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

Deploy V99 (modif collegue app.py) sur main

Redeploy version stable (V99WHATHEFUCK) sur main

Upload app.py

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

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

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

Deploy v1prompt FR (expert actuariat + anti-hallucination) to main

Add ingestion/OCR/exploration tooling + improvements roadmap; ignore local artifacts

Pin huggingface-hub==0.25.0 (fix gradio 4.44.1 HfFolder import vs hf_hub 1.x)

Bump chromadb to 1.x (prebuilt wheels), trim unused langchain deps, ignore data/train_data

Pull latest baseline update (hf sync / bucket storage docs)

Remove query log

Change team name to Team Baseline

Add detailed Hackathon instructions

Add .gitignore

Pull code from source repo

Add team.yml and HF README header

initial commit

Add README.md update

Add simplfied README

Delete README with updated README_HF.md

Upload README.md (#2)

Upload 2 files (#1)

Fix WARNING:llm:ecologits impact calc failed for model=gpt-5.1: float() argument must be a string or a real number, not 'RangeValue'

Add co2 documentation

Add CO2 emission and token counts

Update team name and member list

Change sample data to train data folder

Add ref_text to the referenced text of the source file

Increase embedding/LLM call timeout

Add token count and explanation

Fix error Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

Change endpoint to APIM endpoint

Handle error

Read config.json in the /data folder, instead of reading from the root

Update README for data sync

Add team yml and endpoint LLM models

Add how to update binary files into /data bucket

Call LLM model from Azure OpenAI endpoint

Fix error LLM API call failed: 404 Client Error: Not Found for url...

Fix ssl.SSLCertVerificationError with instruction of how to solve it

Re-structure folder for prompt engineering

Add PDF reader example

Fix error remote: - Error: "emoji" with value "�" fails to match the required pattern: /\p{Extended_Pictographic}/u

Add sample code of RAG API

Add application file

initial commit