Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: https-deeplearning-ai/ragchatbot-codebase
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: main
Choose a base ref
...
head repository: dusalex/ragchatbot-codebase
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: main
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 1 commit
  • 7 files changed
  • 2 contributors

Commits on Sep 5, 2025

  1. Add comprehensive RAG system diagnostic tests and configuration valid…

    …ation
    
    This commit adds extensive diagnostic tests to identify and resolve "query failed"
    issues in the RAG chatbot system, plus improved configuration validation.
    
    New test files:
    - test_live_system_diagnostics.py: Tests actual system configuration and vector store status
    - test_document_loading_integration.py: Tests document processing with real course files
    - test_live_component_integration.py: Tests components (CourseSearchTool, AIGenerator) with real data
    - test_actual_api_endpoints.py: Tests actual running FastAPI server endpoints
    - test_ai_tool_usage_analysis.py: Analyzes AI tool usage patterns
    - tests/README.md: Documents test findings and system behavior
    
    Configuration improvements:
    - Add validation in Config.__post_init__() to detect invalid API keys
    - Add is_api_key_valid() method for runtime API key validation
    - Add helpful error messages for common configuration issues
    
    Key findings from comprehensive testing:
    - RAG system is working correctly with proper API key
    - All components (document loading, vector store, search tools, AI generation) functional
    - AI intelligently chooses between course content and general knowledge
    - No "query failed" issues detected in current system
    - System exhibits appropriate behavior: course queries use tools, general queries use AI knowledge
    
    🤖 Generated with [Claude Code](https://claude.ai/code)
    
    Co-Authored-By: Claude <noreply@anthropic.com>
    dusalex and claude committed Sep 5, 2025
    Configuration menu
    Copy the full SHA
    142dc21 View commit details
    Browse the repository at this point in the history
Loading