HuggingFaceEmbeddings Class — langchain Architecture

Architecture documentation for the HuggingFaceEmbeddings class in huggingface.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  bc29a19b_53a3_8e06_ab58_d933298d898b["HuggingFaceEmbeddings"]
  b1e4f760_c634_d3bf_ca9a_db7ab899cc4a["Embeddings"]
  bc29a19b_53a3_8e06_ab58_d933298d898b -->|extends| b1e4f760_c634_d3bf_ca9a_db7ab899cc4a
  012ca17f_7b56_304b_ccc3_cc98348f8542["huggingface.py"]
  bc29a19b_53a3_8e06_ab58_d933298d898b -->|defined in| 012ca17f_7b56_304b_ccc3_cc98348f8542
  6f8d5d0a_4a99_c3be_d269_1921338dc479["__init__()"]
  bc29a19b_53a3_8e06_ab58_d933298d898b -->|method| 6f8d5d0a_4a99_c3be_d269_1921338dc479
  b7c83ab3_15c9_f495_f1c6_d2b68282f2a6["_embed()"]
  bc29a19b_53a3_8e06_ab58_d933298d898b -->|method| b7c83ab3_15c9_f495_f1c6_d2b68282f2a6
  6c6f5815_8b28_d2f4_cafa_af0cebf3ee04["embed_documents()"]
  bc29a19b_53a3_8e06_ab58_d933298d898b -->|method| 6c6f5815_8b28_d2f4_cafa_af0cebf3ee04
  1f5cc8d7_bd9b_af04_9e37_b08ce61f8ec2["embed_query()"]
  bc29a19b_53a3_8e06_ab58_d933298d898b -->|method| 1f5cc8d7_bd9b_af04_9e37_b08ce61f8ec2

Relationship Graph

Source Code

libs/partners/huggingface/langchain_huggingface/embeddings/huggingface.py lines 18–172

class HuggingFaceEmbeddings(BaseModel, Embeddings):
    """HuggingFace sentence_transformers embedding models.

    To use, you should have the `sentence_transformers` python package installed.

    Example:
        ```python
        from langchain_huggingface import HuggingFaceEmbeddings

        model_name = "sentence-transformers/all-mpnet-base-v2"
        model_kwargs = {"device": "cpu"}
        encode_kwargs = {"normalize_embeddings": False}
        hf = HuggingFaceEmbeddings(
            model_name=model_name,
            model_kwargs=model_kwargs,
            encode_kwargs=encode_kwargs,
        )
        ```
    """

    model_name: str = Field(
        default="sentence-transformers/all-mpnet-base-v2", alias="model"
    )
    """Model name to use."""
    cache_folder: str | None = None
    """Path to store models.
    Can be also set by SENTENCE_TRANSFORMERS_HOME environment variable."""
    model_kwargs: dict[str, Any] = Field(default_factory=dict)
    """Keyword arguments to pass to the Sentence Transformer model, such as `device`,
    `prompts`, `default_prompt_name`, `revision`, `trust_remote_code`, or `token`.
    See also the Sentence Transformer documentation: https://sbert.net/docs/package_reference/SentenceTransformer.html#sentence_transformers.SentenceTransformer"""
    encode_kwargs: dict[str, Any] = Field(default_factory=dict)
    """Keyword arguments to pass when calling the `encode` method for the documents of
    the Sentence Transformer model, such as `prompt_name`, `prompt`, `batch_size`,
    `precision`, `normalize_embeddings`, and more.
    See also the Sentence Transformer documentation: https://sbert.net/docs/package_reference/SentenceTransformer.html#sentence_transformers.SentenceTransformer.encode"""
    query_encode_kwargs: dict[str, Any] = Field(default_factory=dict)
    """Keyword arguments to pass when calling the `encode` method for the query of
    the Sentence Transformer model, such as `prompt_name`, `prompt`, `batch_size`,
    `precision`, `normalize_embeddings`, and more.
    See also the Sentence Transformer documentation: https://sbert.net/docs/package_reference/SentenceTransformer.html#sentence_transformers.SentenceTransformer.encode"""
    multi_process: bool = False
    """Run encode() on multiple GPUs."""
    show_progress: bool = False
    """Whether to show a progress bar."""

    def __init__(self, **kwargs: Any):
        """Initialize the sentence_transformer."""
        super().__init__(**kwargs)
        try:
            import sentence_transformers  # type: ignore[import]
        except ImportError as exc:
            msg = (
                "Could not import sentence_transformers python package. "
                "Please install it with `pip install sentence-transformers`."
            )
            raise ImportError(msg) from exc

        if self.model_kwargs.get("backend", "torch") == "ipex":
            if not is_optimum_intel_available() or not is_ipex_available():
                msg = f"Backend: ipex {IMPORT_ERROR.format('optimum[ipex]')}"
                raise ImportError(msg)

            if is_optimum_intel_version("<", _MIN_OPTIMUM_VERSION):
                msg = (
                    f"Backend: ipex requires optimum-intel>="
                    f"{_MIN_OPTIMUM_VERSION}. You can install it with pip: "
                    "`pip install --upgrade --upgrade-strategy eager "
                    "`optimum[ipex]`."
                )
                raise ImportError(msg)

            from optimum.intel import IPEXSentenceTransformer  # type: ignore[import]

            model_cls = IPEXSentenceTransformer

        else:
            model_cls = sentence_transformers.SentenceTransformer

        self._client = model_cls(
            self.model_name, cache_folder=self.cache_folder, **self.model_kwargs