Number_one / app.py

Commit History

  1. Reactive BM25 (lecture paginee) sur la version du collegue (garde bge-reranker + k=2)

    9f65306
  2. Upload app.py

    Verified signature
    0efe830
  3. Fix BM25: lecture paginee de la collection (evite 'too many SQL variables' sur 84k chunks -> BM25 enfin actif)

    c90a1ed
  4. Deploy v9equilibre sur main: routing OFF (gpt-5.1 only) + k=3 + prompt adouci

    b91ab33
  5. Deploy v5 (BM25+routing gpt-mini) + prompt FR anti-hallucination renforce sur main

    ed5321e

  1. Remove query log

    Quincy Hsieh
    445de19

  1. Add co2 documentation

    Quincy Hsieh
    50775af
  2. Add CO2 emission and token counts

    Quincy Hsieh
    929f2ac

  1. Change sample data to train data folder

    Quincy Hsieh
    48798a9
  2. Add ref_text to the referenced text of the source file

    Quincy Hsieh
    dc06bcc
  3. Increase embedding/LLM call timeout

    Quincy Hsieh
    312a42b
  4. Add token count and explanation

    Quincy Hsieh
    035ac6d
  5. Fix error Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

    Quincy Hsieh
    b818d09
  6. Handle error

    Quincy Hsieh
    731ee37
  7. Read config.json in the /data folder, instead of reading from the root

    Quincy Hsieh
    6ee8606

  1. Add team yml and endpoint LLM models

    Quincy Hsieh
    53cab5b

  1. Call LLM model from Azure OpenAI endpoint

    Quincy Hsieh
    4cf3b63
  2. Fix error LLM API call failed: 404 Client Error: Not Found for url...

    Quincy Hsieh
    c8361c5
  3. Fix ssl.SSLCertVerificationError with instruction of how to solve it

    Quincy Hsieh
    1974292
  4. Re-structure folder for prompt engineering

    Quincy Hsieh
    03514f5
  5. Add PDF reader example

    Quincy Hsieh
    d2c4c08
  6. Add sample code of RAG API

    Quincy Hsieh
    b263309
  7. Add application file

    Quincy Hsieh
    0aebf2c