BobAi/fss-mini-rag-github
7
0
Fork 0
Code Issues 7 Pull Requests 7 Actions Packages Projects Releases Wiki Activity

Improve UX with streaming tokens, fix model references, and add icon integration

Browse Source 
This comprehensive update enhances user experience with several key improvements:

## Enhanced Streaming & Thinking Display
- Implement real-time streaming with gray thinking tokens that collapse after completion
- Fix thinking token redisplay bug with proper content filtering
- Add clear "AI Response:" headers to separate thinking from responses
- Enable streaming by default for better user engagement
- Keep thinking visible for exploration, collapse only for suggested questions

## Natural Conversation Responses
- Convert clunky JSON exploration responses to natural, conversational format
- Improve exploration prompts for friendly, colleague-style interactions
- Update summary generation with better context handling
- Eliminate double response display issues

## Model Reference Updates
- Remove all llama3.2 references in favor of qwen3 models
- Fix non-existent qwen3:3b references, replace with proper model names
- Update model rankings to prioritize working qwen models across all components
- Ensure consistent model recommendations in docs and examples

## Cross-Platform Icon Integration
- Add desktop icon setup to Linux installer with .desktop entry
- Add Windows shortcuts for desktop and Start Menu integration
- Improve installer user experience with visual branding

## Configuration & Navigation Fixes
- Fix "0" option in configuration menu to properly go back
- Improve configuration menu user-friendliness
- Update troubleshooting guides with correct model suggestions

These changes significantly improve the beginner experience while maintaining
technical accuracy and system reliability.
This commit is contained in:
BobAi 2025-08-15 12:20:06 +10:00
parent cc99edde79
commit a84ff94fba
18 changed files with 1280 additions and 327 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/BEGINNER_GLOSSARY.md
View File

@ -117,7 +117,7 @@ def login_user(email, password):
**Models you might see:** **Models you might see:**
- **qwen3:0.6b** - Ultra-fast, good for most questions - **qwen3:0.6b** - Ultra-fast, good for most questions
- **llama3.2** - Slower but more detailed - **qwen3:4b** - Slower but more detailed
- **auto** - Picks the best available model - **auto** - Picks the best available model
--- ---

2
docs/CPU_DEPLOYMENT.md
View File

@ -49,7 +49,7 @@ ollama run qwen3:0.6b "Hello, can you expand this query: authentication"
|-------|------|-----------|---------| |-------|------|-----------|---------|
| qwen3:0.6b | 522MB | Fast ⚡ | Excellent ✅ | | qwen3:0.6b | 522MB | Fast ⚡ | Excellent ✅ |
| qwen3:1.7b | 1.4GB | Medium | Excellent ✅ | | qwen3:1.7b | 1.4GB | Medium | Excellent ✅ |
| qwen3:3b | 2.0GB | Slow | Excellent ✅ | | qwen3:4b | 2.5GB | Slow | Excellent ✅ |
## CPU-Optimized Configuration ## CPU-Optimized Configuration

10
docs/LLM_PROVIDERS.md
View File

@ -22,8 +22,8 @@ This guide shows how to configure FSS-Mini-RAG with different LLM providers for
llm: llm:
provider: ollama provider: ollama
ollama_host: localhost:11434 ollama_host: localhost:11434
synthesis_model: llama3.2 synthesis_model: qwen3:1.7b
expansion_model: llama3.2 expansion_model: qwen3:1.7b
enable_synthesis: false enable_synthesis: false
synthesis_temperature: 0.3 synthesis_temperature: 0.3
cpu_optimized: true cpu_optimized: true
@ -33,13 +33,13 @@ llm:
**Setup:** **Setup:**
1. Install Ollama: `curl -fsSL https://ollama.ai/install.sh | sh` 1. Install Ollama: `curl -fsSL https://ollama.ai/install.sh | sh`
2. Start service: `ollama serve` 2. Start service: `ollama serve`
3. Download model: `ollama pull llama3.2` 3. Download model: `ollama pull qwen3:1.7b`
4. Test: `./rag-mini search /path/to/project "test" --synthesize` 4. Test: `./rag-mini search /path/to/project "test" --synthesize`
**Recommended Models:** **Recommended Models:**
- `qwen3:0.6b` - Ultra-fast, good for CPU-only systems - `qwen3:0.6b` - Ultra-fast, good for CPU-only systems
- `llama3.2` - Balanced quality and speed - `qwen3:1.7b` - Balanced quality and speed (recommended)
- `llama3.1:8b` - Higher quality, needs more RAM - `qwen3:4b` - Higher quality, excellent for most use cases
### LM Studio ### LM Studio

19
docs/QUERY_EXPANSION.md
View File

@ -34,7 +34,24 @@ graph LR
## Configuration ## Configuration
Edit `config.yaml`: ### Easy Configuration (TUI)
Use the interactive Configuration Manager in the TUI:
1. **Start TUI**: `./rag-tui` or `rag.bat` (Windows)
2. **Select Option 6**: Configuration Manager
3. **Choose Option 2**: Toggle query expansion
4. **Follow prompts**: Get explanation and easy on/off toggle
The TUI will:
- Explain benefits and requirements clearly
- Check if Ollama is available
- Show current status (enabled/disabled)
- Save changes automatically
### Manual Configuration (Advanced)
Edit `config.yaml` directly:
```yaml ```yaml
# Search behavior settings # Search behavior settings

4
docs/TROUBLESHOOTING.md
View File

@ -143,8 +143,8 @@ python3 -c "import mini_rag; print('✅ Installation successful')"
2. **Install a model:** 2. **Install a model:**
```bash ```bash
ollama pull qwen3:0.6b # Fast, small model ollama pull qwen2.5:3b # Good balance of speed and quality
# Or: ollama pull llama3.2 # Larger but better # Or: ollama pull qwen3:4b # Larger but better quality
``` ```
3. **Test connection:** 3. **Test connection:**

140
docs/TUI_GUIDE.md
View File

@ -23,8 +23,9 @@ That's it! The TUI will guide you through everything.
### User Flow ### User Flow
1. **Select Project** → Choose directory to search 1. **Select Project** → Choose directory to search
2. **Index Project** → Process files for search 2. **Index Project** → Process files for search
3. **Search Content** → Find what you need 3. **Search Content** → Find what you need quickly
4. **Explore Results** → See full context and files 4. **Explore Project** → Interactive AI-powered discovery (NEW!)
5. **Configure System** → Customize search behavior
## Main Menu Options ## Main Menu Options
@ -110,7 +111,63 @@ That's it! The TUI will guide you through everything.
./rag-mini-enhanced context /path/to/project "login()" ./rag-mini-enhanced context /path/to/project "login()"
``` ```
### 4. View Status ### 4. Explore Project (NEW!)
**Purpose**: Interactive AI-powered discovery with conversation memory
**What Makes Explore Different**:
- **Conversational**: Ask follow-up questions that build on previous answers
- **AI Reasoning**: Uses thinking mode for deeper analysis and explanations
- **Educational**: Perfect for understanding unfamiliar codebases
- **Context Aware**: Remembers what you've already discussed
**Interactive Process**:
1. **First Question Guidance**: Clear prompts with example questions
2. **Starter Suggestions**: Random helpful questions to get you going
3. **Natural Follow-ups**: Ask "why?", "how?", "show me more" naturally
4. **Session Memory**: AI remembers your conversation context
**Explore Mode Features**:
**Quick Start Options**:
- **Option 1 - Help**: Show example questions and explore mode capabilities
- **Option 2 - Status**: Project information and current exploration session
- **Option 3 - Suggest**: Get a random starter question picked from 7 curated examples
**Starter Questions** (randomly suggested):
- "What are the main components of this project?"
- "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"
**Advanced Usage**:
- **Deep Questions**: "Why is this function slow?" "How does the security work?"
- **Code Analysis**: "Explain this algorithm" "What could go wrong here?"
- **Architecture**: "How do these components interact?" "What's the design pattern?"
- **Best Practices**: "Is this code following best practices?" "How would you improve this?"
**What You Learn**:
- **Conversational AI**: How to have productive technical conversations with AI
- **Code Understanding**: Deep analysis capabilities beyond simple search
- **Context Building**: How conversation memory improves over time
- **Question Techniques**: Effective ways to explore unfamiliar code
**CLI Commands Shown**:
```bash
./rag-mini explore /path/to/project # Start interactive exploration
```
**Perfect For**:
- Understanding new codebases
- Code review and analysis
- Learning from existing projects
- Documenting complex systems
- Onboarding new team members
### 5. View Status
**Purpose**: Check system health and project information **Purpose**: Check system health and project information
@ -139,32 +196,61 @@ That's it! The TUI will guide you through everything.
./rag-mini status /path/to/project ./rag-mini status /path/to/project
``` ```
### 5. Configuration ### 6. Configuration Manager (ENHANCED!)
**Purpose**: View and understand system settings **Purpose**: Interactive configuration with user-friendly options
**Configuration Display**: **New Interactive Features**:
- **Current settings** - Chunk size, strategy, file patterns - **Live Configuration Dashboard** - See current settings with clear status
- **File location** - Where config is stored - **Quick Configuration Options** - Change common settings without YAML editing
- **Setting explanations** - What each option does - **Guided Setup** - Explanations and presets for each option
- **Quick actions** - View or edit config directly - **Validation** - Input checking and helpful error messages
**Key Settings Explained**: **Main Configuration Options**:
- **chunking.max_size** - How large each searchable piece is
- **chunking.strategy** - Smart (semantic) vs simple (fixed size)
- **files.exclude_patterns** - Skip certain files/directories
- **embedding.preferred_method** - AI model preference
- **search.default_top_k** - How many results to show
**Interactive Options**: **1. Adjust Chunk Size**:
- **[V]iew config** - See full configuration file - **Presets**: Small (1000), Medium (2000), Large (3000), or custom
- **[E]dit path** - Get command to edit configuration - **Guidance**: Performance vs accuracy explanations
- **Smart Validation**: Range checking and recommendations
**2. Toggle Query Expansion**:
- **Educational Info**: Clear explanation of benefits and requirements
- **Easy Toggle**: Simple on/off with confirmation
- **System Check**: Verifies Ollama availability for AI features
**3. Configure Search Behavior**:
- **Result Count**: Adjust default number of search results (1-100)
- **BM25 Toggle**: Enable/disable keyword matching boost
- **Similarity Threshold**: Fine-tune match sensitivity (0.0-1.0)
**4. View/Edit Configuration File**:
- **Full File Viewer**: Display complete config with syntax highlighting
- **Editor Instructions**: Commands for nano, vim, VS Code
- **YAML Help**: Format explanation and editing tips
**5. Reset to Defaults**:
- **Safe Reset**: Confirmation before resetting all settings
- **Clear Explanations**: Shows what defaults will be restored
- **Backup Reminder**: Suggests saving current config first
**6. Advanced Settings**:
- **File Filtering**: Min file size, exclude patterns (view only)
- **Performance Settings**: Batch sizes, streaming thresholds
- **LLM Preferences**: Model rankings and selection priorities
**Key Settings Dashboard**:
- 📁 **Chunk size**: 2000 characters (with emoji indicators)
- 🧠 **Chunking strategy**: semantic
- 🔍 **Search results**: 10 results
- 📊 **Embedding method**: ollama
- 🚀 **Query expansion**: enabled/disabled
- ⚡ **LLM synthesis**: enabled/disabled
**What You Learn**: **What You Learn**:
- How configuration affects search quality - **Configuration Impact**: How settings affect search quality and speed
- YAML configuration format - **Interactive YAML**: Easier than manual editing for beginners
- Which settings to adjust for different projects - **Best Practices**: Recommended settings for different project types
- Where to find advanced options - **System Understanding**: How all components work together
**CLI Commands Shown**: **CLI Commands Shown**:
```bash ```bash
@ -172,7 +258,13 @@ cat /path/to/project/.mini-rag/config.yaml # View config
nano /path/to/project/.mini-rag/config.yaml # Edit config nano /path/to/project/.mini-rag/config.yaml # Edit config
``` ```
### 6. CLI Command Reference **Perfect For**:
- Beginners who find YAML intimidating
- Quick adjustments without memorizing syntax
- Understanding what each setting actually does
- Safe experimentation with guided validation
### 7. CLI Command Reference
**Purpose**: Complete command reference for transitioning to CLI **Purpose**: Complete command reference for transitioning to CLI

6
examples/config-llm-providers.yaml
View File

@ -68,9 +68,9 @@ search:
llm: llm:
provider: ollama # Use local Ollama provider: ollama # Use local Ollama
ollama_host: localhost:11434 # Default Ollama location ollama_host: localhost:11434 # Default Ollama location
synthesis_model: llama3.2 # Good all-around model synthesis_model: qwen3:1.7b # Good all-around model
# alternatives: qwen3:0.6b (faster), llama3.2:3b (balanced), llama3.1:8b (quality) # alternatives: qwen3:0.6b (faster), qwen2.5:3b (balanced), qwen3:4b (quality)
expansion_model: llama3.2 expansion_model: qwen3:1.7b
enable_synthesis: false enable_synthesis: false
synthesis_temperature: 0.3 synthesis_temperature: 0.3
cpu_optimized: true cpu_optimized: true

2
examples/config-quality.yaml
View File

@ -102,7 +102,7 @@ llm:
# For even better results, try these model combinations: # For even better results, try these model combinations:
# • ollama pull nomic-embed-text:latest (best embeddings) # • ollama pull nomic-embed-text:latest (best embeddings)
# • ollama pull qwen3:1.7b (good general model) # • ollama pull qwen3:1.7b (good general model)
# • ollama pull llama3.2 (excellent for analysis) # • ollama pull qwen3:4b (excellent for analysis)
# #
# Or adjust these settings for your specific needs: # Or adjust these settings for your specific needs:
# • similarity_threshold: 0.3 (more selective results) # • similarity_threshold: 0.3 (more selective results)

2
examples/config.yaml
View File

@ -112,7 +112,7 @@ llm:
synthesis_model: auto # Which AI model to use for explanations synthesis_model: auto # Which AI model to use for explanations
# 'auto': Picks best available model - RECOMMENDED # 'auto': Picks best available model - RECOMMENDED
# 'qwen3:0.6b': Ultra-fast, good for CPU-only computers # 'qwen3:0.6b': Ultra-fast, good for CPU-only computers
# 'llama3.2': Slower but more detailed explanations # 'qwen3:4b': Slower but more detailed explanations
expansion_model: auto # Model for query expansion (usually same as synthesis) expansion_model: auto # Model for query expansion (usually same as synthesis)

70
install_mini_rag.sh
View File

@ -462,6 +462,73 @@ install_dependencies() {
fi fi
} }
# Setup application icon for desktop integration
setup_desktop_icon() {
print_header "Setting Up Desktop Integration"
# Check if we're in a GUI environment
if [ -z "$DISPLAY" ] && [ -z "$WAYLAND_DISPLAY" ]; then
print_info "No GUI environment detected - skipping desktop integration"
return 0
fi
local icon_source="$SCRIPT_DIR/assets/Fss_Mini_Rag.png"
local desktop_dir="$HOME/.local/share/applications"
local icon_dir="$HOME/.local/share/icons"
# Check if icon file exists
if [ ! -f "$icon_source" ]; then
print_warning "Icon file not found at $icon_source"
return 1
fi
# Create directories if needed
mkdir -p "$desktop_dir" "$icon_dir" 2>/dev/null
# Copy icon to standard location
local icon_dest="$icon_dir/fss-mini-rag.png"
if cp "$icon_source" "$icon_dest" 2>/dev/null; then
print_success "Icon installed to $icon_dest"
else
print_warning "Could not install icon (permissions?)"
return 1
fi
# Create desktop entry
local desktop_file="$desktop_dir/fss-mini-rag.desktop"
cat > "$desktop_file" << EOF
[Desktop Entry]
Name=FSS-Mini-RAG
Comment=Fast Semantic Search for Code and Documents
Exec=$SCRIPT_DIR/rag-tui
Icon=fss-mini-rag
Terminal=true
Type=Application
Categories=Development;Utility;TextEditor;
Keywords=search;code;rag;semantic;ai;
StartupNotify=true
EOF
if [ -f "$desktop_file" ]; then
chmod +x "$desktop_file"
print_success "Desktop entry created"
# Update desktop database if available
if command_exists update-desktop-database; then
update-desktop-database "$desktop_dir" 2>/dev/null
print_info "Desktop database updated"
fi
print_info "✨ FSS-Mini-RAG should now appear in your application menu!"
print_info " Look for it in Development or Utility categories"
else
print_warning "Could not create desktop entry"
return 1
fi
return 0
}
# Setup ML models based on configuration # Setup ML models based on configuration
setup_ml_models() { setup_ml_models() {
if [ "$INSTALL_TYPE" != "full" ]; then if [ "$INSTALL_TYPE" != "full" ]; then
@ -794,6 +861,9 @@ main() {
fi fi
setup_ml_models setup_ml_models
# Setup desktop integration with icon
setup_desktop_icon
if test_installation; then if test_installation; then
show_completion show_completion
else else

335
install_windows.bat
View File

@ -1,124 +1,343 @@
@echo off @echo off
REM FSS-Mini-RAG Windows Installer - Simple & Reliable REM FSS-Mini-RAG Windows Installer - Beautiful & Comprehensive
setlocal enabledelayedexpansion
REM Enable colors and unicode for modern Windows
chcp 65001 >nul 2>&1
echo. echo.
echo =================================================== echo ╔══════════════════════════════════════════════════╗
echo FSS-Mini-RAG Windows Setup echo ║ FSS-Mini-RAG Windows Installer ║
echo =================================================== echo ║ Fast Semantic Search for Code ║
echo ╚══════════════════════════════════════════════════╝
echo. echo.
echo 🚀 Comprehensive installation process:
echo • Python environment setup and validation
echo • Smart dependency management
echo • Optional AI model downloads (with your consent)
echo • System testing and verification
echo • Interactive tutorial (optional)
echo.
echo 💡 Note: You'll be asked before downloading any models
echo.
set /p "continue=Begin installation? [Y/n]: "
if /i "!continue!"=="n" (
echo Installation cancelled.
pause
exit /b 0
)
REM Get script directory REM Get script directory
set "SCRIPT_DIR=%~dp0" set "SCRIPT_DIR=%~dp0"
set "SCRIPT_DIR=%SCRIPT_DIR:~0,-1%" set "SCRIPT_DIR=%SCRIPT_DIR:~0,-1%"
echo [1/4] Checking Python... echo.
echo ══════════════════════════════════════════════════
echo [1/5] Checking Python Environment...
python --version >nul 2>&1 python --version >nul 2>&1
if errorlevel 1 ( if errorlevel 1 (
echo ERROR: Python not found! echo ❌ ERROR: Python not found!
echo. echo.
echo Please install Python from: https://python.org/downloads echo 📦 Please install Python from: https://python.org/downloads
echo Make sure to check "Add Python to PATH" during installation echo 🔧 Installation requirements:
echo • Python 3.8 or higher
echo • Make sure to check "Add Python to PATH" during installation
echo • Restart your command prompt after installation
echo.
echo 💡 Quick install options:
echo • Download from python.org (recommended)
echo • Or use: winget install Python.Python.3.11
echo • Or use: choco install python311
echo. echo.
pause pause
exit /b 1 exit /b 1
) )
for /f "tokens=2" %%i in ('python --version 2^>^&1') do set "PYTHON_VERSION=%%i" for /f "tokens=2" %%i in ('python --version 2^>^&1') do set "PYTHON_VERSION=%%i"
echo Found Python %PYTHON_VERSION% echo ✅ Found Python !PYTHON_VERSION!
echo. REM Check Python version (basic check for 3.x)
echo [2/4] Creating virtual environment... for /f "tokens=1 delims=." %%a in ("!PYTHON_VERSION!") do set "MAJOR_VERSION=%%a"
if exist "%SCRIPT_DIR%\.venv" ( if !MAJOR_VERSION! LSS 3 (
echo Removing old virtual environment... echo ❌ ERROR: Python !PYTHON_VERSION! found, but Python 3.8+ required
rmdir /s /q "%SCRIPT_DIR%\.venv" 2>nul echo 📦 Please upgrade Python to 3.8 or higher
pause
exit /b 1
) )
echo.
echo ══════════════════════════════════════════════════
echo [2/5] Creating Python Virtual Environment...
if exist "%SCRIPT_DIR%\.venv" (
echo 🔄 Removing old virtual environment...
rmdir /s /q "%SCRIPT_DIR%\.venv" 2>nul
if exist "%SCRIPT_DIR%\.venv" (
echo ⚠️ Could not remove old environment, creating anyway...
)
)
echo 📁 Creating fresh virtual environment...
python -m venv "%SCRIPT_DIR%\.venv" python -m venv "%SCRIPT_DIR%\.venv"
if errorlevel 1 ( if errorlevel 1 (
echo ERROR: Failed to create virtual environment echo ❌ ERROR: Failed to create virtual environment
echo.
echo 🔧 This might be because:
echo • Python venv module is not installed
echo • Insufficient permissions
echo • Path contains special characters
echo.
echo 💡 Try: python -m pip install --user virtualenv
pause pause
exit /b 1 exit /b 1
) )
echo Virtual environment created successfully echo ✅ Virtual environment created successfully
echo. echo.
echo [3/4] Installing dependencies... echo ══════════════════════════════════════════════════
echo This may take a few minutes... echo [3/5] Installing Python Dependencies...
echo 📦 This may take 2-3 minutes depending on your internet speed...
echo.
call "%SCRIPT_DIR%\.venv\Scripts\activate.bat" call "%SCRIPT_DIR%\.venv\Scripts\activate.bat"
if errorlevel 1 (
echo ❌ ERROR: Could not activate virtual environment
pause
exit /b 1
)
echo 🔧 Upgrading pip...
"%SCRIPT_DIR%\.venv\Scripts\python.exe" -m pip install --upgrade pip --quiet "%SCRIPT_DIR%\.venv\Scripts\python.exe" -m pip install --upgrade pip --quiet
if errorlevel 1 (
echo ⚠️ Warning: Could not upgrade pip, continuing anyway...
)
echo 📚 Installing core dependencies (lancedb, pandas, numpy, etc.)...
echo This provides semantic search capabilities
"%SCRIPT_DIR%\.venv\Scripts\pip.exe" install -r "%SCRIPT_DIR%\requirements.txt" "%SCRIPT_DIR%\.venv\Scripts\pip.exe" install -r "%SCRIPT_DIR%\requirements.txt"
if errorlevel 1 ( if errorlevel 1 (
echo ERROR: Failed to install dependencies echo ❌ ERROR: Failed to install dependencies
echo.
echo 🔧 Possible solutions:
echo • Check internet connection
echo • Try running as administrator
echo • Check if antivirus is blocking pip
echo • Manually run: pip install -r requirements.txt
echo.
pause pause
exit /b 1 exit /b 1
) )
echo Dependencies installed successfully echo ✅ Dependencies installed successfully
echo. echo.
echo [4/4] Testing installation... echo ══════════════════════════════════════════════════
"%SCRIPT_DIR%\.venv\Scripts\python.exe" -c "from mini_rag import CodeEmbedder; print('Import test: OK')" 2>nul echo [4/5] Testing Installation...
echo 🧪 Verifying Python imports...
"%SCRIPT_DIR%\.venv\Scripts\python.exe" -c "from mini_rag import CodeEmbedder, ProjectIndexer, CodeSearcher; print('✅ Core imports successful')" 2>nul
if errorlevel 1 ( if errorlevel 1 (
echo ERROR: Installation test failed echo ❌ ERROR: Installation test failed
echo.
echo 🔧 This usually means:
echo • Dependencies didn't install correctly
echo • Virtual environment is corrupted
echo • Python path issues
echo.
echo 💡 Try running: pip install -r requirements.txt
pause pause
exit /b 1 exit /b 1
) )
echo 🔍 Testing embedding system...
"%SCRIPT_DIR%\.venv\Scripts\python.exe" -c "from mini_rag import CodeEmbedder; embedder = CodeEmbedder(); info = embedder.get_embedding_info(); print(f'✅ Embedding method: {info[\"method\"]}')" 2>nul
if errorlevel 1 (
echo ⚠️ Warning: Embedding test inconclusive, but core system is ready
)
echo. echo.
echo =================================================== echo ══════════════════════════════════════════════════
echo INSTALLATION SUCCESSFUL! echo [5/6] Setting Up Desktop Integration...
echo =================================================== call :setup_windows_icon
echo. echo.
echo Quick start: echo ══════════════════════════════════════════════════
echo rag.bat - Interactive interface echo [6/6] Checking AI Features (Optional)...
call :check_ollama_enhanced
echo.
echo ╔══════════════════════════════════════════════════╗
echo ║ INSTALLATION SUCCESSFUL! ║
echo ╚══════════════════════════════════════════════════╝
echo.
echo 🎯 Quick Start Options:
echo.
echo 🎨 For Beginners (Recommended):
echo rag.bat - Interactive interface with guided setup
echo.
echo 💻 For Developers:
echo rag.bat index C:\myproject - Index a project
echo rag.bat search C:\myproject "authentication" - Search project
echo rag.bat help - Show all commands echo rag.bat help - Show all commands
echo. echo.
REM Check for Ollama and offer model setup REM Offer interactive tutorial
call :check_ollama echo 🧪 Quick Test Available:
echo Test FSS-Mini-RAG with a small sample project (takes ~30 seconds)
echo. echo.
echo Setup complete! FSS-Mini-RAG is ready to use. set /p "run_test=Run interactive tutorial now? [Y/n]: "
set /p choice="Press Enter to continue or 'test' to run quick test: " if /i "!run_test!" NEQ "n" (
if /i "%choice%"=="test" ( call :run_tutorial
echo. ) else (
echo Running quick test... echo 📚 You can run the tutorial anytime with: rag.bat
call "%SCRIPT_DIR%\.venv\Scripts\activate.bat"
"%SCRIPT_DIR%\.venv\Scripts\python.exe" rag-mini.py index . --force
if not errorlevel 1 (
"%SCRIPT_DIR%\.venv\Scripts\python.exe" rag-mini.py search . "embedding" --top-k 3
)
) )
echo.
echo 🎉 Setup complete! FSS-Mini-RAG is ready to use.
echo 💡 Pro tip: Try indexing any folder with text files - code, docs, notes!
echo. echo.
pause pause
exit /b 0 exit /b 0
:check_ollama :check_ollama_enhanced
echo 🤖 Checking for AI capabilities...
echo. echo.
echo Checking for AI features...
REM Simple Ollama check REM Check if Ollama is installed
where ollama >nul 2>&1
if errorlevel 1 (
echo ⚠️ Ollama not installed - using basic search mode
echo.
echo 🎯 For Enhanced AI Features:
echo • 📥 Install Ollama: https://ollama.com/download
echo • 🔄 Run: ollama serve
echo • 🧠 Download model: ollama pull qwen3:1.7b
echo.
echo 💡 Benefits of AI features:
echo • Smart query expansion for better search results
echo • Interactive exploration mode with conversation memory
echo • AI-powered synthesis of search results
echo • Natural language understanding of your questions
echo.
goto :eof
)
REM Check if Ollama server is running
curl -s http://localhost:11434/api/version >nul 2>&1 curl -s http://localhost:11434/api/version >nul 2>&1
if errorlevel 1 ( if errorlevel 1 (
echo Ollama not detected - basic search mode available echo 🟡 Ollama installed but not running
echo. echo.
echo For AI features (synthesis, exploration): set /p "start_ollama=Start Ollama server now? [Y/n]: "
echo 1. Install Ollama: https://ollama.com/download if /i "!start_ollama!" NEQ "n" (
echo 2. Run: ollama serve echo 🚀 Starting Ollama server...
echo 3. Run: ollama pull qwen3:1.7b start /b ollama serve
return timeout /t 3 /nobreak >nul
curl -s http://localhost:11434/api/version >nul 2>&1
if errorlevel 1 (
echo ⚠️ Could not start Ollama automatically
echo 💡 Please run: ollama serve
) else (
echo ✅ Ollama server started successfully!
)
)
) else (
echo ✅ Ollama server is running!
) )
echo Ollama detected! REM Check for available models
echo 🔍 Checking for AI models...
REM Check for any LLM models
ollama list 2>nul | findstr /v "NAME" | findstr /v "^$" >nul ollama list 2>nul | findstr /v "NAME" | findstr /v "^$" >nul
if errorlevel 1 ( if errorlevel 1 (
echo No LLM models found echo 📦 No AI models found
echo. echo.
echo Recommended: ollama pull qwen3:1.7b echo 🧠 Recommended Models (choose one):
echo This enables AI synthesis and exploration features echo • qwen3:1.7b - Excellent for RAG (1.4GB, recommended)
echo • qwen3:0.6b - Lightweight and fast (~500MB)
echo • qwen3:4b - Higher quality but slower (~2.5GB)
echo.
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
ollama pull qwen3:1.7b
if errorlevel 1 (
echo ⚠️ Download failed - you can try again later with: ollama pull qwen3:1.7b
) else ( ) else (
echo LLM models found - AI features available! echo ✅ Model downloaded successfully! AI features are now available.
) )
return )
) else (
echo ✅ AI models found - full AI features available!
echo 🎉 Your system supports query expansion, exploration mode, and synthesis!
)
goto :eof
:run_tutorial
echo.
echo ═══════════════════════════════════════════════════
echo 🧪 Running Interactive Tutorial
echo ═══════════════════════════════════════════════════
echo.
echo 📚 This tutorial will:
echo • Index the FSS-Mini-RAG documentation
echo • Show you how to search effectively
echo • Demonstrate AI features (if available)
echo.
call "%SCRIPT_DIR%\.venv\Scripts\activate.bat"
echo 📁 Indexing project for demonstration...
"%SCRIPT_DIR%\.venv\Scripts\python.exe" rag-mini.py index "%SCRIPT_DIR%" >nul 2>&1
if errorlevel 1 (
echo ❌ Indexing failed - please check the installation
goto :eof
)
echo ✅ Indexing complete!
echo.
echo 🔍 Example search: "embedding"
"%SCRIPT_DIR%\.venv\Scripts\python.exe" rag-mini.py search "%SCRIPT_DIR%" "embedding" --top-k 3
echo.
echo 🎯 Try the interactive interface:
echo rag.bat
echo.
echo 💡 You can now search any project by indexing it first!
goto :eof
:setup_windows_icon
echo 🎨 Setting up application icon and shortcuts...
REM Check if icon exists
if not exist "%SCRIPT_DIR%\assets\Fss_Mini_Rag.png" (
echo ⚠️ Icon file not found - skipping desktop integration
goto :eof
)
REM Create desktop shortcut
echo 📱 Creating desktop shortcut...
set "desktop=%USERPROFILE%\Desktop"
set "shortcut=%desktop%\FSS-Mini-RAG.lnk"
REM Use PowerShell to create shortcut with icon
powershell -Command "& {$WshShell = New-Object -comObject WScript.Shell; $Shortcut = $WshShell.CreateShortcut('%shortcut%'); $Shortcut.TargetPath = '%SCRIPT_DIR%\rag.bat'; $Shortcut.WorkingDirectory = '%SCRIPT_DIR%'; $Shortcut.Description = 'FSS-Mini-RAG - Fast Semantic Search'; $Shortcut.Save()}" >nul 2>&1
if exist "%shortcut%" (
echo ✅ Desktop shortcut created
) else (
echo ⚠️ Could not create desktop shortcut
)
REM Create Start Menu shortcut
echo 📂 Creating Start Menu entry...
set "startmenu=%APPDATA%\Microsoft\Windows\Start Menu\Programs"
set "startshortcut=%startmenu%\FSS-Mini-RAG.lnk"
powershell -Command "& {$WshShell = New-Object -comObject WScript.Shell; $Shortcut = $WshShell.CreateShortcut('%startshortcut%'); $Shortcut.TargetPath = '%SCRIPT_DIR%\rag.bat'; $Shortcut.WorkingDirectory = '%SCRIPT_DIR%'; $Shortcut.Description = 'FSS-Mini-RAG - Fast Semantic Search'; $Shortcut.Save()}" >nul 2>&1
if exist "%startshortcut%" (
echo ✅ Start Menu entry created
) else (
echo ⚠️ Could not create Start Menu entry
)
echo 💡 FSS-Mini-RAG shortcuts have been created on your Desktop and Start Menu
echo You can now launch the application from either location
goto :eof

4
mini_rag/config.py
View File

@ -104,9 +104,9 @@ class LLMConfig:
# Recommended model (excellent quality but larger) # Recommended model (excellent quality but larger)
"qwen3:4b", "qwen3:4b",
# Common fallbacks (only include models we know exist) # Common fallbacks (prioritize Qwen models)
"llama3.2:1b",
"qwen2.5:1.5b", "qwen2.5:1.5b",
"qwen2.5:3b",
] ]

117
mini_rag/explorer.py
View File

@ -115,12 +115,13 @@ class CodeExplorer:
# Add to conversation history # Add to conversation history
self.current_session.add_exchange(question, results, synthesis) self.current_session.add_exchange(question, results, synthesis)
# Format response with exploration context # Streaming already displayed the response
response = self._format_exploration_response( # Just return minimal status for caller
question, synthesis, len(results), search_time, synthesis_time session_duration = time.time() - self.current_session.started_at
) exchange_count = len(self.current_session.conversation_history)
return response 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: def _build_contextual_prompt(self, question: str, results: List[Any]) -> str:
"""Build a prompt that includes conversation context.""" """Build a prompt that includes conversation context."""
@ -185,33 +186,22 @@ CURRENT QUESTION: "{question}"
RELEVANT INFORMATION FOUND: RELEVANT INFORMATION FOUND:
{results_text} {results_text}
Please provide a helpful analysis in JSON format: Please provide a helpful, natural explanation that answers their question. Write as if you're having a friendly conversation with a colleague who's exploring this project.
{{ Structure your response to include:
"summary": "Clear explanation of what you found and how it answers their question", 1. A clear explanation of what you found and how it answers their question
"key_points": [ 2. The most important insights from the information you discovered
"Most important insight from the information", 3. Relevant examples or code patterns when helpful
"Secondary important point or relationship", 4. Practical next steps they could take
"Third key point or practical consideration"
],
"code_examples": [
"Relevant example or pattern from the information",
"Another useful example or demonstration"
],
"suggested_actions": [
"Specific next step they could take",
"Additional exploration or investigation suggestion",
"Practical way to apply this information"
],
"confidence": 0.85
}}
Guidelines: Guidelines:
- Be educational and break things down clearly - Write in a conversational, friendly tone
- Be educational but not condescending
- Reference specific files and information when helpful - Reference specific files and information when helpful
- Give practical, actionable suggestions - Give practical, actionable suggestions
- Keep explanations beginner-friendly but not condescending - Connect everything back to their original question
- Connect information to their question directly - Use natural language, not structured formats
- Break complex topics into understandable pieces
""" """
return prompt return prompt
@ -219,16 +209,12 @@ Guidelines:
def _synthesize_with_context(self, prompt: str, results: List[Any]) -> SynthesisResult: def _synthesize_with_context(self, prompt: str, results: List[Any]) -> SynthesisResult:
"""Synthesize results with full context and thinking.""" """Synthesize results with full context and thinking."""
try: try:
# TEMPORARILY: Use simple non-streaming call to avoid flow issues # Use streaming with thinking visible (don't collapse)
# TODO: Re-enable streaming once flow is stable response = self.synthesizer._call_ollama(prompt, temperature=0.2, disable_thinking=False, use_streaming=True, collapse_thinking=False)
response = self.synthesizer._call_ollama(prompt, temperature=0.2, disable_thinking=False)
thinking_stream = "" thinking_stream = ""
# Display simple thinking indicator # Streaming already shows thinking and response
if response and len(response) > 200: # No need for additional indicators
print("\n💭 Analysis in progress...")
# Don't display thinking stream again - keeping it simple for now
if not response: if not response:
return SynthesisResult( return SynthesisResult(
@ -239,39 +225,13 @@ Guidelines:
confidence=0.0 confidence=0.0
) )
# Parse the structured response # Use natural language response directly
try:
# Extract JSON from response
start_idx = response.find('{')
end_idx = response.rfind('}') + 1
if start_idx >= 0 and end_idx > start_idx:
json_str = response[start_idx:end_idx]
data = json.loads(json_str)
return SynthesisResult( return SynthesisResult(
summary=data.get('summary', 'Analysis completed'), summary=response.strip(),
key_points=data.get('key_points', []), key_points=[], # Not used with natural language responses
code_examples=data.get('code_examples', []), code_examples=[], # Not used with natural language responses
suggested_actions=data.get('suggested_actions', []), suggested_actions=[], # Not used with natural language responses
confidence=float(data.get('confidence', 0.7)) confidence=0.85 # High confidence for natural responses
)
else:
# Fallback: use raw response as summary
return SynthesisResult(
summary=response[:400] + '...' if len(response) > 400 else response,
key_points=[],
code_examples=[],
suggested_actions=[],
confidence=0.5
)
except json.JSONDecodeError:
return SynthesisResult(
summary="Analysis completed but format parsing failed",
key_points=[],
code_examples=[],
suggested_actions=["Try rephrasing your question"],
confidence=0.3
) )
except Exception as e: except Exception as e:
@ -300,27 +260,10 @@ Guidelines:
output.append("=" * 60) output.append("=" * 60)
output.append("") output.append("")
# Main analysis # Response was already displayed via streaming
output.append(f"📝 Analysis:") # Just show completion status
output.append(f" {synthesis.summary}") output.append("✅ Analysis complete")
output.append("") output.append("")
if synthesis.key_points:
output.append("🔍 Key Insights:")
for point in synthesis.key_points:
output.append(f" • {point}")
output.append("")
if synthesis.code_examples:
output.append("💡 Code Examples:")
for example in synthesis.code_examples:
output.append(f" {example}")
output.append("")
if synthesis.suggested_actions:
output.append("🎯 Next Steps:")
for action in synthesis.suggested_actions:
output.append(f" • {action}")
output.append("") output.append("")
# Confidence and context indicator # Confidence and context indicator

4
mini_rag/llm_safeguards.py
View File

@ -195,7 +195,7 @@ class ModelRunawayDetector:
• Try a more specific question • Try a more specific question
• Break complex questions into smaller parts • Break complex questions into smaller parts
• Use exploration mode which handles context better: `rag-mini explore` • Use exploration mode which handles context better: `rag-mini explore`
• Consider: A larger model (qwen3:1.7b or qwen3:3b) would help""" • Consider: A larger model (qwen3:1.7b or qwen3:4b) would help"""
def _explain_thinking_loop(self) -> str: def _explain_thinking_loop(self) -> str:
return """🧠 The AI got caught in a "thinking loop" - overthinking the response. return """🧠 The AI got caught in a "thinking loop" - overthinking the response.
@ -266,7 +266,7 @@ class ModelRunawayDetector:
# Universal suggestions # Universal suggestions
suggestions.extend([ suggestions.extend([
"Consider using a larger model if available (qwen3:1.7b or qwen3:3b)", "Consider using a larger model if available (qwen3:1.7b or qwen3:4b)",
"Check model status: `ollama list`" "Check model status: `ollama list`"
]) ])

134
mini_rag/llm_synthesizer.py
View File

@ -72,8 +72,8 @@ class LLMSynthesizer:
else: else:
# Fallback rankings if no config # Fallback rankings if no config
model_rankings = [ model_rankings = [
"qwen3:1.7b", "qwen3:0.6b", "qwen3:4b", "llama3.2:1b", "qwen3:1.7b", "qwen3:0.6b", "qwen3:4b", "qwen2.5:3b",
"qwen2.5:1.5b", "qwen3:3b", "qwen2.5-coder:1.5b" "qwen2.5:1.5b", "qwen2.5-coder:1.5b"
] ]
# Find first available model from our ranked list (exact matches first) # Find first available model from our ranked list (exact matches first)
@ -119,7 +119,7 @@ class LLMSynthesizer:
self._ensure_initialized() self._ensure_initialized()
return len(self.available_models) > 0 return len(self.available_models) > 0
def _call_ollama(self, prompt: str, temperature: float = 0.3, disable_thinking: bool = False, use_streaming: bool = False) -> Optional[str]: def _call_ollama(self, prompt: str, temperature: float = 0.3, disable_thinking: bool = False, use_streaming: bool = True, collapse_thinking: bool = True) -> Optional[str]:
"""Make a call to Ollama API with safeguards.""" """Make a call to Ollama API with safeguards."""
start_time = time.time() start_time = time.time()
@ -181,9 +181,9 @@ class LLMSynthesizer:
} }
} }
# Handle streaming with early stopping # Handle streaming with thinking display
if use_streaming: if use_streaming:
return self._handle_streaming_with_early_stop(payload, model_to_use, use_thinking, start_time) return self._handle_streaming_with_thinking_display(payload, model_to_use, use_thinking, start_time, collapse_thinking)
response = requests.post( response = requests.post(
f"{self.ollama_url}/api/generate", f"{self.ollama_url}/api/generate",
@ -284,6 +284,130 @@ This is normal with smaller AI models and helps ensure you get quality responses
This is normal with smaller AI models and helps ensure you get quality responses.""" This is normal with smaller AI models and helps ensure you get quality responses."""
def _handle_streaming_with_thinking_display(self, payload: dict, model_name: str, use_thinking: bool, start_time: float, collapse_thinking: bool = True) -> Optional[str]:
"""Handle streaming response with real-time thinking token display."""
import json
import sys
try:
response = requests.post(
f"{self.ollama_url}/api/generate",
json=payload,
stream=True,
timeout=65
)
if response.status_code != 200:
logger.error(f"Ollama API error: {response.status_code}")
return None
full_response = ""
thinking_content = ""
is_in_thinking = False
is_thinking_complete = False
thinking_lines_printed = 0
# ANSI escape codes for colors and cursor control
GRAY = '\033[90m' # Dark gray for thinking
LIGHT_GRAY = '\033[37m' # Light gray alternative
RESET = '\033[0m' # Reset color
CLEAR_LINE = '\033[2K' # Clear entire line
CURSOR_UP = '\033[A' # Move cursor up one line
print(f"\n💭 {GRAY}Thinking...{RESET}", flush=True)
for line in response.iter_lines():
if line:
try:
chunk_data = json.loads(line.decode('utf-8'))
chunk_text = chunk_data.get('response', '')
if chunk_text:
full_response += chunk_text
# Handle thinking tokens
if use_thinking and '<think>' in chunk_text:
is_in_thinking = True
chunk_text = chunk_text.replace('<think>', '')
if is_in_thinking and '</think>' in chunk_text:
is_in_thinking = False
is_thinking_complete = True
chunk_text = chunk_text.replace('</think>', '')
if collapse_thinking:
# Clear thinking content and show completion
# Move cursor up to clear thinking lines
for _ in range(thinking_lines_printed + 1):
print(f"{CURSOR_UP}{CLEAR_LINE}", end='', flush=True)
print(f"💭 {GRAY}Thinking complete ✓{RESET}", flush=True)
thinking_lines_printed = 0
else:
# Keep thinking visible, just show completion
print(f"\n💭 {GRAY}Thinking complete ✓{RESET}", flush=True)
print("🤖 AI Response:", flush=True)
continue
# Display thinking content in gray with better formatting
if is_in_thinking and chunk_text.strip():
thinking_content += chunk_text
# Handle line breaks and word wrapping properly
if ' ' in chunk_text or '\n' in chunk_text or len(thinking_content) > 100:
# Split by sentences for better readability
sentences = thinking_content.replace('\n', ' ').split('. ')
for sentence in sentences[:-1]: # Process complete sentences
sentence = sentence.strip()
if sentence:
# Word wrap long sentences
words = sentence.split()
line = ""
for word in words:
if len(line + " " + word) > 70:
if line:
print(f"{GRAY} {line.strip()}{RESET}", flush=True)
thinking_lines_printed += 1
line = word
else:
line += " " + word if line else word
if line.strip():
print(f"{GRAY} {line.strip()}.{RESET}", flush=True)
thinking_lines_printed += 1
# Keep the last incomplete sentence for next iteration
thinking_content = sentences[-1] if sentences else ""
# Display regular response content (skip any leftover thinking)
elif not is_in_thinking and is_thinking_complete and chunk_text.strip():
# Filter out any remaining thinking tags that might leak through
clean_text = chunk_text
if '<think>' in clean_text or '</think>' in clean_text:
clean_text = clean_text.replace('<think>', '').replace('</think>', '')
if clean_text.strip():
print(clean_text, end='', flush=True)
# Check if response is done
if chunk_data.get('done', False):
print() # Final newline
break
except json.JSONDecodeError:
continue
except Exception as e:
logger.error(f"Error processing stream chunk: {e}")
continue
return full_response
except Exception as e:
logger.error(f"Streaming failed: {e}")
return None
def _handle_streaming_with_early_stop(self, payload: dict, model_name: str, use_thinking: bool, start_time: float) -> Optional[str]: def _handle_streaming_with_early_stop(self, payload: dict, model_name: str, use_thinking: bool, start_time: float) -> Optional[str]:
"""Handle streaming response with intelligent early stopping.""" """Handle streaming response with intelligent early stopping."""
import json import json

4
mini_rag/query_expander.py
View File

@ -170,8 +170,8 @@ Expanded query:"""
# Use same model rankings as main synthesizer for consistency # Use same model rankings as main synthesizer for consistency
expansion_preferences = [ expansion_preferences = [
"qwen3:1.7b", "qwen3:0.6b", "qwen3:4b", "llama3.2:1b", "qwen3:1.7b", "qwen3:0.6b", "qwen3:4b", "qwen2.5:3b",
"qwen2.5:1.5b", "qwen3:3b", "qwen2.5-coder:1.5b" "qwen2.5:1.5b", "qwen2.5-coder:1.5b"
] ]
for preferred in expansion_preferences: for preferred in expansion_preferences:

81
rag-mini.py
View File

@ -142,8 +142,8 @@ def search_project(project_path: Path, query: str, top_k: int = 10, synthesize:
print(" • Search for file types: \"python class\" or \"javascript function\"") print(" • Search for file types: \"python class\" or \"javascript function\"")
print() print()
print("⚙️ Configuration adjustments:") print("⚙️ Configuration adjustments:")
print(f" • Lower threshold: ./rag-mini search {project_path} \"{query}\" --threshold 0.05") print(f" • Lower threshold: ./rag-mini search \"{project_path}\" \"{query}\" --threshold 0.05")
print(" • More results: add --top-k 20") print(f" • More results: ./rag-mini search \"{project_path}\" \"{query}\" --top-k 20")
print() print()
print("📚 Need help? See: docs/TROUBLESHOOTING.md") print("📚 Need help? See: docs/TROUBLESHOOTING.md")
return return
@ -201,7 +201,7 @@ def search_project(project_path: Path, query: str, top_k: int = 10, synthesize:
else: else:
print("❌ LLM synthesis unavailable") print("❌ LLM synthesis unavailable")
print(" • Ensure Ollama is running: ollama serve") print(" • Ensure Ollama is running: ollama serve")
print(" • Install a model: ollama pull llama3.2") print(" • Install a model: ollama pull qwen3:1.7b")
print(" • Check connection to http://localhost:11434") print(" • Check connection to http://localhost:11434")
# Save last search for potential enhancements # Save last search for potential enhancements
@ -317,11 +317,26 @@ def explore_interactive(project_path: Path):
if not explorer.start_exploration_session(): if not explorer.start_exploration_session():
sys.exit(1) sys.exit(1)
# Show enhanced first-time guidance
print(f"\n🤔 Ask your first question about {project_path.name}:") print(f"\n🤔 Ask your first question about {project_path.name}:")
print()
print("💡 Enter your search query or question below:")
print(' Examples: "How does authentication work?" or "Show me error handling"')
print()
print("🔧 Quick options:")
print(" 1. Help - Show example questions")
print(" 2. Status - Project information")
print(" 3. Suggest - Get a random starter question")
print()
is_first_question = True
while True: while True:
try: try:
# Get user input # Get user input with clearer prompt
if is_first_question:
question = input("📝 Enter question or option (1-3): ").strip()
else:
question = input("\n> ").strip() question = input("\n> ").strip()
# Handle exit commands # Handle exit commands
@ -331,14 +346,17 @@ def explore_interactive(project_path: Path):
# Handle empty input # Handle empty input
if not question: if not question:
if is_first_question:
print("Please enter a question or try option 3 for a suggestion.")
else:
print("Please enter a question or 'quit' to exit.") print("Please enter a question or 'quit' to exit.")
continue continue
# Special commands # Handle numbered options and special commands
if question.lower() in ['help', 'h']: if question in ['1'] or question.lower() in ['help', 'h']:
print(""" print("""
🧠 EXPLORATION MODE HELP: 🧠 EXPLORATION MODE HELP:
• Ask any question about the codebase • Ask any question about your documents or code
• I remember our conversation for follow-up questions • I remember our conversation for follow-up questions
• Use 'why', 'how', 'explain' for detailed reasoning • Use 'why', 'how', 'explain' for detailed reasoning
• Type 'summary' to see session overview • Type 'summary' to see session overview
@ -346,12 +364,54 @@ def explore_interactive(project_path: Path):
💡 Example questions: 💡 Example questions:
• "How does authentication work?" • "How does authentication work?"
• "What are the main components?"
• "Show me error handling patterns"
• "Why is this function slow?" • "Why is this function slow?"
• "Explain the database connection logic" • "What security measures are in place?"
• "What are the security concerns here?" • "How does data flow through this system?"
""") """)
continue continue
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':
# 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?",
"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"
]
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
else:
question = next_input
else:
# For subsequent questions, could add AI-powered suggestions here
print("\n💡 Based on our conversation, you might want to ask:")
print(' "Can you explain that in more detail?"')
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()) print("\n" + explorer.get_session_summary())
continue continue
@ -361,6 +421,9 @@ def explore_interactive(project_path: Path):
print("🧠 Thinking with AI model...") print("🧠 Thinking with AI model...")
response = explorer.explore_question(question) response = explorer.explore_question(question)
# Mark as no longer first question after processing
is_first_question = False
if response: if response:
print(f"\n{response}") print(f"\n{response}")
else: else:

595
rag-tui.py
View File

@ -916,28 +916,36 @@ class SimpleTUI:
input("Press Enter to continue...") input("Press Enter to continue...")
return return
print("\n🤔 Ask questions about the codebase:") # Show initial prompt
print(" Quick: 0=quit, 1=summary, 2=history, 3=suggest next question") self._show_exploration_prompt(explorer, is_first=True)
is_first_question = True
while True: while True:
try: try:
question = input("\n> ").strip() question = input("➤ ").strip()
# Handle numbered options # Handle numbered options
if question == '0': if question == '0':
print(explorer.end_session()) print(explorer.end_session())
break break
elif question == '1': elif question == '1':
print("\n" + explorer.get_session_summary()) # Use improved summary function
summary = self._generate_conversation_summary(explorer)
print(f"\n{summary}")
self._show_exploration_prompt(explorer)
continue continue
elif question == '2': elif question == '2':
if hasattr(explorer.current_session, 'conversation_history') and explorer.current_session.conversation_history: if hasattr(explorer.current_session, 'conversation_history') and explorer.current_session.conversation_history:
print("\n🔍 Recent questions:") print("\n📋 Recent Question History:")
for i, exchange in enumerate(explorer.current_session.conversation_history[-3:], 1): print("═" * 40)
q = exchange["question"][:50] + "..." if len(exchange["question"]) > 50 else exchange["question"] for i, exchange in enumerate(explorer.current_session.conversation_history[-5:], 1):
print(f" {i}. {q}") q = exchange["question"][:60] + "..." if len(exchange["question"]) > 60 else exchange["question"]
confidence = exchange["response"].get("confidence", 0)
print(f" {i}. {q} (confidence: {confidence:.0f}%)")
print()
else: else:
print("\n📝 No questions asked yet") print("\n📝 No questions asked yet")
self._show_exploration_prompt(explorer)
continue continue
elif question == '3': elif question == '3':
# Generate smart suggestion # Generate smart suggestion
@ -945,13 +953,14 @@ class SimpleTUI:
if suggested_question: if suggested_question:
print(f"\n💡 Suggested question: {suggested_question}") print(f"\n💡 Suggested question: {suggested_question}")
print(" Press Enter to use this, or type your own question:") print(" Press Enter to use this, or type your own question:")
next_input = input("> ").strip() next_input = input("➤ ").strip()
if not next_input: # User pressed Enter to use suggestion if not next_input: # User pressed Enter to use suggestion
question = suggested_question question = suggested_question
else: else:
question = next_input question = next_input
else: else:
print("\n💡 No suggestions available yet. Ask a question first!") print("\n💡 No suggestions available yet. Ask a question first!")
self._show_exploration_prompt(explorer)
continue continue
# Simple exit handling # Simple exit handling
@ -961,23 +970,31 @@ class SimpleTUI:
# Skip empty input # Skip empty input
if not question: if not question:
print("💡 Please enter a question or choose an option (0-3)")
continue continue
# Simple help # Simple help
if question.lower() in ['help', 'h', '?']: if question.lower() in ['help', 'h', '?']:
print("\n💡 Just ask any question about the codebase!") print("\n💡 Exploration Help:")
print(" Examples: 'how does search work?' or 'explain the indexing'") print(" • Just ask any question about the codebase!")
print(" Quick: 0=quit, 1=summary, 2=history, 3=suggest") print(" • Examples: 'how does search work?' or 'explain the indexing'")
print(" • Use options 0-3 for quick actions")
self._show_exploration_prompt(explorer)
continue continue
# Process the question immediately # Process the question with streaming
print("🔍 Thinking...") print("\n🔍 Starting analysis...")
response = explorer.explore_question(question) response = explorer.explore_question(question)
if response: if response:
print(f"\n{response}\n") print(f"\n{response}")
is_first_question = False
# Show prompt for next question
self._show_exploration_prompt(explorer)
else: else:
print("❌ Sorry, I couldn't process that question.\n") print("❌ Sorry, I couldn't process that question.")
print("💡 Try rephrasing or using simpler terms.")
self._show_exploration_prompt(explorer)
except KeyboardInterrupt: except KeyboardInterrupt:
print(f"\n{explorer.end_session()}") print(f"\n{explorer.end_session()}")
@ -994,10 +1011,173 @@ class SimpleTUI:
# Exploration session completed successfully, return to menu without extra prompt # Exploration session completed successfully, return to menu without extra prompt
def _get_context_tokens_estimate(self, explorer):
"""Estimate the total tokens used in the conversation context."""
if not explorer.current_session or not explorer.current_session.conversation_history:
return 0
total_chars = 0
for exchange in explorer.current_session.conversation_history:
total_chars += len(exchange["question"])
# Estimate response character count (summary + key points)
response = exchange["response"]
total_chars += len(response.get("summary", ""))
for point in response.get("key_points", []):
total_chars += len(point)
# Rough estimate: 4 characters = 1 token
return total_chars // 4
def _get_context_limit_estimate(self):
"""Get estimated context limit for current model."""
# Conservative estimates for common models
return 32000 # Most models we use have 32k context
def _format_token_display(self, used_tokens, limit_tokens):
"""Format token usage display with color coding."""
percentage = (used_tokens / limit_tokens) * 100 if limit_tokens > 0 else 0
if percentage < 50:
color = "🟢" # Green - plenty of space
elif percentage < 75:
color = "🟡" # Yellow - getting full
else:
color = "🔴" # Red - almost full
return f"{color} Context: {used_tokens}/{limit_tokens} tokens ({percentage:.0f}%)"
def _show_exploration_prompt(self, explorer, is_first=False):
"""Show standardized input prompt for exploration mode."""
print()
print("═" * 60)
if is_first:
print("🤔 Ask your first question about the codebase:")
else:
print("🤔 What would you like to explore next?")
print()
# Show context usage
used_tokens = self._get_context_tokens_estimate(explorer)
limit_tokens = self._get_context_limit_estimate()
token_display = self._format_token_display(used_tokens, limit_tokens)
print(f"📊 {token_display}")
print()
print("🔧 Quick Options:")
print(" 0 = Quit exploration 1 = Summarize conversation")
print(" 2 = Show question history 3 = Suggest next question")
print()
print("💬 Enter your question or choose an option:")
def _generate_conversation_summary(self, explorer):
"""Generate a detailed summary of the conversation history."""
if not explorer.current_session or not explorer.current_session.conversation_history:
return "📝 No conversation to summarize yet. Ask a question first!"
try:
# Build conversation context
conversation_text = ""
for i, exchange in enumerate(explorer.current_session.conversation_history, 1):
conversation_text += f"Question {i}: {exchange['question']}\n"
conversation_text += f"Response {i}: {exchange['response']['summary']}\n"
# Add key points if available
if exchange['response'].get('key_points'):
for point in exchange['response']['key_points']:
conversation_text += f"- {point}\n"
conversation_text += "\n"
# Determine summary length based on conversation length
char_count = len(conversation_text)
if char_count < 500:
target_length = "brief"
target_words = "50-80"
elif char_count < 2000:
target_length = "moderate"
target_words = "100-150"
else:
target_length = "comprehensive"
target_words = "200-300"
# Create summary prompt for natural conversation style
prompt = f"""Please summarize this conversation about the project we've been exploring. Write a {target_length} summary ({target_words} words) in a natural, conversational style that captures:
1. Main topics we explored together
2. Key insights we discovered
3. Important details we learned
4. Overall understanding we gained
Conversation:
{conversation_text.strip()}
Write your summary as if you're explaining to a colleague what we discussed. Use a friendly, informative tone and avoid JSON or structured formats."""
# Use the synthesizer to generate summary with streaming and thinking
print("\n💭 Generating summary...")
response = explorer.synthesizer._call_ollama(prompt, temperature=0.1, disable_thinking=False, use_streaming=True)
if response:
return f"📋 **Conversation Summary**\n\n{response.strip()}"
else:
# Fallback summary
return self._generate_fallback_summary(explorer.current_session.conversation_history)
except Exception as e:
logger.error(f"Summary generation failed: {e}")
return self._generate_fallback_summary(explorer.current_session.conversation_history)
def _generate_fallback_summary(self, conversation_history):
"""Generate a simple fallback summary when AI summary fails."""
if not conversation_history:
return "📝 No conversation to summarize yet."
question_count = len(conversation_history)
topics = []
# Extract simple topics from questions
for exchange in conversation_history:
question = exchange["question"].lower()
if "component" in question or "part" in question:
topics.append("system components")
elif "error" in question or "bug" in question:
topics.append("error handling")
elif "security" in question or "auth" in question:
topics.append("security/authentication")
elif "test" in question:
topics.append("testing")
elif "config" in question or "setting" in question:
topics.append("configuration")
elif "performance" in question or "speed" in question:
topics.append("performance")
else:
# Extract first few words as topic
words = question.split()[:3]
topics.append(" ".join(words))
unique_topics = list(dict.fromkeys(topics)) # Remove duplicates while preserving order
summary = f"📋 **Conversation Summary**\n\n"
summary += f"Questions asked: {question_count}\n"
summary += f"Topics explored: {', '.join(unique_topics[:5])}\n"
summary += f"Session duration: {len(conversation_history) * 2} minutes (estimated)\n\n"
summary += "💡 Use option 2 to see recent question history for more details."
return summary
def _generate_smart_suggestion(self, explorer): def _generate_smart_suggestion(self, explorer):
"""Generate a smart follow-up question based on conversation context.""" """Generate a smart follow-up question based on conversation context."""
if not explorer.current_session or not explorer.current_session.conversation_history: if not explorer.current_session or not explorer.current_session.conversation_history:
return None # First question - provide a random starter question
import random
starters = [
"What are the main components of this project?",
"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"
]
return random.choice(starters)
try: try:
# Get recent conversation context # Get recent conversation context
@ -1023,8 +1203,8 @@ Respond with ONLY a single short question that would logically explore deeper or
Your suggested question (under 10 words):""" Your suggested question (under 10 words):"""
# Use the synthesizer to generate suggestion # Use the synthesizer to generate suggestion with thinking collapse
response = explorer.synthesizer._call_ollama(prompt, temperature=0.3, disable_thinking=True) response = explorer.synthesizer._call_ollama(prompt, temperature=0.3, disable_thinking=False, use_streaming=True, collapse_thinking=True)
if response: if response:
# Clean up the response - extract just the question # Clean up the response - extract just the question
@ -1149,99 +1329,344 @@ Your suggested question (under 10 words):"""
input("Press Enter to continue...") input("Press Enter to continue...")
def show_configuration(self): def show_configuration(self):
"""Show and manage configuration options.""" """Show and manage configuration options with interactive editing."""
if not self.project_path: if not self.project_path:
print("❌ No project selected") print("❌ No project selected")
input("Press Enter to continue...") input("Press Enter to continue...")
return return
while True:
self.clear_screen() self.clear_screen()
self.print_header() self.print_header()
print("⚙️ Configuration") print("⚙️ Configuration Manager")
print("================") print("========================")
print() print()
print(f"Project: {self.project_path.name}") print(f"Project: {self.project_path.name}")
print() print()
# Load current configuration
try:
from mini_rag.config import ConfigManager
config_manager = ConfigManager(self.project_path)
config = config_manager.load_config()
config_path = self.project_path / '.mini-rag' / 'config.yaml' config_path = self.project_path / '.mini-rag' / 'config.yaml'
# Show current configuration if it exists
if config_path.exists():
print("✅ Configuration file exists")
print(f" Location: {config_path}")
print()
try:
import yaml
with open(config_path) as f:
config = yaml.safe_load(f)
print("📋 Current Settings:") print("📋 Current Settings:")
if 'chunking' in config: print(f" 📁 Chunk size: {config.chunking.max_size} characters")
chunk_cfg = config['chunking'] print(f" 🧠 Chunking strategy: {config.chunking.strategy}")
print(f" Chunk size: {chunk_cfg.get('max_size', 2000)} characters") print(f" 🔍 Search results: {config.search.default_top_k} results")
print(f" Strategy: {chunk_cfg.get('strategy', 'semantic')}") print(f" 📊 Embedding method: {config.embedding.preferred_method}")
print(f" 🚀 Query expansion: {'enabled' if config.search.expand_queries else 'disabled'}")
if 'embedding' in config: print(f" ⚡ LLM synthesis: {'enabled' if config.llm.enable_synthesis else 'disabled'}")
emb_cfg = config['embedding']
print(f" Embedding method: {emb_cfg.get('preferred_method', 'auto')}")
if 'files' in config:
files_cfg = config['files']
print(f" Min file size: {files_cfg.get('min_file_size', 50)} bytes")
exclude_count = len(files_cfg.get('exclude_patterns', []))
print(f" Excluded patterns: {exclude_count} patterns")
print() print()
print("🛠️ Quick Configuration Options:")
print(" 1. Adjust chunk size (performance vs accuracy)")
print(" 2. Toggle query expansion (smarter searches)")
print(" 3. Configure search behavior")
print(" 4. View/edit full configuration file")
print(" 5. Reset to defaults")
print(" 6. Advanced settings")
print()
print(" V. View current config file")
print(" B. Back to main menu")
except Exception as e: except Exception as e:
print(f"⚠️ Could not read config: {e}") print(f"❌ Error loading configuration: {e}")
print(" A default config will be created when needed")
print() print()
print(" B. Back to main menu")
print()
choice = input("Choose option: ").strip().lower()
if choice == 'b' or choice == '' or choice == '0':
break
elif choice == 'v':
self._show_config_file(config_path)
elif choice == '1':
self._configure_chunk_size(config_manager, config)
elif choice == '2':
self._toggle_query_expansion(config_manager, config)
elif choice == '3':
self._configure_search_behavior(config_manager, config)
elif choice == '4':
self._edit_config_file(config_path)
elif choice == '5':
self._reset_config(config_manager)
elif choice == '6':
self._advanced_settings(config_manager, config)
else: else:
print("⚠️ No configuration file found") print("Invalid option. Press Enter to continue...")
print(" A default config will be created when you index") input()
def _show_config_file(self, config_path):
"""Display the full configuration file."""
self.clear_screen()
print("📄 Configuration File Contents")
print("=" * 50)
print() print()
# Show CLI commands for configuration
self.print_cli_command(f"cat {config_path}",
"View current configuration")
self.print_cli_command(f"nano {config_path}",
"Edit configuration file")
print("🛠️ Configuration Options:")
print(" • chunking.max_size - How large each searchable chunk is")
print(" • chunking.strategy - 'semantic' (smart) vs 'fixed' (simple)")
print(" • files.exclude_patterns - Skip files matching these patterns")
print(" • embedding.preferred_method - 'ollama', 'ml', 'hash', or 'auto'")
print(" • search.default_top_k - Default number of search results (top-k)")
print()
print("📚 References:")
print(" • README.md - Complete configuration documentation")
print(" • examples/config.yaml - Example with all options")
print(" • docs/TUI_GUIDE.md - Detailed TUI walkthrough")
print()
# Quick actions
if config_path.exists(): if config_path.exists():
action = input("Quick actions: [V]iew config, [E]dit path, or Enter to continue: ").lower()
if action == 'v':
print("\n" + "="*60)
try: try:
with open(config_path) as f: with open(config_path) as f:
print(f.read()) content = f.read()
print(content)
except Exception as e: except Exception as e:
print(f"Could not read file: {e}") print(f"❌ Could not read file: {e}")
print("="*60)
input("\nPress Enter to continue...")
elif action == 'e':
print(f"\n💡 To edit configuration:")
print(f" nano {config_path}")
print(f" # Or use your preferred editor")
input("\nPress Enter to continue...")
else: else:
print("⚠️ Configuration file doesn't exist yet")
print(" It will be created when you first index a project")
print("\n" + "=" * 50)
input("Press Enter to continue...")
def _configure_chunk_size(self, config_manager, config):
"""Interactive chunk size configuration."""
self.clear_screen()
print("📁 Chunk Size Configuration")
print("===========================")
print()
print("Chunk size affects both performance and search accuracy:")
print("• Smaller chunks (500-1000): More precise but may miss context")
print("• Medium chunks (1500-2500): Good balance (recommended)")
print("• Larger chunks (3000+): More context but less precise")
print()
print(f"Current chunk size: {config.chunking.max_size} characters")
print()
print("Quick presets:")
print(" 1. Small (1000) - Precise searching")
print(" 2. Medium (2000) - Balanced (default)")
print(" 3. Large (3000) - More context")
print(" 4. Custom size")
print()
choice = input("Choose preset or enter custom size: ").strip()
new_size = None
if choice == '1':
new_size = 1000
elif choice == '2':
new_size = 2000
elif choice == '3':
new_size = 3000
elif choice == '4':
try:
new_size = int(input("Enter custom chunk size (500-5000): "))
if new_size < 500 or new_size > 5000:
print("❌ Size must be between 500 and 5000")
input("Press Enter to continue...")
return
except ValueError:
print("❌ Invalid number")
input("Press Enter to continue...")
return
elif choice.isdigit():
try:
new_size = int(choice)
if new_size < 500 or new_size > 5000:
print("❌ Size must be between 500 and 5000")
input("Press Enter to continue...")
return
except ValueError:
pass
if new_size and new_size != config.chunking.max_size:
config.chunking.max_size = new_size
config_manager.save_config(config)
print(f"\n✅ Chunk size updated to {new_size} characters")
print("💡 Tip: Re-index your project for changes to take effect")
input("Press Enter to continue...")
def _toggle_query_expansion(self, config_manager, config):
"""Toggle query expansion on/off."""
self.clear_screen()
print("🚀 Query Expansion Configuration")
print("================================")
print()
print("Query expansion automatically adds related terms to your searches")
print("to improve results quality. This uses an LLM to understand your")
print("intent and find related concepts.")
print()
print("Benefits:")
print("• Find relevant results even with different terminology")
print("• Better semantic understanding of queries")
print("• Improved search for complex technical concepts")
print()
print("Requirements:")
print("• Ollama with a language model (e.g., qwen3:1.7b)")
print("• Slightly slower search (1-2 seconds)")
print()
current_status = "enabled" if config.search.expand_queries else "disabled"
print(f"Current status: {current_status}")
print()
if config.search.expand_queries:
choice = input("Query expansion is currently ON. Turn OFF? [y/N]: ").lower()
if choice == 'y':
config.search.expand_queries = False
config_manager.save_config(config)
print("✅ Query expansion disabled")
else:
choice = input("Query expansion is currently OFF. Turn ON? [y/N]: ").lower()
if choice == 'y':
config.search.expand_queries = True
config_manager.save_config(config)
print("✅ Query expansion enabled")
print("💡 Make sure Ollama is running with a language model")
input("\nPress Enter to continue...")
def _configure_search_behavior(self, config_manager, config):
"""Configure search behavior settings."""
self.clear_screen()
print("🔍 Search Behavior Configuration")
print("================================")
print()
print(f"Current settings:")
print(f"• Default results: {config.search.default_top_k}")
print(f"• BM25 keyword boost: {'enabled' if config.search.enable_bm25 else 'disabled'}")
print(f"• Similarity threshold: {config.search.similarity_threshold}")
print()
print("Configuration options:")
print(" 1. Change default number of results")
print(" 2. Toggle BM25 keyword matching")
print(" 3. Adjust similarity threshold")
print(" B. Back")
print()
choice = input("Choose option: ").strip().lower()
if choice == '1':
try:
new_top_k = int(input(f"Enter default number of results (current: {config.search.default_top_k}): "))
if 1 <= new_top_k <= 100:
config.search.default_top_k = new_top_k
config_manager.save_config(config)
print(f"✅ Default results updated to {new_top_k}")
else:
print("❌ Number must be between 1 and 100")
except ValueError:
print("❌ Invalid number")
elif choice == '2':
config.search.enable_bm25 = not config.search.enable_bm25
config_manager.save_config(config)
status = "enabled" if config.search.enable_bm25 else "disabled"
print(f"✅ BM25 keyword matching {status}")
elif choice == '3':
try:
new_threshold = float(input(f"Enter similarity threshold 0.0-1.0 (current: {config.search.similarity_threshold}): "))
if 0.0 <= new_threshold <= 1.0:
config.search.similarity_threshold = new_threshold
config_manager.save_config(config)
print(f"✅ Similarity threshold updated to {new_threshold}")
else:
print("❌ Threshold must be between 0.0 and 1.0")
except ValueError:
print("❌ Invalid number")
if choice != 'b' and choice != '':
input("Press Enter to continue...")
def _edit_config_file(self, config_path):
"""Provide instructions for editing the config file."""
self.clear_screen()
print("📝 Edit Configuration File")
print("=========================")
print()
if config_path.exists():
print(f"Configuration file location:")
print(f" {config_path}")
print()
print("To edit the configuration:")
print(" • Use any text editor (nano, vim, VS Code, etc.)")
print(" • The file is in YAML format with helpful comments")
print(" • Changes take effect after saving")
print()
print("Quick edit commands:")
self.print_cli_command(f"nano {config_path}", "Edit with nano")
self.print_cli_command(f"code {config_path}", "Edit with VS Code")
self.print_cli_command(f"vim {config_path}", "Edit with vim")
else:
print("⚠️ Configuration file doesn't exist yet")
print(" It will be created automatically when you index a project")
input("\nPress Enter to continue...")
def _reset_config(self, config_manager):
"""Reset configuration to defaults."""
self.clear_screen()
print("🔄 Reset Configuration")
print("=====================")
print()
print("This will reset all settings to default values:")
print("• Chunk size: 2000 characters")
print("• Chunking strategy: semantic")
print("• Query expansion: disabled")
print("• Search results: 10")
print("• Embedding method: auto")
print()
confirm = input("Are you sure you want to reset to defaults? [y/N]: ").lower()
if confirm == 'y':
from mini_rag.config import RAGConfig
default_config = RAGConfig()
config_manager.save_config(default_config)
print("✅ Configuration reset to defaults")
print("💡 You may want to re-index for changes to take effect")
else:
print("❌ Reset cancelled")
input("Press Enter to continue...")
def _advanced_settings(self, config_manager, config):
"""Configure advanced settings."""
self.clear_screen()
print("⚙️ Advanced Configuration")
print("==========================")
print()
print("Advanced settings for power users:")
print()
print(f"Current advanced settings:")
print(f"• Min file size: {config.files.min_file_size} bytes")
print(f"• Streaming threshold: {config.streaming.threshold_bytes} bytes")
print(f"• Embedding batch size: {config.embedding.batch_size}")
print(f"• LLM synthesis: {'enabled' if config.llm.enable_synthesis else 'disabled'}")
print()
print("Advanced options:")
print(" 1. Configure file filtering")
print(" 2. Adjust performance settings")
print(" 3. LLM model preferences")
print(" B. Back")
print()
choice = input("Choose option: ").strip().lower()
if choice == '1':
print("\n📁 File filtering settings:")
print(f"Minimum file size: {config.files.min_file_size} bytes")
print(f"Excluded patterns: {len(config.files.exclude_patterns)} patterns")
print("\n💡 Edit the config file directly for detailed file filtering")
elif choice == '2':
print("\n⚡ Performance settings:")
print(f"Embedding batch size: {config.embedding.batch_size}")
print(f"Streaming threshold: {config.streaming.threshold_bytes}")
print("\n💡 Higher batch sizes = faster indexing but more memory")
elif choice == '3':
print("\n🧠 LLM model preferences:")
if hasattr(config.llm, 'model_rankings') and config.llm.model_rankings:
print("Current model priority order:")
for i, model in enumerate(config.llm.model_rankings[:5], 1):
print(f" {i}. {model}")
print("\n💡 Edit config file to change model preferences")
if choice != 'b' and choice != '':
input("Press Enter to continue...") input("Press Enter to continue...")
def show_cli_reference(self): def show_cli_reference(self):