Source code for langchain_huggingface.embeddings.huggingface

from typing import Any, Dict, List, Optional  # type: ignore[import-not-found]

from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, Field

DEFAULT_MODEL_NAME = "sentence-transformers/all-mpnet-base-v2"


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

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

    Example:
        .. code-block:: 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
            )
    """

    client: Any  #: :meta private:
    model_name: str = DEFAULT_MODEL_NAME
    """Model name to use."""
    cache_folder: Optional[str] = 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 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:
            raise ImportError(
                "Could not import sentence_transformers python package. "
                "Please install it with `pip install sentence-transformers`."
            ) from exc

        self.client = sentence_transformers.SentenceTransformer(
            self.model_name, cache_folder=self.cache_folder, **self.model_kwargs
        )

    class Config:
        """Configuration for this pydantic object."""

        extra = "forbid"

    def embed_documents(self, texts: List[str]) -> List[List[float]]:
        """Compute doc embeddings using a HuggingFace transformer model.

        Args:
            texts: The list of texts to embed.

        Returns:
            List of embeddings, one for each text.
        """
        import sentence_transformers  # type: ignore[import]

        texts = list(map(lambda x: x.replace("\n", " "), texts))
        if self.multi_process:
            pool = self.client.start_multi_process_pool()
            embeddings = self.client.encode_multi_process(texts, pool)
            sentence_transformers.SentenceTransformer.stop_multi_process_pool(pool)
        else:
            embeddings = self.client.encode(
                texts, show_progress_bar=self.show_progress, **self.encode_kwargs
            )

        return embeddings.tolist()

    def embed_query(self, text: str) -> List[float]:
        """Compute query embeddings using a HuggingFace transformer model.

        Args:
            text: The text to embed.

        Returns:
            Embeddings for the text.
        """
        return self.embed_documents([text])[0]