model rankings: {rankings}")
if rankings and rankings[0] == "qwen3:1.7b":
print("✓ qwen3:1.7b is FIRST priority - CORRECT!")
return True
else:
print(
f"✗ WRONG: First model is {rankings[0] if rankings else 'None'}, should be qwen3:1.7b"
)
print(f"✗ WRONG: First model is {rankings[0] if rankings else 'None'}, should be qwen3:1.7b")
return False
else:
print("✗ Model rankings not found in LLM config")
@ -72,7 +66,7 @@ def test_config_model_rankings():
else:
print("✗ LLM config not found")
return False
except ImportError as e:
print(f"✗ Import error: {e}")
return False
@ -80,18 +74,17 @@ def test_config_model_rankings():
print(f"✗ Error: {e}")
return False
def test_context_length_fix():
"""Test that context length is correctly set to 32K."""
print("\n" + "=" * 60)
print("TESTING CONTEXT LENGTH FIXES")
print("=" * 60)
try:
# Read the synthesizer file and check for 32000
with open("mini_rag/llm_synthesizer.py", "r") as f:
with open('mini_rag/llm_synthesizer.py', 'r') as f:
synthesizer_content = f.read()
if '"num_ctx": 32000' in synthesizer_content:
print("✓ LLM Synthesizer: num_ctx is correctly set to 32000")
elif '"num_ctx": 80000' in synthesizer_content:
@ -99,139 +92,133 @@ def test_context_length_fix():
return False
else:
print("? LLM Synthesizer: num_ctx setting not found clearly")
# Read the safeguards file and check for 32000
with open("mini_rag/llm_safeguards.py", "r") as f:
with open('mini_rag/llm_safeguards.py', 'r') as f:
safeguards_content = f.read()
if "context_window: int = 32000" in safeguards_content:
if 'context_window: int = 32000' in safeguards_content:
print("✓ Safeguards: context_window is correctly set to 32000")
return True
elif "context_window: int = 80000" in safeguards_content:
elif 'context_window: int = 80000' in safeguards_content:
print("✗ Safeguards: context_window is still 80000 - NEEDS FIX")
return False
else:
print("? Safeguards: context_window setting not found clearly")
return False
except Exception as e:
print(f"✗ Error checking context length: {e}")
return False
def test_safeguard_preservation():
"""Test that safeguards preserve content instead of dropping it."""
print("\n" + "=" * 60)
print("TESTING SAFEGUARD CONTENT PRESERVATION")
print("=" * 60)
try:
# Read the synthesizer file and check for the preservation method
with open("mini_rag/llm_synthesizer.py", "r") as f:
with open('mini_rag/llm_synthesizer.py', 'r') as f:
synthesizer_content = f.read()
if "_create_safeguard_response_with_content" in synthesizer_content:
if '_create_safeguard_response_with_content' in synthesizer_content:
print("✓ Safeguard content preservation method exists")
else:
print("✗ Safeguard content preservation method missing")
return False
# Check for the specific preservation logic
if "AI Response (use with caution):" in synthesizer_content:
if 'AI Response (use with caution):' in synthesizer_content:
print("✓ Content preservation warning format found")
else:
print("✗ Content preservation warning format missing")
return False
# Check that it's being called instead of dropping content
if (
"return self._create_safeguard_response_with_content(" in synthesizer_content
and "issue_type, explanation, raw_response" in synthesizer_content
):
if 'return self._create_safeguard_response_with_content(issue_type, explanation, raw_response)' in synthesizer_content:
print("✓ Preservation method is called when safeguards trigger")
return True
else:
print("✗ Preservation method not called properly")
return False
except Exception as e:
print(f"✗ Error checking safeguard preservation: {e}")
return False
def test_import_fixes():
"""Test that import statements are fixed from claude_rag to mini_rag."""
print("\n" + "=" * 60)
print("TESTING IMPORT STATEMENT FIXES")
print("=" * 60)
test_files = [
"tests/test_rag_integration.py",
"tests/01_basic_integration_test.py",
"tests/test_hybrid_search.py",
"tests/test_context_retrieval.py",
'tests/test_rag_integration.py',
'tests/01_basic_integration_test.py',
'tests/test_hybrid_search.py',
'tests/test_context_retrieval.py'
]
all_good = True
for test_file in test_files:
if Path(test_file).exists():
try:
with open(test_file, "r") as f:
with open(test_file, 'r') as f:
content = f.read()
if "claude_rag" in content:
if 'claude_rag' in content:
print(f"✗ {test_file}: Still contains 'claude_rag' imports")
all_good = False
elif "mini_rag" in content:
elif 'mini_rag' in content:
print(f"✓ {test_file}: Uses correct 'mini_rag' imports")
else:
print(f"? {test_file}: No rag imports found")
except Exception as e:
print(f"✗ Error reading {test_file}: {e}")
all_good = False
else:
print(f"? {test_file}: File not found")
return all_good
def main():
"""Run all tests."""
print("FSS-Mini-RAG Fix Verification Tests")
print("Testing all the critical fixes...")
tests = [
("Model Rankings", test_config_model_rankings),
("Context Length", test_context_length_fix),
("Context Length", test_context_length_fix),
("Safeguard Preservation", test_safeguard_preservation),
("Import Fixes", test_import_fixes),
("Import Fixes", test_import_fixes)
]
results = {}
for test_name, test_func in tests:
try:
results[test_name] = test_func()
except Exception as e:
print(f"✗ {test_name} test crashed: {e}")
results[test_name] = False
# Summary
print("\n" + "=" * 60)
print("TEST SUMMARY")
print("=" * 60)
passed = sum(1 for result in results.values() if result)
total = len(results)
for test_name, result in results.items():
status = "✓ PASS" if result else "✗ FAIL"
print(f"{status} {test_name}")
print(f"\nOverall: {passed}/{total} tests passed")
if passed == total:
print("🎉 ALL TESTS PASSED - System should be working properly!")
return 0
@ -239,6 +226,5 @@ def main():
print("❌ SOME TESTS FAILED - System needs more fixes!")
return 1
if __name__ == "__main__":
sys.exit(main())
sys.exit(main())

131
tests/01_basic_integration_test.py
View File

@ -14,82 +14,74 @@ import sys
import tempfile
from pathlib import Path
from mini_rag.chunker import CodeChunker
from mini_rag.indexer import ProjectIndexer
from mini_rag.ollama_embeddings import OllamaEmbedder as CodeEmbedder
from mini_rag.search import CodeSearcher
# Check if virtual environment is activated
def check_venv():
if "VIRTUAL_ENV" not in os.environ:
if 'VIRTUAL_ENV' not in os.environ:
print("⚠️ WARNING: Virtual environment not detected!")
print(" This test requires the virtual environment to be activated.")
print(
" Run: source .venv/bin/activate && PYTHONPATH=. python tests/01_basic_integration_test.py"
)
print(" Run: source .venv/bin/activate && PYTHONPATH=. python tests/01_basic_integration_test.py")
print(" Continuing anyway...\n")
check_venv()
# Fix Windows encoding
if sys.platform == "win32":
os.environ["PYTHONUTF8"] = "1"
sys.stdout.reconfigure(encoding="utf-8")
if sys.platform == 'win32':
os.environ['PYTHONUTF8'] = '1'
sys.stdout.reconfigure(encoding='utf-8')
from mini_rag.chunker import CodeChunker
from mini_rag.indexer import ProjectIndexer
from mini_rag.search import CodeSearcher
from mini_rag.ollama_embeddings import OllamaEmbedder as CodeEmbedder
def main():
print("=" * 60)
print("RAG System Integration Demo")
print("=" * 60)
with tempfile.TemporaryDirectory() as tmpdir:
project_path = Path(tmpdir)
# Create sample project files
print("\n1. Creating sample project files...")
# Main calculator module
(project_path / "calculator.py").write_text(
'''"""
(project_path / "calculator.py").write_text('''"""
Advanced calculator module with various mathematical operations.
"""
import math
from typing import List, Union
class BasicCalculator:
"""Basic calculator with fundamental operations."""
def __init__(self):
"""Initialize calculator with result history."""
self.history = []
self.last_result = 0
def add(self, a: float, b: float) -> float:
"""Add two numbers and store result."""
result = a + b
self.history.append(f"{a} + {b} = {result}")
self.last_result = result
return result
def subtract(self, a: float, b: float) -> float:
"""Subtract b from a."""
result = a - b
self.history.append(f"{a} - {b} = {result}")
self.last_result = result
return result
def multiply(self, a: float, b: float) -> float:
"""Multiply two numbers."""
result = a * b
self.history.append(f"{a} * {b} = {result}")
self.last_result = result
return result
def divide(self, a: float, b: float) -> float:
"""Divide a by b with zero check."""
if b == 0:
@ -99,17 +91,16 @@ class BasicCalculator:
self.last_result = result
return result
class ScientificCalculator(BasicCalculator):
"""Scientific calculator extending basic operations."""
def power(self, base: float, exponent: float) -> float:
"""Calculate base raised to exponent."""
result = math.pow(base, exponent)
self.history.append(f"{base} ^ {exponent} = {result}")
self.last_result = result
return result
def sqrt(self, n: float) -> float:
"""Calculate square root."""
if n < 0:
@ -118,7 +109,7 @@ class ScientificCalculator(BasicCalculator):
self.history.append(f"sqrt({n}) = {result}")
self.last_result = result
return result
def logarithm(self, n: float, base: float = 10) -> float:
"""Calculate logarithm with specified base."""
result = math.log(n, base)
@ -132,7 +123,6 @@ def calculate_mean(numbers: List[float]) -> float:
return 0.0
return sum(numbers) / len(numbers)
def calculate_median(numbers: List[float]) -> float:
"""Calculate median of a list of numbers."""
if not numbers:
@ -143,7 +133,6 @@ def calculate_median(numbers: List[float]) -> float:
return (sorted_nums[n//2-1] + sorted_nums[n//2]) / 2
return sorted_nums[n//2]
def calculate_mode(numbers: List[float]) -> float:
"""Calculate mode (most frequent value)."""
if not numbers:
@ -153,88 +142,79 @@ def calculate_mode(numbers: List[float]) -> float:
frequency[num] = frequency.get(num, 0) + 1
mode = max(frequency.keys(), key=frequency.get)
return mode
'''
)
''')
# Test file for the calculator
(project_path / "test_calculator.py").write_text(
'''"""
(project_path / "test_calculator.py").write_text('''"""
Unit tests for calculator module.
"""
import unittest
from calculator import BasicCalculator, ScientificCalculator, calculate_mean
class TestBasicCalculator(unittest.TestCase):
"""Test cases for BasicCalculator."""
def setUp(self):
"""Set up test calculator."""
self.calc = BasicCalculator()
def test_addition(self):
"""Test addition operation."""
result = self.calc.add(5, 3)
self.assertEqual(result, 8)
self.assertEqual(self.calc.last_result, 8)
def test_division_by_zero(self):
"""Test division by zero raises error."""
with self.assertRaises(ValueError):
self.calc.divide(10, 0)
class TestStatistics(unittest.TestCase):
"""Test statistical functions."""
def test_mean(self):
"""Test mean calculation."""
numbers = [1, 2, 3, 4, 5]
self.assertEqual(calculate_mean(numbers), 3.0)
def test_empty_list(self):
"""Test mean of empty list."""
self.assertEqual(calculate_mean([]), 0.0)
if __name__ == "__main__":
unittest.main()
'''
)
''')
print(" Created 2 Python files")
# 2. Index the project
print("\n2. Indexing project with intelligent chunking...")
# Use realistic chunk size
chunker = CodeChunker(min_chunk_size=10, max_chunk_size=100)
indexer = ProjectIndexer(project_path, chunker=chunker)
stats = indexer.index_project()
print(f" Indexed {stats['files_indexed']} files")
print(f" Created {stats['chunks_created']} chunks")
print(f" Time: {stats['time_taken']:.2f} seconds")
# 3. Demonstrate search capabilities
print("\n3. Testing search capabilities...")
searcher = CodeSearcher(project_path)
# Test different search types
print("\n a) Semantic search for 'calculate average':")
results = searcher.search("calculate average", top_k=3)
for i, result in enumerate(results, 1):
print(
f" {i}. {result.chunk_type} '{result.name}' in {result.file_path} (score: {result.score:.3f})"
)
print(f" {i}. {result.chunk_type} '{result.name}' in {result.file_path} (score: {result.score:.3f})")
print("\n b) BM25-weighted search for 'divide zero':")
results = searcher.search("divide zero", top_k=3, semantic_weight=0.2, bm25_weight=0.8)
for i, result in enumerate(results, 1):
print(
f" {i}. {result.chunk_type} '{result.name}' in {result.file_path} (score: {result.score:.3f})"
)
print(f" {i}. {result.chunk_type} '{result.name}' in {result.file_path} (score: {result.score:.3f})")
print("\n c) Search with context for 'test addition':")
results = searcher.search("test addition", top_k=2, include_context=True)
for i, result in enumerate(results, 1):
@ -245,39 +225,39 @@ if __name__ == "__main__":
print(f" Has previous context: {len(result.context_before)} chars")
if result.context_after:
print(f" Has next context: {len(result.context_after)} chars")
# 4. Test chunk navigation
print("\n4. Testing chunk navigation...")
# Get all chunks to find a method
df = searcher.table.to_pandas()
method_chunks = df[df["chunk_type"] == "method"]
method_chunks = df[df['chunk_type'] == 'method']
if len(method_chunks) > 0:
# Pick a method in the middle
mid_idx = len(method_chunks) // 2
chunk_id = method_chunks.iloc[mid_idx]["chunk_id"]
chunk_name = method_chunks.iloc[mid_idx]["name"]
chunk_id = method_chunks.iloc[mid_idx]['chunk_id']
chunk_name = method_chunks.iloc[mid_idx]['name']
print(f"\n Getting context for method '{chunk_name}':")
context = searcher.get_chunk_context(chunk_id)
if context["chunk"]:
if context['chunk']:
print(f" Current: {context['chunk'].name}")
if context["prev"]:
if context['prev']:
print(f" Previous: {context['prev'].name}")
if context["next"]:
if context['next']:
print(f" Next: {context['next'].name}")
if context["parent"]:
if context['parent']:
print(f" Parent class: {context['parent'].name}")
# 5. Show statistics
print("\n5. Index Statistics:")
stats = searcher.get_statistics()
print(f" - Total chunks: {stats['total_chunks']}")
print(f" - Unique files: {stats['unique_files']}")
print(f" - Chunk types: {stats['chunk_types']}")
print("\n" + "=" * 60)
print(" All features working correctly!")
print("=" * 60)
@ -288,6 +268,5 @@ if __name__ == "__main__":
print("- Context-aware search with adjacent chunks")
print("- Chunk navigation following code relationships")
if __name__ == "__main__":
main()
main()

111
tests/02_search_examples.py
View File

@ -5,10 +5,9 @@ Simple demo of the hybrid search system showing real results.
import sys
from pathlib import Path
from rich.console import Console
from rich.panel import Panel
from rich.syntax import Syntax
from rich.panel import Panel
from rich.table import Table
from mini_rag.search import CodeSearcher
@ -18,110 +17,102 @@ console = Console()
def demo_search(project_path: Path):
"""Run demo searches showing the hybrid system in action."""
console.print("\n[bold cyan]Mini RAG Hybrid Search Demo[/bold cyan]\n")
# Initialize searcher
console.print("Initializing search system...")
searcher = CodeSearcher(project_path)
# Get index stats
stats = searcher.get_statistics()
if "error" not in stats:
console.print(
f"\n[green] Index ready:[/green] {stats['total_chunks']} chunks from {stats['unique_files']} files"
)
if 'error' not in stats:
console.print(f"\n[green] Index ready:[/green] {stats['total_chunks']} chunks from {stats['unique_files']} files")
console.print(f"[dim]Languages: {', '.join(stats['languages'].keys())}[/dim]")
console.print(f"[dim]Chunk types: {', '.join(stats['chunk_types'].keys())}[/dim]\n")
# Demo queries
demos = [
{
"title": "Keyword-Heavy Search",
"query": "BM25Okapi rank_bm25 search scoring",
"description": "This query has specific technical keywords that BM25 excels at finding",
"top_k": 5,
'title': 'Keyword-Heavy Search',
'query': 'BM25Okapi rank_bm25 search scoring',
'description': 'This query has specific technical keywords that BM25 excels at finding',
'top_k': 5
},
{
"title": "Natural Language Query",
"query": "how to build search index from database chunks",
"description": "This semantic query benefits from transformer embeddings understanding intent",
"top_k": 5,
'title': 'Natural Language Query',
'query': 'how to build search index from database chunks',
'description': 'This semantic query benefits from transformer embeddings understanding intent',
'top_k': 5
},
{
"title": "Mixed Technical Query",
"query": "vector embeddings for semantic code search with transformers",
"description": "This hybrid query combines technical terms with conceptual understanding",
"top_k": 5,
'title': 'Mixed Technical Query',
'query': 'vector embeddings for semantic code search with transformers',
'description': 'This hybrid query combines technical terms with conceptual understanding',
'top_k': 5
},
{
"title": "Function Search",
"query": "search method implementation with filters",
"description": "Looking for specific function implementations",
"top_k": 5,
},
'title': 'Function Search',
'query': 'search method implementation with filters',
'description': 'Looking for specific function implementations',
'top_k': 5
}
]
for demo in demos:
console.rule(f"\n[bold yellow]{demo['title']}[/bold yellow]")
console.print(f"[dim]{demo['description']}[/dim]")
console.print(f"\n[cyan]Query:[/cyan] '{demo['query']}'")
# Run search with hybrid mode
results = searcher.search(
query=demo["query"],
top_k=demo["top_k"],
query=demo['query'],
top_k=demo['top_k'],
semantic_weight=0.7,
bm25_weight=0.3,
bm25_weight=0.3
)
if not results:
console.print("[red]No results found![/red]")
continue
console.print(f"\n[green]Found {len(results)} results:[/green]\n")
# Show each result
for i, result in enumerate(results, 1):
# Create result panel
header = f"#{i} {result.file_path}:{result.start_line}-{result.end_line}"
# Get code preview
lines = result.content.splitlines()
if len(lines) > 10:
preview_lines = lines[:8] + ["..."] + lines[-2:]
preview_lines = lines[:8] + ['...'] + lines[-2:]
else:
preview_lines = lines
preview = "\n".join(preview_lines)
preview = '\n'.join(preview_lines)
# Create info table
info = Table.grid(padding=0)
info.add_column(style="cyan", width=12)
info.add_column(style="white")
info.add_row("Score:", f"{result.score:.3f}")
info.add_row("Type:", result.chunk_type)
info.add_row("Name:", result.name or "N/A")
info.add_row("Language:", result.language)
# Display result
console.print(
Panel(
f"{info}\n\n[dim]{preview}[/dim]",
title=header,
title_align="left",
border_style="blue",
)
)
console.print(Panel(
f"{info}\n\n[dim]{preview}[/dim]",
title=header,
title_align="left",
border_style="blue"
))
# Show scoring breakdown for top result
if results:
console.print(
"\n[dim]Top result hybrid score: {:.3f} (70% semantic + 30% BM25)[/dim]".format(
results[0].score
)
)
console.print("\n[dim]Top result hybrid score: {:.3f} (70% semantic + 30% BM25)[/dim]".format(results[0].score))
def main():
@ -131,14 +122,14 @@ def main():
else:
# Use the RAG system itself as the demo project
project_path = Path(__file__).parent
if not (project_path / ".mini-rag").exists():
if not (project_path / '.mini-rag').exists():
console.print("[red]Error: No RAG index found. Run 'rag-mini index' first.[/red]")
console.print(f"[dim]Looked in: {project_path / '.mini-rag'}[/dim]")
return
demo_search(project_path)
if __name__ == "__main__":
main()
main()

235
tests/03_system_validation.py
View File

@ -2,55 +2,53 @@
Integration test to verify all three agents' work integrates properly.
"""
import os
import sys
import os
import tempfile
from pathlib import Path
# Fix Windows encoding
if sys.platform == "win32":
os.environ["PYTHONUTF8"] = "1"
sys.stdout.reconfigure(encoding="utf-8")
if sys.platform == 'win32':
os.environ['PYTHONUTF8'] = '1'
sys.stdout.reconfigure(encoding='utf-8')
from mini_rag.chunker import CodeChunker
from mini_rag.config import RAGConfig
from mini_rag.indexer import ProjectIndexer
from mini_rag.search import CodeSearcher
from mini_rag.ollama_embeddings import OllamaEmbedder as CodeEmbedder
from mini_rag.query_expander import QueryExpander
from mini_rag.search import CodeSearcher
from mini_rag.config import RAGConfig
def test_chunker():
"""Test that chunker creates chunks with all required metadata."""
print("1. Testing Chunker...")
# Create test Python file with more substantial content
test_code = '''"""Test module for integration testing the chunker."""
import os
import sys
class TestClass:
"""A test class with multiple methods."""
def __init__(self):
"""Initialize the test class."""
self.value = 42
self.name = "test"
def method_one(self):
"""First method with some logic."""
result = self.value * 2
return result
def method_two(self, x):
"""Second method that takes a parameter."""
if x > 0:
return self.value + x
else:
return self.value - x
def method_three(self):
"""Third method for testing."""
data = []
@ -58,14 +56,13 @@ class TestClass:
data.append(i * self.value)
return data
class AnotherClass:
"""Another test class."""
def __init__(self, name):
"""Initialize with name."""
self.name = name
def process(self):
"""Process something."""
return f"Processing {self.name}"
@ -75,25 +72,22 @@ def standalone_function(arg1, arg2):
result = arg1 + arg2
return result * 2
def another_function():
"""Another standalone function."""
data = {"key": "value", "number": 123}
return data
'''
chunker = CodeChunker(min_chunk_size=1) # Use small chunk size for testing
chunks = chunker.chunk_file(Path("test.py"), test_code)
print(f" Created {len(chunks)} chunks")
# Debug: Show what chunks were created
print(" Chunks created:")
for chunk in chunks:
print(
f" - Type: {chunk.chunk_type}, Name: {chunk.name}, Lines: {chunk.start_line}-{chunk.end_line}"
)
print(f" - Type: {chunk.chunk_type}, Name: {chunk.name}, Lines: {chunk.start_line}-{chunk.end_line}")
# Check metadata
issues = []
for i, chunk in enumerate(chunks):
@ -103,82 +97,68 @@ def another_function():
issues.append(f"Chunk {i} missing total_chunks")
if chunk.file_lines is None:
issues.append(f"Chunk {i} missing file_lines")
# Check links (except first/last)
if i > 0 and chunk.prev_chunk_id is None:
issues.append(f"Chunk {i} missing prev_chunk_id")
if i < len(chunks) - 1 and chunk.next_chunk_id is None:
issues.append(f"Chunk {i} missing next_chunk_id")
# Check parent_class for methods
if chunk.chunk_type == "method" and chunk.parent_class is None:
if chunk.chunk_type == 'method' and chunk.parent_class is None:
issues.append(f"Method chunk {chunk.name} missing parent_class")
print(
f" - Chunk {i}: {chunk.chunk_type} '{chunk.name}' "
f"[{chunk.chunk_index}/{chunk.total_chunks}] "
f"prev={chunk.prev_chunk_id} next={chunk.next_chunk_id}"
)
print(f" - Chunk {i}: {chunk.chunk_type} '{chunk.name}' "
f"[{chunk.chunk_index}/{chunk.total_chunks}] "
f"prev={chunk.prev_chunk_id} next={chunk.next_chunk_id}")
if issues:
print(" Issues found:")
for issue in issues:
print(f" - {issue}")
else:
print(" All metadata present")
return len(issues) == 0
def test_indexer_storage():
"""Test that indexer stores the new metadata."""
print("\n2. Testing Indexer Storage...")
with tempfile.TemporaryDirectory() as tmpdir:
project_path = Path(tmpdir)
# Create test file
test_file = project_path / "test.py"
test_file.write_text(
"""
test_file.write_text('''
class MyClass:
def my_method(self):
return 42
"""
)
''')
# Index the project with small chunk size for testing
from mini_rag.chunker import CodeChunker
chunker = CodeChunker(min_chunk_size=1)
indexer = ProjectIndexer(project_path, chunker=chunker)
stats = indexer.index_project()
print(f" Indexed {stats['chunks_created']} chunks")
# Check what was stored
if indexer.table:
df = indexer.table.to_pandas()
columns = df.columns.tolist()
required_fields = [
"chunk_id",
"prev_chunk_id",
"next_chunk_id",
"parent_class",
]
required_fields = ['chunk_id', 'prev_chunk_id', 'next_chunk_id', 'parent_class']
missing_fields = [f for f in required_fields if f not in columns]
if missing_fields:
print(f" Missing fields in database: {missing_fields}")
print(f" Current fields: {columns}")
return False
else:
print(" All required fields in database schema")
# Check if data is actually stored
sample = df.iloc[0] if len(df) > 0 else None
if sample is not None:
@ -186,41 +166,38 @@ class MyClass:
print(f" Sample prev_chunk_id: {sample.get('prev_chunk_id', 'MISSING')}")
print(f" Sample next_chunk_id: {sample.get('next_chunk_id', 'MISSING')}")
print(f" Sample parent_class: {sample.get('parent_class', 'MISSING')}")
return len(missing_fields) == 0
def test_search_integration():
"""Test that search uses the new metadata."""
print("\n3. Testing Search Integration...")
with tempfile.TemporaryDirectory() as tmpdir:
project_path = Path(tmpdir)
# Create test files with proper content that will create multiple chunks
(project_path / "math_utils.py").write_text(
'''"""Math utilities module."""
(project_path / "math_utils.py").write_text('''"""Math utilities module."""
import math
class Calculator:
"""A simple calculator class."""
def __init__(self):
"""Initialize calculator."""
self.result = 0
def add(self, a, b):
"""Add two numbers."""
self.result = a + b
return self.result
def multiply(self, a, b):
"""Multiply two numbers."""
self.result = a * b
return self.result
def divide(self, a, b):
"""Divide two numbers."""
if b == 0:
@ -228,15 +205,14 @@ class Calculator:
self.result = a / b
return self.result
class AdvancedCalculator(Calculator):
"""Advanced calculator with more operations."""
def power(self, a, b):
"""Raise a to power b."""
self.result = a ** b
return self.result
def sqrt(self, a):
"""Calculate square root."""
self.result = math.sqrt(a)
@ -248,7 +224,6 @@ def compute_average(numbers):
return 0
return sum(numbers) / len(numbers)
def compute_median(numbers):
"""Compute median of a list."""
if not numbers:
@ -258,22 +233,20 @@ def compute_median(numbers):
if n % 2 == 0:
return (sorted_nums[n//2-1] + sorted_nums[n//2]) / 2
return sorted_nums[n//2]
'''
)
''')
# Index with small chunk size for testing
chunker = CodeChunker(min_chunk_size=1)
indexer = ProjectIndexer(project_path, chunker=chunker)
indexer.index_project()
# Search
searcher = CodeSearcher(project_path)
# Test BM25 integration
results = searcher.search(
"multiply numbers", top_k=5, semantic_weight=0.3, bm25_weight=0.7
)
results = searcher.search("multiply numbers", top_k=5,
semantic_weight=0.3, bm25_weight=0.7)
if results:
print(f" BM25 + semantic search returned {len(results)} results")
for r in results[:2]:
@ -281,50 +254,45 @@ def compute_median(numbers):
else:
print(" No search results returned")
return False
# Test context retrieval
print("\n Testing context retrieval...")
if searcher.table:
df = searcher.table.to_pandas()
print(f" Total chunks in DB: {len(df)}")
# Find a method/function chunk to test parent context
method_chunks = df[df["chunk_type"].isin(["method", "function"])]
# Find a method chunk to test parent context
method_chunks = df[df['chunk_type'] == 'method']
if len(method_chunks) > 0:
method_chunk_id = method_chunks.iloc[0]["chunk_id"]
method_chunk_id = method_chunks.iloc[0]['chunk_id']
context = searcher.get_chunk_context(method_chunk_id)
if context["chunk"]:
if context['chunk']:
print(f" Got main chunk: {context['chunk'].name}")
if context["prev"]:
if context['prev']:
print(f" Got previous chunk: {context['prev'].name}")
else:
print(" - No previous chunk (might be first)")
if context["next"]:
print(f" - No previous chunk (might be first)")
if context['next']:
print(f" Got next chunk: {context['next'].name}")
else:
print(" - No next chunk (might be last)")
if context["parent"]:
print(f" - No next chunk (might be last)")
if context['parent']:
print(f" Got parent chunk: {context['parent'].name}")
else:
print(" - No parent chunk")
print(f" - No parent chunk")
# Test include_context in search
results_with_context = searcher.search("add", include_context=True, top_k=2)
if results_with_context:
print(f" Found {len(results_with_context)} results with context")
for r in results_with_context:
# Check if result has context (unused variable removed)
print(
f" - {r.name}: context_before={bool(r.context_before)}, "
f"context_after={bool(r.context_after)}, parent={bool(r.parent_chunk)}"
)
has_context = bool(r.context_before or r.context_after or r.parent_chunk)
print(f" - {r.name}: context_before={bool(r.context_before)}, "
f"context_after={bool(r.context_after)}, parent={bool(r.parent_chunk)}")
# Check if at least one result has some context
if any(
r.context_before or r.context_after or r.parent_chunk
for r in results_with_context
):
if any(r.context_before or r.context_after or r.parent_chunk for r in results_with_context):
print(" Search with context working")
return True
else:
@ -336,117 +304,112 @@ def compute_median(numbers):
else:
print(" No method chunks found in database")
return False
return True
def test_server():
"""Test that server still works."""
print("\n4. Testing Server...")
# Just check if we can import and create server instance
try:
from mini_rag.server import RAGServer
# RAGServer(Path("."), port=7778) # Unused variable removed
server = RAGServer(Path("."), port=7778)
print(" Server can be instantiated")
return True
except Exception as e:
print(f" Server error: {e}")
return False
def test_new_features():
"""Test new features: query expansion and smart ranking."""
print("\n5. Testing New Features (Query Expansion & Smart Ranking)...")
try:
# Test configuration loading
config = RAGConfig()
print(" ✅ Configuration loaded successfully")
print(f" ✅ Configuration loaded successfully")
print(f" Query expansion enabled: {config.search.expand_queries}")
print(f" Max expansion terms: {config.llm.max_expansion_terms}")
# Test query expander (will use mock if Ollama unavailable)
expander = QueryExpander(config)
test_query = "authentication"
if expander.is_available():
expanded = expander.expand_query(test_query)
print(f" ✅ Query expansion working: '{test_query}' → '{expanded}'")
else:
print(" ⚠️ Query expansion offline (Ollama not available)")
print(f" ⚠️ Query expansion offline (Ollama not available)")
# Test that it still returns original query
expanded = expander.expand_query(test_query)
if expanded == test_query:
print(" ✅ Graceful degradation working: returns original query")
print(f" ✅ Graceful degradation working: returns original query")
else:
print(" ❌ Error: should return original query when offline")
print(f" ❌ Error: should return original query when offline")
return False
# Test smart ranking (this always works as it's zero-overhead)
print(" 🧮 Testing smart ranking...")
# Create a simple test to verify the method exists and can be called
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
# Create a simple test project
test_file = temp_path / "README.md"
test_file.write_text("# Test Project\nThis is a test README file.")
try:
searcher = CodeSearcher(temp_path)
# Test that the _smart_rerank method exists
if hasattr(searcher, "_smart_rerank"):
if hasattr(searcher, '_smart_rerank'):
print(" ✅ Smart ranking method available")
return True
else:
print(" ❌ Smart ranking method not found")
return False
except Exception as e:
print(f" ❌ Smart ranking test failed: {e}")
return False
except Exception as e:
print(f" ❌ New features test failed: {e}")
return False
def main():
"""Run all integration tests."""
print("=" * 50)
print("RAG System Integration Check")
print("=" * 50)
results = {
"Chunker": test_chunker(),
"Indexer": test_indexer_storage(),
"Indexer": test_indexer_storage(),
"Search": test_search_integration(),
"Server": test_server(),
"New Features": test_new_features(),
"New Features": test_new_features()
}
print("\n" + "=" * 50)
print("SUMMARY:")
print("=" * 50)
all_passed = True
for component, passed in results.items():
status = " PASS" if passed else " FAIL"
print(f"{component}: {status}")
if not passed:
all_passed = False
if all_passed:
print("\n All integration tests passed!")
else:
print("\n️ Some tests failed - fixes needed!")
return all_passed
if __name__ == "__main__":
success = main()
sys.exit(0 if success else 1)
sys.exit(0 if success else 1)

24
tests/show_index_contents.py
View File

@ -3,19 +3,19 @@
Show what files are actually indexed in the RAG system.
"""
import os
import sys
from collections import Counter
import os
from pathlib import Path
from mini_rag.vector_store import VectorStore
if sys.platform == "win32":
os.environ["PYTHONUTF8"] = "1"
sys.stdout.reconfigure(encoding="utf-8")
if sys.platform == 'win32':
os.environ['PYTHONUTF8'] = '1'
sys.stdout.reconfigure(encoding='utf-8')
sys.path.insert(0, str(Path(__file__).parent))
from mini_rag.vector_store import VectorStore
from collections import Counter
project_path = Path.cwd()
store = VectorStore(project_path)
store._connect()
@ -32,16 +32,16 @@ for row in store.table.to_pandas().itertuples():
unique_files = sorted(set(files))
print("\n Indexed Files Summary")
print(f"\n Indexed Files Summary")
print(f"Total files: {len(unique_files)}")
print(f"Total chunks: {len(files)}")
print(f"\nChunk types: {dict(chunk_types)}")
print("\n Files with most chunks:")
print(f"\n Files with most chunks:")
for file, count in chunks_by_file.most_common(10):
print(f" {count:3d} chunks: {file}")
print("\n Text-to-speech files:")
tts_files = [f for f in unique_files if "text-to-speech" in f or "speak" in f.lower()]
print(f"\n Text-to-speech files:")
tts_files = [f for f in unique_files if 'text-to-speech' in f or 'speak' in f.lower()]
for f in tts_files:
print(f" - {f} ({chunks_by_file[f]} chunks)")
print(f" - {f} ({chunks_by_file[f]} chunks)")

67
tests/test_context_retrieval.py
View File

@ -12,37 +12,30 @@ Or run directly with venv:
import os
from pathlib import Path
from mini_rag.ollama_embeddings import OllamaEmbedder as CodeEmbedder
from mini_rag.search import CodeSearcher
from mini_rag.ollama_embeddings import OllamaEmbedder as CodeEmbedder
# Check if virtual environment is activated
def check_venv():
if "VIRTUAL_ENV" not in os.environ:
if 'VIRTUAL_ENV' not in os.environ:
print("⚠️ WARNING: Virtual environment not detected!")
print(" This test requires the virtual environment to be activated.")
print(
" Run: source .venv/bin/activate && PYTHONPATH=. python tests/test_context_retrieval.py"
)
print(" Run: source .venv/bin/activate && PYTHONPATH=. python tests/test_context_retrieval.py")
print(" Continuing anyway...\n")
check_venv()
def test_context_retrieval():
"""Test the new context retrieval functionality."""
# Initialize searcher
project_path = Path(__file__).parent
try:
embedder = CodeEmbedder()
searcher = CodeSearcher(project_path, embedder)
print("Testing search with context...")
# Test 1: Search without context
print("\n1. Search WITHOUT context:")
results = searcher.search("chunk metadata", top_k=3, include_context=False)
@ -52,7 +45,7 @@ def test_context_retrieval():
print(f" Has context_before: {result.context_before is not None}")
print(f" Has context_after: {result.context_after is not None}")
print(f" Has parent_chunk: {result.parent_chunk is not None}")
# Test 2: Search with context
print("\n2. Search WITH context:")
results = searcher.search("chunk metadata", top_k=3, include_context=True)
@ -62,51 +55,39 @@ def test_context_retrieval():
print(f" Has context_before: {result.context_before is not None}")
print(f" Has context_after: {result.context_after is not None}")
print(f" Has parent_chunk: {result.parent_chunk is not None}")
if result.context_before:
print(f" Context before preview: {result.context_before[:50]}...")
if result.context_after:
print(f" Context after preview: {result.context_after[:50]}...")
if result.parent_chunk:
print(
f" Parent chunk: {result.parent_chunk.name} ({result.parent_chunk.chunk_type})"
)
print(f" Parent chunk: {result.parent_chunk.name} ({result.parent_chunk.chunk_type})")
# Test 3: get_chunk_context method
print("\n3. Testing get_chunk_context method:")
# Get a sample chunk_id from the first result
df = searcher.table.to_pandas()
if not df.empty:
sample_chunk_id = df.iloc[0]["chunk_id"]
sample_chunk_id = df.iloc[0]['chunk_id']
print(f" Getting context for chunk_id: {sample_chunk_id}")
context = searcher.get_chunk_context(sample_chunk_id)
if context["chunk"]:
print(
f" Main chunk: {context['chunk'].file_path}:{context['chunk'].start_line}"
)
if context["prev"]:
print(
f" Previous chunk: lines {context['prev'].start_line}-{context['prev'].end_line}"
)
if context["next"]:
print(
f" Next chunk: lines {context['next'].start_line}-{context['next'].end_line}"
)
if context["parent"]:
print(
f" Parent chunk: {context['parent'].name} ({context['parent'].chunk_type})"
)
if context['chunk']:
print(f" Main chunk: {context['chunk'].file_path}:{context['chunk'].start_line}")
if context['prev']:
print(f" Previous chunk: lines {context['prev'].start_line}-{context['prev'].end_line}")
if context['next']:
print(f" Next chunk: lines {context['next'].start_line}-{context['next'].end_line}")
if context['parent']:
print(f" Parent chunk: {context['parent'].name} ({context['parent'].chunk_type})")
print("\nAll tests completed successfully!")
except Exception as e:
print(f"Error during testing: {e}")
import traceback
traceback.print_exc()
if __name__ == "__main__":
test_context_retrieval()
test_context_retrieval()

263
tests/test_hybrid_search.py
View File

@ -12,49 +12,46 @@ Or run directly with venv:
"""
import time
import json
from pathlib import Path
from typing import Any, Dict
from typing import List, Dict, Any
from rich.console import Console
from rich.progress import track
from rich.table import Table
from rich.panel import Panel
from rich.columns import Columns
from rich.syntax import Syntax
from rich.progress import track
from mini_rag.search import CodeSearcher, SearchResult
from mini_rag.ollama_embeddings import OllamaEmbedder as CodeEmbedder
from mini_rag.search import CodeSearcher
console = Console()
class SearchTester:
"""Test harness for hybrid search evaluation."""
def __init__(self, project_path: Path):
self.project_path = project_path
console.print(f"\n[cyan]Initializing search system for: {project_path}[/cyan]")
# Initialize searcher
start = time.time()
self.searcher = CodeSearcher(project_path)
init_time = time.time() - start
console.print(f"[green] Initialized in {init_time:.2f}s[/green]")
# Get statistics
stats = self.searcher.get_statistics()
if "error" not in stats:
console.print(
f"[dim]Index contains {stats['total_chunks']} chunks from {stats['unique_files']} files[/dim]\n"
)
def run_query(
self,
query: str,
top_k: int = 10,
semantic_only: bool = False,
bm25_only: bool = False,
) -> Dict[str, Any]:
if 'error' not in stats:
console.print(f"[dim]Index contains {stats['total_chunks']} chunks from {stats['unique_files']} files[/dim]\n")
def run_query(self, query: str, top_k: int = 10,
semantic_only: bool = False,
bm25_only: bool = False) -> Dict[str, Any]:
"""Run a single query and return metrics."""
# Set weights based on mode
if semantic_only:
semantic_weight, bm25_weight = 1.0, 0.0
@ -65,156 +62,150 @@ class SearchTester:
else:
semantic_weight, bm25_weight = 0.7, 0.3
mode = "Hybrid (70/30)"
# Run search
start = time.time()
results = self.searcher.search(
query=query,
top_k=top_k,
semantic_weight=semantic_weight,
bm25_weight=bm25_weight,
bm25_weight=bm25_weight
)
search_time = time.time() - start
return {
"query": query,
"mode": mode,
"results": results,
"search_time_ms": search_time * 1000,
"num_results": len(results),
"top_score": results[0].score if results else 0,
"avg_score": sum(r.score for r in results) / len(results) if results else 0,
'query': query,
'mode': mode,
'results': results,
'search_time_ms': search_time * 1000,
'num_results': len(results),
'top_score': results[0].score if results else 0,
'avg_score': sum(r.score for r in results) / len(results) if results else 0,
}
def compare_search_modes(self, query: str, top_k: int = 5):
"""Compare results across different search modes."""
console.print(f"\n[bold cyan]Query:[/bold cyan] '{query}'")
console.print(f"[dim]Top {top_k} results per mode[/dim]\n")
# Run searches in all modes
modes = [
("hybrid", False, False),
("semantic", True, False),
("bm25", False, True),
('hybrid', False, False),
('semantic', True, False),
('bm25', False, True)
]
all_results = {}
for mode_name, semantic_only, bm25_only in modes:
result = self.run_query(query, top_k, semantic_only, bm25_only)
all_results[mode_name] = result
# Create comparison table
table = Table(title="Search Mode Comparison")
table.add_column("Metric", style="cyan", width=20)
table.add_column("Hybrid (70/30)", style="green")
table.add_column("Semantic Only", style="blue")
table.add_column("BM25 Only", style="magenta")
# Add metrics
table.add_row(
"Search Time (ms)",
f"{all_results['hybrid']['search_time_ms']:.1f}",
f"{all_results['semantic']['search_time_ms']:.1f}",
f"{all_results['bm25']['search_time_ms']:.1f}",
f"{all_results['bm25']['search_time_ms']:.1f}"
)
table.add_row(
"Results Found",
str(all_results["hybrid"]["num_results"]),
str(all_results["semantic"]["num_results"]),
str(all_results["bm25"]["num_results"]),
str(all_results['hybrid']['num_results']),
str(all_results['semantic']['num_results']),
str(all_results['bm25']['num_results'])
)
table.add_row(
"Top Score",
f"{all_results['hybrid']['top_score']:.3f}",
f"{all_results['semantic']['top_score']:.3f}",
f"{all_results['bm25']['top_score']:.3f}",
f"{all_results['bm25']['top_score']:.3f}"
)
table.add_row(
"Avg Score",
f"{all_results['hybrid']['avg_score']:.3f}",
f"{all_results['semantic']['avg_score']:.3f}",
f"{all_results['bm25']['avg_score']:.3f}",
f"{all_results['bm25']['avg_score']:.3f}"
)
console.print(table)
# Show top results from each mode
console.print("\n[bold]Top Results by Mode:[/bold]")
for mode_name, result_data in all_results.items():
console.print(f"\n[bold cyan]{result_data['mode']}:[/bold cyan]")
for i, result in enumerate(result_data["results"][:3], 1):
console.print(
f"\n{i}. [green]{result.file_path}[/green]:{result.start_line}-{result.end_line}"
)
console.print(
f" [dim]Type: {result.chunk_type} | Name: {result.name} | Score: {result.score:.3f}[/dim]"
)
for i, result in enumerate(result_data['results'][:3], 1):
console.print(f"\n{i}. [green]{result.file_path}[/green]:{result.start_line}-{result.end_line}")
console.print(f" [dim]Type: {result.chunk_type} | Name: {result.name} | Score: {result.score:.3f}[/dim]")
# Show snippet
lines = result.content.splitlines()[:5]
for line in lines:
console.print(
f" [dim]{line[:80]}{'...' if len(line) > 80 else ''}[/dim]"
)
console.print(f" [dim]{line[:80]}{'...' if len(line) > 80 else ''}[/dim]")
def test_query_types(self):
"""Test different types of queries to show system capabilities."""
test_queries = [
# Keyword-heavy queries (should benefit from BM25)
{
"query": "class CodeSearcher search method",
"description": "Specific class and method names",
"expected": "Should find exact matches with BM25 boost",
'query': 'class CodeSearcher search method',
'description': 'Specific class and method names',
'expected': 'Should find exact matches with BM25 boost'
},
{
"query": "import pandas numpy torch",
"description": "Multiple import keywords",
"expected": "BM25 should excel at finding import statements",
'query': 'import pandas numpy torch',
'description': 'Multiple import keywords',
'expected': 'BM25 should excel at finding import statements'
},
# Semantic queries (should benefit from embeddings)
{
"query": "find similar code chunks using vector similarity",
"description": "Natural language description",
"expected": "Semantic search should understand intent",
'query': 'find similar code chunks using vector similarity',
'description': 'Natural language description',
'expected': 'Semantic search should understand intent'
},
{
"query": "how to initialize database connection",
"description": "How-to question",
"expected": "Semantic search should find relevant implementations",
'query': 'how to initialize database connection',
'description': 'How-to question',
'expected': 'Semantic search should find relevant implementations'
},
# Mixed queries (benefit from hybrid)
{
"query": "BM25 scoring implementation for search ranking",
"description": "Technical terms + intent",
"expected": "Hybrid should balance keyword and semantic matching",
'query': 'BM25 scoring implementation for search ranking',
'description': 'Technical terms + intent',
'expected': 'Hybrid should balance keyword and semantic matching'
},
{
"query": "embedding vectors for code search with transformers",
"description": "Domain-specific terminology",
"expected": "Hybrid should leverage both approaches",
},
'query': 'embedding vectors for code search with transformers',
'description': 'Domain-specific terminology',
'expected': 'Hybrid should leverage both approaches'
}
]
console.print("\n[bold yellow]Query Type Analysis[/bold yellow]")
console.print(
"[dim]Testing different query patterns to demonstrate hybrid search benefits[/dim]\n"
)
console.print("[dim]Testing different query patterns to demonstrate hybrid search benefits[/dim]\n")
for test_case in test_queries:
console.rule(f"\n[cyan]{test_case['description']}[/cyan]")
console.print(f"[dim]{test_case['expected']}[/dim]")
self.compare_search_modes(test_case["query"], top_k=3)
self.compare_search_modes(test_case['query'], top_k=3)
time.sleep(0.5) # Brief pause between tests
def benchmark_performance(self, num_queries: int = 50):
"""Run performance benchmarks."""
console.print("\n[bold yellow]Performance Benchmark[/bold yellow]")
console.print(f"[dim]Running {num_queries} queries to measure performance[/dim]\n")
# Sample queries for benchmarking
benchmark_queries = [
"search function implementation",
@ -226,28 +217,28 @@ class SearchTester:
"test cases unit testing",
"configuration settings",
"logging and debugging",
"performance optimization",
"performance optimization"
] * (num_queries // 10 + 1)
benchmark_queries = benchmark_queries[:num_queries]
# Benchmark each mode
modes = [
("Hybrid (70/30)", 0.7, 0.3),
("Semantic Only", 1.0, 0.0),
("BM25 Only", 0.0, 1.0),
('Hybrid (70/30)', 0.7, 0.3),
('Semantic Only', 1.0, 0.0),
('BM25 Only', 0.0, 1.0)
]
results_table = Table(title="Performance Benchmark Results")
results_table.add_column("Mode", style="cyan")
results_table.add_column("Avg Time (ms)", style="green")
results_table.add_column("Min Time (ms)", style="blue")
results_table.add_column("Max Time (ms)", style="red")
results_table.add_column("Total Time (s)", style="magenta")
for mode_name, sem_weight, bm25_weight in modes:
times = []
console.print(f"[cyan]Testing {mode_name}...[/cyan]")
for query in track(benchmark_queries, description=f"Running {mode_name}"):
start = time.time()
@ -255,75 +246,69 @@ class SearchTester:
query=query,
limit=10,
semantic_weight=sem_weight,
bm25_weight=bm25_weight,
bm25_weight=bm25_weight
)
elapsed = (time.time() - start) * 1000
times.append(elapsed)
# Calculate statistics
avg_time = sum(times) / len(times)
min_time = min(times)
max_time = max(times)
total_time = sum(times) / 1000
results_table.add_row(
mode_name,
f"{avg_time:.2f}",
f"{min_time:.2f}",
f"{max_time:.2f}",
f"{total_time:.2f}",
f"{total_time:.2f}"
)
console.print("\n")
console.print(results_table)
def test_diversity_constraints(self):
"""Test the diversity constraints in search results."""
console.print("\n[bold yellow]Diversity Constraints Test[/bold yellow]")
console.print("[dim]Verifying max 2 chunks per file and chunk type diversity[/dim]\n")
# Query that might return many results from same files
query = "function implementation code search"
results = self.searcher.search(query, top_k=20)
# Analyze diversity
file_counts = {}
chunk_types = {}
for result in results:
file_counts[result.file_path] = file_counts.get(result.file_path, 0) + 1
chunk_types[result.chunk_type] = chunk_types.get(result.chunk_type, 0) + 1
# Create diversity report
table = Table(title="Result Diversity Analysis")
table.add_column("Metric", style="cyan")
table.add_column("Value", style="green")
table.add_row("Total Results", str(len(results)))
table.add_row("Unique Files", str(len(file_counts)))
table.add_row(
"Max Chunks per File", str(max(file_counts.values()) if file_counts else 0)
)
table.add_row("Max Chunks per File", str(max(file_counts.values()) if file_counts else 0))
table.add_row("Unique Chunk Types", str(len(chunk_types)))
console.print(table)
# Show file distribution
if len(file_counts) > 0:
console.print("\n[bold]File Distribution:[/bold]")
for file_path, count in sorted(
file_counts.items(), key=lambda x: x[1], reverse=True
)[:5]:
for file_path, count in sorted(file_counts.items(), key=lambda x: x[1], reverse=True)[:5]:
console.print(f" {count}x {file_path}")
# Show chunk type distribution
if len(chunk_types) > 0:
console.print("\n[bold]Chunk Type Distribution:[/bold]")
for chunk_type, count in sorted(
chunk_types.items(), key=lambda x: x[1], reverse=True
):
for chunk_type, count in sorted(chunk_types.items(), key=lambda x: x[1], reverse=True):
console.print(f" {chunk_type}: {count} chunks")
# Verify constraints
console.print("\n[bold]Constraint Verification:[/bold]")
max_per_file = max(file_counts.values()) if file_counts else 0
@ -336,45 +321,45 @@ class SearchTester:
def main():
"""Run comprehensive hybrid search tests."""
import sys
if len(sys.argv) > 1:
project_path = Path(sys.argv[1])
else:
project_path = Path.cwd()
if not (project_path / ".mini-rag").exists():
if not (project_path / '.mini-rag').exists():
console.print("[red]Error: No RAG index found. Run 'rag-mini index' first.[/red]")
return
# Create tester
tester = SearchTester(project_path)
# Run all tests
console.print("\n" + "=" * 80)
console.print("\n" + "="*80)
console.print("[bold green]Mini RAG Hybrid Search Test Suite[/bold green]")
console.print("=" * 80)
console.print("="*80)
# Test 1: Query type analysis
tester.test_query_types()
# Test 2: Performance benchmark
console.print("\n" + "-" * 80)
console.print("\n" + "-"*80)
tester.benchmark_performance(num_queries=30)
# Test 3: Diversity constraints
console.print("\n" + "-" * 80)
console.print("\n" + "-"*80)
tester.test_diversity_constraints()
# Summary
console.print("\n" + "=" * 80)
console.print("\n" + "="*80)
console.print("[bold green]Test Suite Complete![/bold green]")
console.print("\n[dim]The hybrid search combines:")
console.print(" • Semantic understanding from transformer embeddings")
console.print(" • Keyword relevance from BM25 scoring")
console.print(" • Result diversity through intelligent filtering")
console.print(" • Performance optimization through concurrent processing[/dim]")
console.print("=" * 80 + "\n")
console.print("="*80 + "\n")
if __name__ == "__main__":
main()
main()

7
tests/test_min_chunk_size.py
View File

@ -1,16 +1,13 @@
"""Test with smaller min_chunk_size."""
from pathlib import Path
from mini_rag.chunker import CodeChunker
from pathlib import Path
test_code = '''"""Test module."""
import os
class MyClass:
def method(self):
return 42
@ -27,4 +24,4 @@ for i, chunk in enumerate(chunks):
print(f"\nChunk {i}: {chunk.chunk_type} '{chunk.name}'")
print(f"Lines {chunk.start_line}-{chunk.end_line}")
print(f"Size: {len(chunk.content.splitlines())} lines")
print("-" * 40)
print("-" * 40)

199
tests/test_mode_separation.py
View File

@ -7,6 +7,7 @@ between thinking and no-thinking modes.
"""
import sys
import os
import tempfile
import unittest
from pathlib import Path
@ -15,54 +16,51 @@ from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))
try:
from mini_rag.config import RAGConfig
from mini_rag.llm_synthesizer import LLMSynthesizer
from mini_rag.explorer import CodeExplorer
from mini_rag.config import RAGConfig
from mini_rag.indexer import ProjectIndexer
from mini_rag.llm_synthesizer import LLMSynthesizer
from mini_rag.search import CodeSearcher
except ImportError as e:
print(f"❌ Could not import RAG components: {e}")
print(" This test requires the full RAG system to be installed")
sys.exit(1)
class TestModeSeparation(unittest.TestCase):
"""Test the clean separation between synthesis and exploration modes."""
def setUp(self):
"""Set up test environment."""
self.temp_dir = tempfile.mkdtemp()
self.project_path = Path(self.temp_dir)
# Create a simple test project
test_file = self.project_path / "test_module.py"
test_file.write_text(
'''"""Test module for mode separation testing."""
test_file.write_text('''"""Test module for mode separation testing."""
def authenticate_user(username: str, password: str) -> bool:
"""Authenticate a user with username and password."""
# Simple authentication logic
if not username or not password:
return False
# Check against database (simplified)
valid_users = {"admin": "secret", "user": "password"}
return valid_users.get(username) == password
class UserManager:
"""Manages user operations."""
def __init__(self):
self.users = {}
def create_user(self, username: str) -> bool:
"""Create a new user."""
if username in self.users:
return False
self.users[username] = {"created": True}
return True
def get_user_info(self, username: str) -> dict:
"""Get user information."""
return self.users.get(username, {})
@ -73,216 +71,196 @@ def process_login_request(username: str, password: str) -> dict:
return {"success": True, "message": "Login successful"}
else:
return {"success": False, "message": "Invalid credentials"}
'''
)
''')
# Index the project for testing
try:
indexer = ProjectIndexer(self.project_path)
indexer.index_project()
except Exception as e:
self.skipTest(f"Could not index test project: {e}")
def tearDown(self):
"""Clean up test environment."""
import shutil
shutil.rmtree(self.temp_dir, ignore_errors=True)
def test_01_synthesis_mode_defaults(self):
"""Test that synthesis mode has correct defaults."""
synthesizer = LLMSynthesizer()
# Should default to no thinking
self.assertFalse(
synthesizer.enable_thinking, "Synthesis mode should default to no thinking"
)
self.assertFalse(synthesizer.enable_thinking,
"Synthesis mode should default to no thinking")
print("✅ Synthesis mode defaults to no thinking")
def test_02_exploration_mode_defaults(self):
"""Test that exploration mode enables thinking."""
config = RAGConfig()
explorer = CodeExplorer(self.project_path, config)
# Should enable thinking in exploration mode
self.assertTrue(
explorer.synthesizer.enable_thinking,
"Exploration mode should enable thinking",
)
self.assertTrue(explorer.synthesizer.enable_thinking,
"Exploration mode should enable thinking")
print("✅ Exploration mode enables thinking by default")
def test_03_no_runtime_thinking_toggle(self):
"""Test that thinking mode cannot be toggled at runtime."""
synthesizer = LLMSynthesizer(enable_thinking=False)
# Should not have public methods to toggle thinking
thinking_methods = [
method
for method in dir(synthesizer)
if "thinking" in method.lower() and not method.startswith("_")
]
thinking_methods = [method for method in dir(synthesizer)
if 'thinking' in method.lower() and not method.startswith('_')]
# The only thinking-related attribute should be the readonly enable_thinking
self.assertEqual(
len(thinking_methods), 0, "Should not have public thinking toggle methods"
)
self.assertEqual(len(thinking_methods), 0,
"Should not have public thinking toggle methods")
print("✅ No runtime thinking toggle methods available")
def test_04_mode_contamination_prevention(self):
"""Test that modes don't contaminate each other."""
if not self._ollama_available():
self.skipTest("Ollama not available for contamination testing")
# Create synthesis mode synthesizer
synthesis_synthesizer = LLMSynthesizer(enable_thinking=False)
# Create exploration mode synthesizer
# Create exploration mode synthesizer
exploration_synthesizer = LLMSynthesizer(enable_thinking=True)
# Both should maintain their thinking settings
self.assertFalse(
synthesis_synthesizer.enable_thinking,
"Synthesis synthesizer should remain no-thinking",
)
self.assertTrue(
exploration_synthesizer.enable_thinking,
"Exploration synthesizer should remain thinking-enabled",
)
self.assertFalse(synthesis_synthesizer.enable_thinking,
"Synthesis synthesizer should remain no-thinking")
self.assertTrue(exploration_synthesizer.enable_thinking,
"Exploration synthesizer should remain thinking-enabled")
print("✅ Mode contamination prevented")
def test_05_exploration_session_management(self):
"""Test exploration session management."""
config = RAGConfig()
explorer = CodeExplorer(self.project_path, config)
# Should start with no active session
self.assertIsNone(explorer.current_session, "Should start with no active session")
self.assertIsNone(explorer.current_session,
"Should start with no active session")
# Should be able to create session summary even without session
summary = explorer.get_session_summary()
self.assertIn("No active", summary, "Should handle no active session gracefully")
self.assertIn("No active", summary,
"Should handle no active session gracefully")
print("✅ Session management working correctly")
def test_06_context_memory_structure(self):
"""Test that exploration mode has context memory structure."""
config = RAGConfig()
explorer = CodeExplorer(self.project_path, config)
# Should have context tracking attributes
self.assertTrue(
hasattr(explorer, "current_session"),
"Explorer should have session tracking",
)
self.assertTrue(hasattr(explorer, 'current_session'),
"Explorer should have session tracking")
print("✅ Context memory structure present")
def test_07_synthesis_mode_no_thinking_prompts(self):
"""Test that synthesis mode properly handles no-thinking."""
if not self._ollama_available():
self.skipTest("Ollama not available for prompt testing")
synthesizer = LLMSynthesizer(enable_thinking=False)
# Test the _call_ollama method handling
if hasattr(synthesizer, "_call_ollama"):
if hasattr(synthesizer, '_call_ollama'):
# Should append <no_think> when thinking disabled
# This is a white-box test of the implementation
try:
# Mock test - just verify the method exists and can be called
# Test call (result unused)
synthesizer._call_ollama("test", temperature=0.1, disable_thinking=True)
result = synthesizer._call_ollama("test", temperature=0.1, disable_thinking=True)
# Don't assert on result since Ollama might not be available
print("✅ No-thinking prompt handling available")
except Exception as e:
print(f"⚠️ Prompt handling test skipped: {e}")
else:
self.fail("Synthesizer should have _call_ollama method")
def test_08_mode_specific_initialization(self):
"""Test that modes initialize correctly with lazy loading."""
# Synthesis mode
synthesis_synthesizer = LLMSynthesizer(enable_thinking=False)
self.assertFalse(
synthesis_synthesizer._initialized,
"Should start uninitialized for lazy loading",
)
# Exploration mode
self.assertFalse(synthesis_synthesizer._initialized,
"Should start uninitialized for lazy loading")
# Exploration mode
config = RAGConfig()
explorer = CodeExplorer(self.project_path, config)
self.assertFalse(
explorer.synthesizer._initialized,
"Should start uninitialized for lazy loading",
)
self.assertFalse(explorer.synthesizer._initialized,
"Should start uninitialized for lazy loading")
print("✅ Lazy initialization working correctly")
def test_09_search_vs_exploration_integration(self):
"""Test integration differences between search and exploration."""
# Regular search (synthesis mode)
searcher = CodeSearcher(self.project_path)
search_results = searcher.search("authentication", top_k=3)
self.assertGreater(len(search_results), 0, "Search should return results")
self.assertGreater(len(search_results), 0,
"Search should return results")
# Exploration mode setup
config = RAGConfig()
explorer = CodeExplorer(self.project_path, config)
# Both should work with same project but different approaches
self.assertTrue(
hasattr(explorer, "synthesizer"),
"Explorer should have thinking-enabled synthesizer",
)
self.assertTrue(hasattr(explorer, 'synthesizer'),
"Explorer should have thinking-enabled synthesizer")
print("✅ Search and exploration integration working")
def test_10_mode_guidance_detection(self):
"""Test that the system can detect when to recommend different modes."""
# Words that should trigger exploration mode recommendation
exploration_triggers = ["why", "how", "explain", "debug"]
exploration_triggers = ['why', 'how', 'explain', 'debug']
for trigger in exploration_triggers:
query = f"{trigger} does authentication work"
# This would typically be tested in the main CLI
# Here we just verify the trigger detection logic exists
has_trigger = any(word in query.lower() for word in exploration_triggers)
self.assertTrue(has_trigger, f"Should detect '{trigger}' as exploration trigger")
self.assertTrue(has_trigger,
f"Should detect '{trigger}' as exploration trigger")
print("✅ Mode guidance detection working")
def _ollama_available(self) -> bool:
"""Check if Ollama is available for testing."""
try:
import requests
response = requests.get("http://localhost:11434/api/tags", timeout=5)
return response.status_code == 200
except Exception:
return False
def main():
"""Run mode separation tests."""
print("🧪 Testing Mode Separation")
print("=" * 40)
# Check if we're in the right environment
if not Path("mini_rag").exists():
print("❌ Tests must be run from the FSS-Mini-RAG root directory")
sys.exit(1)
# Run tests
loader = unittest.TestLoader()
suite = loader.loadTestsFromTestCase(TestModeSeparation)
runner = unittest.TextTestRunner(verbosity=2)
result = runner.run(suite)
# Summary
print("\n" + "=" * 40)
if result.wasSuccessful():
@ -291,10 +269,9 @@ def main():
else:
print("❌ Some tests failed")
print(f" Failed: {len(result.failures)}, Errors: {len(result.errors)}")
return result.wasSuccessful()
if __name__ == "__main__":
success = main()
sys.exit(0 if success else 1)
sys.exit(0 if success else 1)

244
tests/test_ollama_integration.py
View File

@ -8,71 +8,72 @@ what's working and what needs attention.
Run with: python3 tests/test_ollama_integration.py
"""
import sys
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
import requests
from mini_rag.config import RAGConfig
from mini_rag.llm_synthesizer import LLMSynthesizer
from mini_rag.query_expander import QueryExpander
import json
import sys
from pathlib import Path
from unittest.mock import patch, MagicMock
# Add project to path
sys.path.insert(0, str(Path(__file__).parent.parent))
from mini_rag.query_expander import QueryExpander
from mini_rag.llm_synthesizer import LLMSynthesizer
from mini_rag.config import RAGConfig
class TestOllamaIntegration(unittest.TestCase):
"""
Tests to help beginners troubleshoot their Ollama setup.
Each test explains what it's checking and gives clear feedback
about what's working or needs to be fixed.
"""
def setUp(self):
"""Set up test configuration."""
self.config = RAGConfig()
print(f"\n🧪 Testing with Ollama host: {self.config.llm.ollama_host}")
def test_01_ollama_server_running(self):
"""
✅ Check if Ollama server is running and responding.
This test verifies that:
- Ollama is installed and running
- The API endpoint is accessible
- Basic connectivity works
"""
print("\n📡 Testing Ollama server connectivity...")
try:
response = requests.get(
f"http://{self.config.llm.ollama_host}/api/tags", timeout=5
f"http://{self.config.llm.ollama_host}/api/tags",
timeout=5
)
if response.status_code == 200:
data = response.json()
models = data.get("models", [])
print(" ✅ Ollama server is running!")
models = data.get('models', [])
print(f" ✅ Ollama server is running!")
print(f" 📦 Found {len(models)} models available")
if models:
print(" 🎯 Available models:")
for model in models[:5]: # Show first 5
name = model.get("name", "unknown")
size = model.get("size", 0)
name = model.get('name', 'unknown')
size = model.get('size', 0)
print(f" • {name} ({size//1000000:.0f}MB)")
if len(models) > 5:
print(f" ... and {len(models)-5} more")
else:
print(" ⚠️ No models found. Install with: ollama pull qwen3:4b")
self.assertTrue(True)
else:
self.fail(f"Ollama server responded with status {response.status_code}")
except requests.exceptions.ConnectionError:
self.fail(
"❌ Cannot connect to Ollama server.\n"
@ -83,32 +84,35 @@ class TestOllamaIntegration(unittest.TestCase):
)
except Exception as e:
self.fail(f"❌ Unexpected error: {e}")
def test_02_embedding_model_available(self):
"""
✅ Check if embedding model is available.
This test verifies that:
- The embedding model (nomic-embed-text) is installed
- Embedding API calls work correctly
- Model responds with valid embeddings
"""
print("\n🧠 Testing embedding model availability...")
try:
# Test embedding generation
response = requests.post(
f"http://{self.config.llm.ollama_host}/api/embeddings",
json={"model": "nomic-embed-text", "prompt": "test embedding"},
timeout=10,
json={
"model": "nomic-embed-text",
"prompt": "test embedding"
},
timeout=10
)
if response.status_code == 200:
data = response.json()
embedding = data.get("embedding", [])
embedding = data.get('embedding', [])
if embedding and len(embedding) > 0:
print(" ✅ Embedding model working!")
print(f" ✅ Embedding model working!")
print(f" 📊 Generated {len(embedding)}-dimensional vectors")
self.assertTrue(len(embedding) > 100) # Should be substantial vectors
else:
@ -122,283 +126,285 @@ class TestOllamaIntegration(unittest.TestCase):
)
else:
self.fail(f"Embedding API error: {response.status_code}")
except Exception as e:
self.fail(f"❌ Embedding test failed: {e}")
def test_03_llm_model_available(self):
"""
✅ Check if LLM models are available for synthesis/expansion.
This test verifies that:
- At least one LLM model is available
- The model can generate text responses
- Response quality is reasonable
"""
print("\n🤖 Testing LLM model availability...")
synthesizer = LLMSynthesizer(config=self.config)
if not synthesizer.is_available():
self.fail(
"❌ No LLM models available.\n"
" 💡 Install a model like: ollama pull qwen3:4b"
)
print(f" ✅ Found {len(synthesizer.available_models)} LLM models")
print(f" 🎯 Will use: {synthesizer.model}")
# Test basic text generation
try:
response = synthesizer._call_ollama(
"Complete this: The capital of France is", temperature=0.1
"Complete this: The capital of France is",
temperature=0.1
)
if response and len(response.strip()) > 0:
print(" ✅ Model generating responses!")
print(f" ✅ Model generating responses!")
print(f" 💬 Sample response: '{response[:50]}...'")
# Basic quality check
if "paris" in response.lower():
print(" 🎯 Response quality looks good!")
else:
print(" ⚠️ Response quality might be low")
self.assertTrue(len(response) > 5)
else:
self.fail("Model produced empty response")
except Exception as e:
self.fail(f"❌ LLM generation test failed: {e}")
def test_04_query_expansion_working(self):
"""
✅ Check if query expansion is working correctly.
This test verifies that:
- QueryExpander can connect to Ollama
- Expansion produces reasonable results
- Caching is working
"""
print("\n🔍 Testing query expansion...")
# Enable expansion for testing
self.config.search.expand_queries = True
expander = QueryExpander(self.config)
if not expander.is_available():
self.skipTest("⏭️ Skipping - Ollama not available (tested above)")
# Test expansion
test_query = "authentication"
expanded = expander.expand_query(test_query)
print(f" 📝 Original: '{test_query}'")
print(f" ➡️ Expanded: '{expanded}'")
# Quality checks
if expanded == test_query:
print(" ⚠️ No expansion occurred (might be normal for simple queries)")
else:
# Should contain original query
self.assertIn(test_query.lower(), expanded.lower())
# Should be longer
self.assertGreater(len(expanded.split()), len(test_query.split()))
# Test caching
cached = expander.expand_query(test_query)
self.assertEqual(expanded, cached)
print(" ✅ Expansion and caching working!")
def test_05_synthesis_mode_no_thinking(self):
"""
✅ Test synthesis mode operates without thinking.
Verifies that LLMSynthesizer in synthesis mode:
- Defaults to no thinking
- Handles <no_think> tokens properly
- Works independently of exploration mode
"""
print("\n🚀 Testing synthesis mode (no thinking)...")
# Create synthesis mode synthesizer (default behavior)
synthesizer = LLMSynthesizer()
# Should default to no thinking
self.assertFalse(
synthesizer.enable_thinking, "Synthesis mode should default to no thinking"
)
self.assertFalse(synthesizer.enable_thinking,
"Synthesis mode should default to no thinking")
print(" ✅ Defaults to no thinking")
if synthesizer.is_available():
print(" 📝 Testing with live Ollama...")
# Create mock search results
from dataclasses import dataclass
@dataclass
class MockResult:
file_path: str
content: str
score: float
results = [MockResult("auth.py", "def authenticate(user): return True", 0.95)]
# Test synthesis
results = [
MockResult("auth.py", "def authenticate(user): return True", 0.95)
]
# Test synthesis
synthesis = synthesizer.synthesize_search_results(
"user authentication", results, Path(".")
)
# Should get reasonable synthesis
self.assertIsNotNone(synthesis)
self.assertGreater(len(synthesis.summary), 10)
print(" ✅ Synthesis mode working without thinking")
else:
print(" ⏭️ Live test skipped - Ollama not available")
def test_06_exploration_mode_thinking(self):
"""
✅ Test exploration mode enables thinking.
Verifies that CodeExplorer:
- Enables thinking by default
- Has session management
- Works independently of synthesis mode
"""
print("\n🧠 Testing exploration mode (with thinking)...")
try:
from mini_rag.explorer import CodeExplorer
except ImportError:
self.skipTest("⏭️ CodeExplorer not available")
# Create exploration mode
explorer = CodeExplorer(Path("."), self.config)
# Should enable thinking
self.assertTrue(
explorer.synthesizer.enable_thinking,
"Exploration mode should enable thinking",
)
self.assertTrue(explorer.synthesizer.enable_thinking,
"Exploration mode should enable thinking")
print(" ✅ Enables thinking by default")
# Should have session management
self.assertIsNone(explorer.current_session, "Should start with no active session")
self.assertIsNone(explorer.current_session,
"Should start with no active session")
print(" ✅ Session management available")
# Should handle session summary gracefully
summary = explorer.get_session_summary()
self.assertIn("No active", summary)
print(" ✅ Graceful session handling")
def test_07_mode_separation(self):
"""
✅ Test that synthesis and exploration modes don't interfere.
Verifies clean separation:
- Different thinking settings
- Independent operation
- No cross-contamination
"""
print("\n🔄 Testing mode separation...")
# Create both modes
synthesizer = LLMSynthesizer(enable_thinking=False)
try:
from mini_rag.explorer import CodeExplorer
explorer = CodeExplorer(Path("."), self.config)
except ImportError:
self.skipTest("⏭️ CodeExplorer not available")
# Should have different thinking settings
self.assertFalse(synthesizer.enable_thinking, "Synthesis should not use thinking")
self.assertTrue(
explorer.synthesizer.enable_thinking, "Exploration should use thinking"
)
self.assertFalse(synthesizer.enable_thinking,
"Synthesis should not use thinking")
self.assertTrue(explorer.synthesizer.enable_thinking,
"Exploration should use thinking")
# Both should be uninitialized (lazy loading)
self.assertFalse(synthesizer._initialized, "Should use lazy loading")
self.assertFalse(explorer.synthesizer._initialized, "Should use lazy loading")
self.assertFalse(synthesizer._initialized,
"Should use lazy loading")
self.assertFalse(explorer.synthesizer._initialized,
"Should use lazy loading")
print(" ✅ Clean mode separation confirmed")
def test_08_with_mocked_ollama(self):
"""
✅ Test components work with mocked Ollama (for offline testing).
This test verifies that:
- System gracefully handles Ollama being unavailable
- Fallback behaviors work correctly
- Error messages are helpful
"""
print("\n🎭 Testing with mocked Ollama responses...")
# Mock successful embedding response
mock_embedding_response = MagicMock()
mock_embedding_response.status_code = 200
mock_embedding_response.json.return_value = {
"embedding": [0.1] * 768 # Standard embedding size
'embedding': [0.1] * 768 # Standard embedding size
}
# Mock LLM response
mock_llm_response = MagicMock()
mock_llm_response.status_code = 200
mock_llm_response.json.return_value = {
"response": "authentication login user verification credentials"
'response': 'authentication login user verification credentials'
}
with patch("requests.post", side_effect=[mock_embedding_response, mock_llm_response]):
with patch('requests.post', side_effect=[mock_embedding_response, mock_llm_response]):
# Test query expansion with mocked response
expander = QueryExpander(self.config)
expander.enabled = True
expanded = expander._llm_expand_query("authentication")
if expanded:
print(f" ✅ Mocked expansion: '{expanded}'")
self.assertIn("authentication", expanded)
else:
print(" ⚠️ Expansion returned None (might be expected)")
# Test graceful degradation when Ollama unavailable
with patch("requests.get", side_effect=requests.exceptions.ConnectionError()):
with patch('requests.get', side_effect=requests.exceptions.ConnectionError()):
expander_offline = QueryExpander(self.config)
# Should handle unavailable server gracefully
self.assertFalse(expander_offline.is_available())
# Should return original query when offline
result = expander_offline.expand_query("test query")
self.assertEqual(result, "test query")
print(" ✅ Graceful offline behavior working!")
def test_06_configuration_validation(self):
"""
✅ Check if configuration is valid and complete.
This test verifies that:
- All required config sections exist
- Values are reasonable
- Host/port settings are valid
"""
print("\n⚙️ Testing configuration validation...")
# Check LLM config
self.assertIsNotNone(self.config.llm)
self.assertTrue(self.config.llm.ollama_host)
self.assertTrue(isinstance(self.config.llm.max_expansion_terms, int))
self.assertGreater(self.config.llm.max_expansion_terms, 0)
print(" ✅ LLM config valid")
print(f" ✅ LLM config valid")
print(f" Host: {self.config.llm.ollama_host}")
print(f" Max expansion terms: {self.config.llm.max_expansion_terms}")
# Check search config
# Check search config
self.assertIsNotNone(self.config.search)
self.assertGreater(self.config.search.default_top_k, 0)
print(" ✅ Search config valid")
print(f" ✅ Search config valid")
print(f" Default top-k: {self.config.search.default_top_k}")
print(f" Query expansion: {self.config.search.expand_queries}")
@ -412,10 +418,10 @@ def run_troubleshooting():
print("These tests help you troubleshoot your Ollama setup.")
print("Each test explains what it's checking and how to fix issues.")
print()
# Run tests with detailed output
unittest.main(verbosity=2, exit=False)
print("\n" + "=" * 50)
print("💡 Common Solutions:")
print(" • Install Ollama: https://ollama.ai/download")
@ -426,5 +432,5 @@ def run_troubleshooting():
print("📚 For more help, see docs/QUERY_EXPANSION.md")
if __name__ == "__main__":
run_troubleshooting()
if __name__ == '__main__':
run_troubleshooting()

100
tests/test_rag_integration.py
View File

@ -10,26 +10,21 @@ Or run directly with venv:
source .venv/bin/activate && PYTHONPATH=. python tests/test_rag_integration.py
"""
import os
import tempfile
import shutil
import os
from pathlib import Path
from mini_rag.indexer import ProjectIndexer
from mini_rag.search import CodeSearcher
# Check if virtual environment is activated
def check_venv():
if "VIRTUAL_ENV" not in os.environ:
if 'VIRTUAL_ENV' not in os.environ:
print("⚠️ WARNING: Virtual environment not detected!")
print(" This test requires the virtual environment to be activated.")
print(
" Run: source .venv/bin/activate && PYTHONPATH=. python tests/test_rag_integration.py"
)
print(" Run: source .venv/bin/activate && PYTHONPATH=. python tests/test_rag_integration.py")
print(" Continuing anyway...\n")
check_venv()
# Sample Python file with proper structure
@ -40,16 +35,15 @@ This module demonstrates various Python constructs.
import os
import sys
from typing import List, Optional
from typing import List, Dict, Optional
from dataclasses import dataclass
# Module-level constants
DEFAULT_TIMEOUT = 30
MAX_RETRIES = 3
@dataclass
class Config:
"""Configuration dataclass."""
timeout: int = DEFAULT_TIMEOUT
@ -59,71 +53,73 @@ class Config:
class DataProcessor:
"""
Main data processor class.
This class handles the processing of various data types
and provides a unified interface for data operations.
"""
def __init__(self, config: Config):
"""
Initialize the processor with configuration.
Args:
config: Configuration object
"""
self.config = config
self._cache = {}
self._initialized = False
def process(self, data: List[Dict]) -> List[Dict]:
"""
Process a list of data items.
Args:
data: List of dictionaries to process
Returns:
Processed data list
"""
if not self._initialized:
self._initialize()
results = []
for item in data:
processed = self._process_item(item)
results.append(processed)
return results
def _initialize(self):
"""Initialize internal state."""
self._cache.clear()
self._initialized = True
def _process_item(self, item: Dict) -> Dict:
"""Process a single item."""
# Implementation details
return {**item, 'processed': True}
def main():
"""Main entry point."""
config = Config()
processor = DataProcessor(config)
test_data = [
{'id': 1, 'value': 'test1'},
{'id': 2, 'value': 'test2'},
]
results = processor.process(test_data)
print(f"Processed {len(results)} items")
if __name__ == "__main__":
main()
'''
# Sample markdown file
sample_markdown = """# RAG System Documentation
sample_markdown = '''# RAG System Documentation
## Overview
@ -179,103 +175,103 @@ Main class for indexing projects.
### CodeSearcher
Provides semantic search capabilities.
"""
'''
def test_integration():
"""Test the complete RAG system with smart chunking."""
# Create temporary project directory
with tempfile.TemporaryDirectory() as tmpdir:
project_path = Path(tmpdir)
# Create test files
(project_path / "processor.py").write_text(sample_code)
(project_path / "README.md").write_text(sample_markdown)
print("=" * 60)
print("TESTING RAG SYSTEM INTEGRATION")
print("=" * 60)
# Index the project
print("\n1. Indexing project...")
indexer = ProjectIndexer(project_path)
stats = indexer.index_project()
print(f" - Files indexed: {stats['files_indexed']}")
print(f" - Total chunks: {stats['chunks_created']}")
print(f" - Indexing time: {stats['time_taken']:.2f}s")
# Verify chunks were created properly
print("\n2. Verifying chunk metadata...")
# Initialize searcher
searcher = CodeSearcher(project_path)
# Search for specific content
print("\n3. Testing search functionality...")
# Test 1: Search for class with docstring
results = searcher.search("data processor class unified interface", top_k=3)
print("\n Test 1 - Class search:")
print(f"\n Test 1 - Class search:")
for i, result in enumerate(results[:1]):
print(f" - Match {i+1}: {result.file_path}")
print(f" Chunk type: {result.chunk_type}")
print(f" Score: {result.score:.3f}")
if "This class handles" in result.content:
if 'This class handles' in result.content:
print(" [OK] Docstring included with class")
else:
print(" [FAIL] Docstring not found")
# Test 2: Search for method with docstring
results = searcher.search("process list of data items", top_k=3)
print("\n Test 2 - Method search:")
print(f"\n Test 2 - Method search:")
for i, result in enumerate(results[:1]):
print(f" - Match {i+1}: {result.file_path}")
print(f" Chunk type: {result.chunk_type}")
print(f" Parent class: {getattr(result, 'parent_class', 'N/A')}")
if "Args:" in result.content and "Returns:" in result.content:
if 'Args:' in result.content and 'Returns:' in result.content:
print(" [OK] Docstring included with method")
else:
print(" [FAIL] Method docstring not complete")
# Test 3: Search markdown content
results = searcher.search("smart chunking capabilities markdown", top_k=3)
print("\n Test 3 - Markdown search:")
print(f"\n Test 3 - Markdown search:")
for i, result in enumerate(results[:1]):
print(f" - Match {i+1}: {result.file_path}")
print(f" Chunk type: {result.chunk_type}")
print(f" Lines: {result.start_line}-{result.end_line}")
# Test 4: Verify chunk navigation
print("\n Test 4 - Chunk navigation:")
print(f"\n Test 4 - Chunk navigation:")
all_results = searcher.search("", top_k=100) # Get all chunks
py_chunks = [r for r in all_results if r.file_path.endswith(".py")]
py_chunks = [r for r in all_results if r.file_path.endswith('.py')]
if py_chunks:
first_chunk = py_chunks[0]
print(f" - First chunk: index={getattr(first_chunk, 'chunk_index', 'N/A')}")
print(f" Next chunk ID: {getattr(first_chunk, 'next_chunk_id', 'N/A')}")
# Verify chain
valid_chain = True
for i in range(len(py_chunks) - 1):
curr = py_chunks[i]
# py_chunks[i + 1] # Unused variable removed
next_chunk = py_chunks[i + 1]
expected_next = f"processor_{i+1}"
if getattr(curr, "next_chunk_id", None) != expected_next:
if getattr(curr, 'next_chunk_id', None) != expected_next:
valid_chain = False
break
if valid_chain:
print(" [OK] Chunk navigation chain is valid")
else:
print(" [FAIL] Chunk navigation chain broken")
print("\n" + "=" * 60)
print("INTEGRATION TEST COMPLETED")
print("=" * 60)
if __name__ == "__main__":
test_integration()
test_integration()

188
tests/test_smart_ranking.py
View File

@ -8,26 +8,26 @@ and producing better quality results.
Run with: python3 tests/test_smart_ranking.py
"""
import sys
import unittest
from datetime import datetime, timedelta
import sys
from pathlib import Path
from unittest.mock import MagicMock, patch
from mini_rag.search import CodeSearcher, SearchResult
from datetime import datetime, timedelta
from unittest.mock import patch, MagicMock
# Add project to path
sys.path.insert(0, str(Path(__file__).parent.parent))
from mini_rag.search import SearchResult, CodeSearcher
class TestSmartRanking(unittest.TestCase):
"""
Test smart result re-ranking for better search quality.
These tests verify that important files, recent files, and
well-structured content get appropriate boosts.
"""
def setUp(self):
"""Set up test results for ranking."""
# Create mock search results with different characteristics
@ -40,31 +40,27 @@ class TestSmartRanking(unittest.TestCase):
end_line=2,
chunk_type="text",
name="temp",
language="text",
language="text"
),
SearchResult(
file_path=Path("README.md"),
content=(
"This is a comprehensive README file\n"
"with detailed installation instructions\n"
"and usage examples for beginners."
),
file_path=Path("README.md"),
content="This is a comprehensive README file\nwith detailed installation instructions\nand usage examples for beginners.",
score=0.7, # Lower initial score
start_line=1,
end_line=5,
chunk_type="markdown",
name="Installation Guide",
language="markdown",
language="markdown"
),
SearchResult(
file_path=Path("src/main.py"),
content='def main():\n """Main application entry point."""\n app = create_app()\n return app.run()',
content="def main():\n \"\"\"Main application entry point.\"\"\"\n app = create_app()\n return app.run()",
score=0.75,
start_line=10,
end_line=15,
chunk_type="function",
name="main",
language="python",
language="python"
),
SearchResult(
file_path=Path("temp/cache_123.log"),
@ -72,123 +68,123 @@ class TestSmartRanking(unittest.TestCase):
score=0.85,
start_line=1,
end_line=1,
chunk_type="text",
chunk_type="text",
name="log",
language="text",
),
language="text"
)
]
def test_01_important_file_boost(self):
"""
✅ Test that important files get ranking boosts.
README files, main files, config files, etc. should be
ranked higher than random temporary files.
"""
print("\n📈 Testing important file boost...")
# Create a minimal CodeSearcher to test ranking
searcher = MagicMock()
searcher._smart_rerank = CodeSearcher._smart_rerank.__get__(searcher)
# Test re-ranking
ranked = searcher._smart_rerank(self.mock_results.copy())
# Find README and temp file results
readme_result = next((r for r in ranked if "README" in str(r.file_path)), None)
temp_result = next((r for r in ranked if "temp" in str(r.file_path)), None)
readme_result = next((r for r in ranked if 'README' in str(r.file_path)), None)
temp_result = next((r for r in ranked if 'temp' in str(r.file_path)), None)
self.assertIsNotNone(readme_result)
self.assertIsNotNone(temp_result)
# README should be boosted (original 0.7 * 1.2 = 0.84)
self.assertGreater(readme_result.score, 0.8)
# README should now rank higher than the temp file
readme_index = ranked.index(readme_result)
temp_index = ranked.index(temp_result)
self.assertLess(readme_index, temp_index)
print(f" ✅ README boosted from 0.7 to {readme_result.score:.3f}")
print(f" 📊 README now ranks #{readme_index + 1}, temp file ranks #{temp_index + 1}")
def test_02_content_quality_boost(self):
"""
✅ Test that well-structured content gets boosts.
Content with multiple lines and good structure should
rank higher than very short snippets.
"""
print("\n📝 Testing content quality boost...")
searcher = MagicMock()
searcher._smart_rerank = CodeSearcher._smart_rerank.__get__(searcher)
ranked = searcher._smart_rerank(self.mock_results.copy())
# Find short and long content results
short_result = next((r for r in ranked if len(r.content.strip()) < 20), None)
structured_result = next((r for r in ranked if "README" in str(r.file_path)), None)
structured_result = next((r for r in ranked if 'README' in str(r.file_path)), None)
if short_result:
# Short content should be penalized (score * 0.9)
print(f" 📉 Short content penalized: {short_result.score:.3f}")
# Original was likely reduced
if structured_result:
# Well-structured content gets small boost (score * 1.02)
lines = structured_result.content.strip().split("\n")
lines = structured_result.content.strip().split('\n')
if len(lines) >= 3:
print(f" 📈 Structured content boosted: {structured_result.score:.3f}")
print(f" ({len(lines)} lines of content)")
self.assertTrue(True) # Test passes if no exceptions
def test_03_chunk_type_relevance(self):
"""
✅ Test that relevant chunk types get appropriate boosts.
Functions, classes, and documentation should be ranked
higher than random text snippets.
"""
print("\n🏷️ Testing chunk type relevance...")
searcher = MagicMock()
searcher._smart_rerank = CodeSearcher._smart_rerank.__get__(searcher)
ranked = searcher._smart_rerank(self.mock_results.copy())
# Find function result
function_result = next((r for r in ranked if r.chunk_type == "function"), None)
function_result = next((r for r in ranked if r.chunk_type == 'function'), None)
if function_result:
# Function should get boost (original score * 1.1)
print(f" ✅ Function chunk boosted: {function_result.score:.3f}")
print(f" Function: {function_result.name}")
# Should rank well compared to original score
original_score = 0.75
self.assertGreater(function_result.score, original_score)
self.assertTrue(True)
@patch("pathlib.Path.stat")
@patch('pathlib.Path.stat')
def test_04_recency_boost(self, mock_stat):
"""
✅ Test that recently modified files get ranking boosts.
Files modified in the last week should rank higher than
very old files.
"""
print("\n⏰ Testing recency boost...")
# Mock file stats for different modification times
now = datetime.now()
def mock_stat_side_effect(file_path):
mock_stat_obj = MagicMock()
if "README" in str(file_path):
if 'README' in str(file_path):
# Recent file (2 days ago)
recent_time = (now - timedelta(days=2)).timestamp()
mock_stat_obj.st_mtime = recent_time
@ -196,102 +192,98 @@ class TestSmartRanking(unittest.TestCase):
# Old file (2 months ago)
old_time = (now - timedelta(days=60)).timestamp()
mock_stat_obj.st_mtime = old_time
return mock_stat_obj
# Apply mock to Path.stat for each result
mock_stat.side_effect = lambda: mock_stat_side_effect("dummy")
# Patch the Path constructor to return mocked paths
with patch.object(Path, "stat", side_effect=mock_stat_side_effect):
with patch.object(Path, 'stat', side_effect=mock_stat_side_effect):
searcher = MagicMock()
searcher._smart_rerank = CodeSearcher._smart_rerank.__get__(searcher)
ranked = searcher._smart_rerank(self.mock_results.copy())
readme_result = next((r for r in ranked if "README" in str(r.file_path)), None)
readme_result = next((r for r in ranked if 'README' in str(r.file_path)), None)
if readme_result:
# Recent file should get boost
# Original 0.7 * 1.2 (important) * 1.1 (recent) * 1.02 (structured) ≈ 0.88
print(f" ✅ Recent file boosted: {readme_result.score:.3f}")
self.assertGreater(readme_result.score, 0.8)
print(" 📅 Recency boost system working!")
def test_05_overall_ranking_quality(self):
"""
✅ Test that overall ranking produces sensible results.
After all boosts and penalties, the ranking should make sense:
- Important, recent, well-structured files should rank highest
- Short, temporary, old files should rank lowest
"""
print("\n🏆 Testing overall ranking quality...")
searcher = MagicMock()
searcher._smart_rerank = CodeSearcher._smart_rerank.__get__(searcher)
# Test with original unsorted results
unsorted = self.mock_results.copy()
ranked = searcher._smart_rerank(unsorted)
print(" 📊 Final ranking:")
for i, result in enumerate(ranked, 1):
file_name = Path(result.file_path).name
print(f" {i}. {file_name} (score: {result.score:.3f})")
# Quality checks:
# 1. Results should be sorted by score (descending)
scores = [r.score for r in ranked]
self.assertEqual(scores, sorted(scores, reverse=True))
# 2. README should rank higher than temp files
readme_pos = next(
(i for i, r in enumerate(ranked) if "README" in str(r.file_path)), None
)
temp_pos = next((i for i, r in enumerate(ranked) if "temp" in str(r.file_path)), None)
readme_pos = next((i for i, r in enumerate(ranked) if 'README' in str(r.file_path)), None)
temp_pos = next((i for i, r in enumerate(ranked) if 'temp' in str(r.file_path)), None)
if readme_pos is not None and temp_pos is not None:
self.assertLess(readme_pos, temp_pos)
print(f" ✅ README ranks #{readme_pos + 1}, temp file ranks #{temp_pos + 1}")
# 3. Function/code should rank well
function_pos = next(
(i for i, r in enumerate(ranked) if r.chunk_type == "function"), None
)
function_pos = next((i for i, r in enumerate(ranked) if r.chunk_type == 'function'), None)
if function_pos is not None:
self.assertLess(function_pos, len(ranked) // 2) # Should be in top half
print(f" ✅ Function code ranks #{function_pos + 1}")
print(" 🎯 Ranking quality looks good!")
def test_06_zero_overhead_verification(self):
"""
✅ Verify that smart ranking adds zero overhead.
The ranking should only use existing data and lightweight operations.
No additional API calls or expensive operations.
"""
print("\n⚡ Testing zero overhead...")
searcher = MagicMock()
searcher._smart_rerank = CodeSearcher._smart_rerank.__get__(searcher)
import time
# Time the ranking operation
start_time = time.time()
# searcher._smart_rerank(self.mock_results.copy()) # Unused variable removed
ranked = searcher._smart_rerank(self.mock_results.copy())
end_time = time.time()
ranking_time = (end_time - start_time) * 1000 # Convert to milliseconds
print(f" ⏱️ Ranking took {ranking_time:.2f}ms for {len(self.mock_results)} results")
# Should be very fast (< 10ms for small result sets)
self.assertLess(ranking_time, 50) # Very generous upper bound
# Verify no external calls were made (check that we only use existing data)
# This is implicitly tested by the fact that we're using mock objects
print(" ✅ Zero overhead verified - only uses existing result data!")
@ -305,18 +297,18 @@ def run_ranking_tests():
print("=" * 40)
print("Testing the zero-overhead ranking improvements.")
print()
unittest.main(verbosity=2, exit=False)
print("\n" + "=" * 40)
print("💡 Smart Ranking Features:")
print(" • Important files (README, main, config) get 20% boost")
print(" • Recent files (< 1 week) get 10% boost")
print(" • Recent files (< 1 week) get 10% boost")
print(" • Functions/classes get 10% boost")
print(" • Well-structured content gets 2% boost")
print(" • Very short content gets 10% penalty")
print(" • All boosts are cumulative for maximum quality")
if __name__ == "__main__":
run_ranking_tests()
if __name__ == '__main__':
run_ranking_tests()

37
tests/troubleshoot.py
View File

@ -8,22 +8,21 @@ and helps identify what's working and what needs attention.
Run with: python3 tests/troubleshoot.py
"""
import subprocess
import sys
import subprocess
from pathlib import Path
# Add project to path
sys.path.insert(0, str(Path(__file__).parent.parent))
def main():
"""Run comprehensive troubleshooting checks."""
print("🔧 FSS-Mini-RAG Troubleshooting Tool")
print("=" * 50)
print("This tool checks your setup and helps fix common issues.")
print()
# Menu of available tests
print("Available tests:")
print(" 1. Full Ollama Integration Test")
@ -31,21 +30,21 @@ def main():
print(" 3. Basic System Validation")
print(" 4. All Tests (recommended)")
print()
choice = input("Select test (1-4, or Enter for all): ").strip()
if choice == "1" or choice == "" or choice == "4":
print("\n" + "🤖 OLLAMA INTEGRATION TESTS".center(50, "="))
run_test("test_ollama_integration.py")
if choice == "2" or choice == "" or choice == "4":
print("\n" + "🧮 SMART RANKING TESTS".center(50, "="))
run_test("test_smart_ranking.py")
if choice == "3" or choice == "" or choice == "4":
print("\n" + "🔍 SYSTEM VALIDATION TESTS".center(50, "="))
run_test("03_system_validation.py")
print("\n" + "✅ TROUBLESHOOTING COMPLETE".center(50, "="))
print("💡 If you're still having issues:")
print(" • Check docs/QUERY_EXPANSION.md for setup help")
@ -53,37 +52,35 @@ def main():
print(" • Start Ollama server: ollama serve")
print(" • Install models: ollama pull qwen3:4b")
def run_test(test_file):
"""Run a specific test file."""
test_path = Path(__file__).parent / test_file
if not test_path.exists():
print(f"❌ Test file not found: {test_file}")
return
try:
# Run the test
result = subprocess.run(
[sys.executable, str(test_path)], capture_output=True, text=True, timeout=60
)
result = subprocess.run([
sys.executable, str(test_path)
], capture_output=True, text=True, timeout=60)
# Show output
if result.stdout:
print(result.stdout)
if result.stderr:
print("STDERR:", result.stderr)
if result.returncode == 0:
print(f"✅ {test_file} completed successfully!")
else:
print(f"⚠️ {test_file} had some issues (return code: {result.returncode})")
except subprocess.TimeoutExpired:
print(f"⏰ {test_file} timed out after 60 seconds")
except Exception as e:
print(f"❌ Error running {test_file}: {e}")
if __name__ == "__main__":
main()
main()