huggingface.py — langchain Source File

Source Code

from __future__ import annotations

from typing import Any

from langchain_core.embeddings import Embeddings
from pydantic import BaseModel, ConfigDict, Field

from langchain_huggingface.utils.import_utils import (
    IMPORT_ERROR,
    is_ipex_available,
    is_optimum_intel_available,
    is_optimum_intel_version,
)

_MIN_OPTIMUM_VERSION = "1.22"


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."""
// ... (113 more lines)