RAG-Generation / RAG_FULL_APPLICATION_BACKEND

Commit History

  1. fix: install tesseract-ocr-eng in Dockerfile and add grayscale contrast preprocessing for image OCR Running

    d61e4dd
  2. fix: non-blocking async timeout for vision analysis with fast Tesseract OCR fallback

    8d465e5
  3. fix: robust OCR/image ingestion parsing and add one-click Supabase document deletion to Search Playground

    0e82360

  1. chore: add uploads and pdf files to gitignore

    653d9a8
  2. fix: ColBERT dense fallback and increase Nginx proxy timeouts to 300s

    decdb15
  3. feat: implement Hybrid Intent Detection (Keywords + LLM) for CRAG

    84acb35
  4. fix: Nginx proxy for /advanced and LLM JSON intent classification

    8f9c9c9
  5. feat: upgrade RAG conversational intent classification to multi-lingual LLM

    27d1bb9

  1. Security Hardening: Fixed path traversal, BM25 RCE, IDOR, and removed backdoor

    82d183d

  1. Refactor LLM architecture to SOLID principles, add Gemini Judge, and self-reflective RAGAS logic

    9748ae9

  1. feat: enterprise multi-page RAG platform with GraphRAG, CRAG, Guardrails, and VectorDB Inspector

    73905db
  2. feat: Add RAG Execution Transparency, Technique Compatibility Matrix, and RAGAS Quality Dashboard

    dc7b682
  3. security: Remove hardcoded GLM API key from source files (use environment variable GLM_4_7_API_KEY)

    d66e894
  4. feat: Implement GLM-4.7-Flash RAGAS Judge and LLM fallback (Qwen -> GLM-4.7-Flash)

    a46ca29
  5. fix: rebuild BM25 index from Supabase on serverless cold start

    0d0fa3f

  1. Fix file upload UI refresh and add Metadata Filters UI

    bf7338b

  1. Final Build: Dockeerized Frontend/Backend with full RAG multi-format support

    1b08040

  1. Initial commit: Multimodal RAG Pipeline V3.0 with Fallback Logic

    2ecc4a7