langchain-huggingface: use separate kwargs for queries and docs

[Samoed]

Now encode_kwargs used for both for documents and queries and this leads to wrong embeddings. E. g.:

    model_kwargs = {"device": "cuda", "trust_remote_code": True}
    encode_kwargs = {"normalize_embeddings": False, "prompt_name": "s2p_query"}

    model = HuggingFaceEmbeddings(
        model_name="dunzhang/stella_en_400M_v5",
        model_kwargs=model_kwargs,
        encode_kwargs=encode_kwargs,
    )

    query_embedding = np.array(
        model.embed_query("What are some ways to reduce stress?",)
    )
    document_embedding = np.array(
        model.embed_documents(
            [
                "There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.",
                "Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.",
            ]
        )
    )
    print(model._client.similarity(query_embedding, document_embedding)) # output: tensor([[0.8421, 0.3317]], dtype=torch.float64)

But from the model card expexted like this:

    model_kwargs = {"device": "cuda", "trust_remote_code": True}
    encode_kwargs = {"normalize_embeddings": False}
    query_encode_kwargs = {"normalize_embeddings": False, "prompt_name": "s2p_query"}

    model = HuggingFaceEmbeddings(
        model_name="dunzhang/stella_en_400M_v5",
        model_kwargs=model_kwargs,
        encode_kwargs=encode_kwargs,
        query_encode_kwargs=query_encode_kwargs,
    )

    query_embedding = np.array(
        model.embed_query("What are some ways to reduce stress?", )
    )
    document_embedding = np.array(
        model.embed_documents(
            [
                "There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.",
                "Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.",
            ]
        )
    )
    print(model._client.similarity(query_embedding, document_embedding)) # tensor([[0.8398, 0.2990]], dtype=torch.float64)

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		Nov 5, 2024 3:08pm

[vbarda]

consider making private

[Samoed]

@vbarda Done!

[Samoed]

@vbarda Can you merge this PR, please?