Commit History

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

    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
  4. fix: auto-select active document on load and ingestion finish so search is never disabled

    f4970d3

  1. fix: align all UI model documentation strings with Tencent Hy3 + Gemini 3.1 Flash backend

    0db65ad
  2. fix: update UI labels to accurately reflect Gemini 3.1 Flash as the active RAGAS judge

    f7874af
  3. chore: add uploads and pdf files to gitignore

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

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

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

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

    27d1bb9

  1. Update RAG application backend, LLM services, ingest file safety and frontend components

    308053f
  2. Security Hardening: Fixed path traversal, BM25 RCE, IDOR, and removed backdoor

    82d183d

  1. Update documentation files and interview Q&A guide with latest SOLID architecture and RAGAS self-correction details

    28dc115
  2. Elaborate RAG Fundamentals page with real-world applications and concrete examples

    7a01d82
  3. 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. Merge remote-tracking branch 'origin/main' into main

    592f48d
  6. my local frontend changes

    963fa66
  7. fix: rebuild BM25 index from Supabase on serverless cold start

    0d0fa3f

  1. Implement Frontend-Only Session History

    849e50c
  2. Sync updated RAG application code: Fix UI refresh and add Metadata Filters

    637e77d
  3. Fix file upload UI refresh and add Metadata Filters UI

    bf7338b
  4. Update RAG_FULL_APPLICATION_FRONTEND/src/components/FileUpload.jsx⁠

    b1c72d5

  1. Update RAG_FULL_APPLICATION_BACKEND/requirements.txt⁠

    cbe9ada
  2. Pin bcrypt==3.2.2 to fix passlib 72-byte hash bug on Python 3.12

    be51a9c
  3. Add full traceback to seed_admin for debugging

    01d221d
  4. Fix permission issue for Hugging Face non-root user

    e7b8f12

  1. Configure monolithic full-stack app

    a2e039d

  1. initial commit

    48fc37f

  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