gardio_test / app.py

Commit History

  1. fix: quantization_config 역직렬화 오류를 config.json 패치로 완전 해결 (로컬 통합 테스트 통과)

    415ebef
  2. fix: keras 3.12.1 + tf 2.21.0 복원 (로컬 환경 일치) + quantization_config 역직렬화 오류 3단계 fallback 추가

    9efb88a
  3. fix: tensorflow 2.15 (keras 충돌 제거) + 에러 메시지 500자로 확장

    d42dc1b
  4. fix: local model load fallback + score grade color fix

    3155350

  1. Fix SyntaxError in css string

    2be8232
  2. Remove Soft theme (blue label bug), unit back in label parentheses

    8cb66e5
  3. Unit in info field, enlarged section title

    82f601c
  4. Fix placeholder encoding, enlarge title

    6e12111
  5. Add unit suffix to input field labels (만원, 일, 개)

    a973827
  6. UI: dark mode, placeholder, 2-col inputs

    34a4c19
  7. Fix RAG KeyError L10210000; Add grade-colored HTML score display

    dc01a88
  8. Enhance LLM personal features context

    2c9909d
  9. Fix Gemini model configuration and R/A/G display

    09dbaf7
  10. Fix scikit-learn version mismatch and visualize R/A/G steps

    c5ed44a
  11. fix

    53616e0
  12. Hotfix: Gemini 404 and enhanced error visibility

    b1040cf
  13. Final stable: hf_hub_download and dictionary-based chat

    737169d
  14. Emergency fix: Remove type='messages' and restore Tuple format for absolute Gradio compatibility

    3143f3f
  15. Fix model load traceability and Chatbot data format

    0112759
  16. Robustness update: Detailed error reporting and stable chatbot format

    5393c73
  17. Final stable sync: Tuples for Chatbot and HF health check

    b93d655
  18. fix

    d087132
  19. Fix HF deployment errors: Gradio 5 upgrade and 0.0.0.0 binding

    e3388ce
  20. Clean up scratch files and finalize robust deployment

    14f70ce
  21. fix

    1f20aa8
  22. fix

    53c9adb
  23. Fix NameError in app.py and ensure internal loan count calculation works

    14570a1
  24. Remove L10210000 from UI and calculate internally

    5ca9ce0
  25. Corrected feature labels, implemented loan sum logic, and fixed API key config

    270cbe3

  1. Clean: Synced code for Hugging Face (binary files handled via API)

    61525d4
  2. UX: Improve all input labels with full descriptions, units, and example values

    5994e00
  3. Critical Fix: Use Gradio 5.2.0, tuple-based Chatbot, and Docker ENV vars to resolve all crash issues

    6d40f77
  4. Fix: Final memory optimization to prevent RUNTIME_ERROR by deferring embedding model loading

    c353fe2
  5. Fix: Upgrade to Gradio 5.1.0 and enable queue to resolve TypeError and sharing issue on Docker

    267e2af
  6. Optimize: Final refinement for Hugging Face Docker SDK (0.0.0.0:7860)

    bffc58d
  7. Ultra-Stable: Defer ALL heavy imports to function call to prevent boot crash (500 error)

    dfd1ae6
  8. Stabilize: Downgrade to Gradio 4.44.1 and implement Lazy Loading to fix 500 error

    1d4b2ed
  9. Fix: Expand UI features to 14 to match prediction model and fix No API found error

    7813475
  10. Hotfix: Add monkeypatch for HfFolder ImportError

    7ca482a
  11. Switch LLM to Google Gemini 1.5 Flash (Google AI Studio)

    3f9602c
  12. Deploy to Hugging Face Spaces

    eb55100
  13. Add

    d4ecde8

  1. first commit

    60102cd