mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-06-26 22:19:57 +00:00

### What problem does this PR solve? This PR adds fields to the `Chunk` class to store retrieval results like similarity scores, term similarity, vector similarity, positions, and document type. This allows the chunk object to hold all the information needed when returning search results from the vector database. ### Type of change - [x] New Feature (non-breaking change which adds functionality)
ragflow-sdk
build and publish python SDK to pypi.org
uv build
uv pip install twine
export TWINE_USERNAME="__token__"
export TWINE_PASSWORD=$YOUR_PYPI_API_TOKEN
twine upload dist/*.whl