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

Fix LLM response formatting and Windows installer robustness

Browse Source 
- Preserve whitespace and newlines in streaming responses
- Clean thinking tags from final LLM responses
- Add lazy initialization to _call_ollama method
- Improve Windows installer to handle existing virtual environments
- Add better error reporting for import failures

These fixes address formatting corruption in numbered lists and
improve installer reliability when dependencies already exist.
This commit is contained in:
BobAi 2025-08-15 14:26:53 +10:00
parent 17f4f57dad
commit 92cb600dd6
3 changed files with 59 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.mini-rag/last_search
View File

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

28
install_windows.bat
View File

@ -70,10 +70,19 @@ echo.
echo ══════════════════════════════════════════════════
echo [2/5] Creating Python Virtual Environment...
if exist "%SCRIPT_DIR%\.venv" (
echo 🔄 Removing old virtual environment...
echo 🔄 Found existing virtual environment, checking if it works...
call "%SCRIPT_DIR%\.venv\Scripts\activate.bat" >nul 2>&1
if not errorlevel 1 (
"%SCRIPT_DIR%\.venv\Scripts\python.exe" -c "import sys; print('✅ Existing environment works')" >nul 2>&1
if not errorlevel 1 (
echo ✅ Using existing virtual environment
goto skip_venv_creation
)
)
echo 🔄 Removing problematic virtual environment...
rmdir /s /q "%SCRIPT_DIR%\.venv" 2>nul
if exist "%SCRIPT_DIR%\.venv" (
echo ⚠️ Could not remove old environment, creating anyway...
echo ⚠️ Could not remove old environment, will try to work with it...
)
)
@ -93,6 +102,7 @@ if errorlevel 1 (
)
echo ✅ Virtual environment created successfully
:skip_venv_creation
echo.
echo ══════════════════════════════════════════════════
echo [3/5] Installing Python Dependencies...
@ -133,19 +143,29 @@ echo.
echo ══════════════════════════════════════════════════
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
echo Attempting import test...
"%SCRIPT_DIR%\.venv\Scripts\python.exe" -c "from mini_rag import CodeEmbedder, ProjectIndexer, CodeSearcher; print('✅ Core imports successful')" 2>import_error.txt
if errorlevel 1 (
echo ❌ ERROR: Installation test failed
echo.
echo 🔍 Import error details:
type import_error.txt
echo.
echo 🔧 This usually means:
echo • Dependencies didn't install correctly
echo • Virtual environment is corrupted
echo • Python path issues
echo • Module conflicts with existing installations
echo.
echo 💡 Try running: pip install -r requirements.txt
echo 💡 Troubleshooting options:
echo • Try: "%SCRIPT_DIR%\.venv\Scripts\pip.exe" install -r requirements.txt --force-reinstall
echo • Or delete .venv folder and run installer again
echo • Or check import_error.txt for specific error details
del import_error.txt >nul 2>&1
pause
exit /b 1
)
del import_error.txt >nul 2>&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

36
mini_rag/llm_synthesizer.py
View File

@ -169,6 +169,9 @@ class LLMSynthesizer:
start_time = time.time()
try:
# Ensure we're initialized
self._ensure_initialized()
# Use the best available model
model_to_use = self.model
if self.model not in self.available_models:
@ -262,7 +265,20 @@ class LLMSynthesizer:
# Preserve original response but add safeguard warning
return self._create_safeguard_response_with_content(issue_type, explanation, raw_response)
return raw_response
# Clean up thinking tags from final response
cleaned_response = raw_response
if '<think>' in cleaned_response or '</think>' in cleaned_response:
# Remove thinking content but preserve the rest
cleaned_response = cleaned_response.replace('<think>', '').replace('</think>', '')
# Clean up extra whitespace that might be left
lines = cleaned_response.split('\n')
cleaned_lines = []
for line in lines:
if line.strip(): # Only keep non-empty lines
cleaned_lines.append(line)
cleaned_response = '\n'.join(cleaned_lines)
return cleaned_response.strip()
else:
logger.error(f"Ollama API error: {response.status_code}")
return None
@ -433,7 +449,8 @@ This is normal with smaller AI models and helps ensure you get quality responses
if '<think>' in clean_text or '</think>' in clean_text:
clean_text = clean_text.replace('<think>', '').replace('</think>', '')
if clean_text.strip():
if clean_text: # Remove .strip() here to preserve whitespace
# Preserve all formatting including newlines and spaces
print(clean_text, end='', flush=True)
# Check if response is done
@ -520,7 +537,20 @@ This is normal with smaller AI models and helps ensure you get quality responses
except json.JSONDecodeError:
continue
return full_response.strip()
# Clean up thinking tags from final response
cleaned_response = full_response
if '<think>' in cleaned_response or '</think>' in cleaned_response:
# Remove thinking content but preserve the rest
cleaned_response = cleaned_response.replace('<think>', '').replace('</think>', '')
# Clean up extra whitespace that might be left
lines = cleaned_response.split('\n')
cleaned_lines = []
for line in lines:
if line.strip(): # Only keep non-empty lines
cleaned_lines.append(line)
cleaned_response = '\n'.join(cleaned_lines)
return cleaned_response.strip()
except Exception as e:
logger.error(f"Streaming with early stop failed: {e}")