You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs
Mohammad Mohtashim d1b7a934aa
[Community]: HuggingFaceCrossEncoder `score` accounting for <not-relevant score,relevant score> pairs. (#22578)
- **Description:** Some of the Cross-Encoder models provide scores in
pairs, i.e., <not-relevant score (higher means the document is less
relevant to the query), relevant score (higher means the document is
more relevant to the query)>. However, the `HuggingFaceCrossEncoder`
`score` method does not currently take into account the pair situation.
This PR addresses this issue by modifying the method to consider only
the relevant score if score is being provided in pair. The reason for
focusing on the relevant score is that the compressors select the top-n
documents based on relevance.
    - **Issue:** #22556 
- Please also refer to this
[comment](https://github.com/UKPLab/sentence-transformers/issues/568#issuecomment-729153075)
4 months ago
..
cli cli[patch]: Release 0.0.25 (#22876) 4 months ago
community [Community]: HuggingFaceCrossEncoder `score` accounting for <not-relevant score,relevant score> pairs. (#22578) 4 months ago
core core: release 0.2.6 (#22868) 4 months ago
experimental Fix: lint errors and update Field alias in models.py and AutoSelectionScorer initialization (#22846) 4 months ago
langchain docs: `ReAct` reference (#22830) 4 months ago
partners anthropic[patch]: always add tool_result type to ToolMessage content (#22721) 4 months ago
standard-tests multiple: add `stop` attribute (#22573) 4 months ago
text-splitters Community[minor]: Add language parser for Elixir (#22742) 4 months ago