2 Commits

Author	SHA1	Message	Date
Thomas van Dongen	ee640d6bd3	community: fixed bug in model2vec embedding code (#28670) ... This PR fixes a bug with the current implementation for Model2Vec embeddings where `embed_documents` does not work as expected. - **Description**: the current implementation uses `encode_as_sequence` for encoding documents. This is incorrect, as `encode_as_sequence` creates token embeddings and not mean embeddings. The normal `encode` function handles both single and batched inputs and should be used instead. The return type was also incorrect, as encode returns a NumPy array. This PR converts the embedding to a list so that the output is consistent with the Embeddings ABC.	2024-12-11 15:50:56 -08:00
Abhinav	317a38b83e	community[minor]: Add support for modle2vec embeddings (#28507) ... This PR add an embeddings integration for model2vec, the `Model2vecEmbeddings` class. - **Description**: [Model2Vec](https://github.com/MinishLab/model2vec) lets you turn any sentence transformer into a really small static model and makes running the model faster. - **Issue**: - **Dependencies**: model2vec ([pypi](https://pypi.org/project/model2vec/)) - **Twitter handle:**: - [x] **Add tests and docs**: - [Test](https://github.com/blacksmithop/langchain/blob/model2vec_embeddings/libs/community/langchain_community/embeddings/model2vec.py), [docs](https://github.com/blacksmithop/langchain/blob/model2vec_embeddings/docs/docs/integrations/text_embedding/model2vec.ipynb) - [x] **Lint and test**: --------- Co-authored-by: Abhinav KM <abhinav.m@zerone-consulting.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2024-12-09 02:17:22 +00:00