Source code for langchain_community.embeddings.huggingface_hub

import json
from typing import Any, Dict, List, Optional

from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
from langchain_core.utils import get_from_dict_or_env

DEFAULT_MODEL = "sentence-transformers/all-mpnet-base-v2"
VALID_TASKS = ("feature-extraction",)


[docs]class HuggingFaceHubEmbeddings(BaseModel, Embeddings): """HuggingFaceHub embedding models. To use, you should have the ``huggingface_hub`` python package installed, and the environment variable ``HUGGINGFACEHUB_API_TOKEN`` set with your API token, or pass it as a named parameter to the constructor. Example: .. code-block:: python from langchain_community.embeddings import HuggingFaceHubEmbeddings model = "sentence-transformers/all-mpnet-base-v2" hf = HuggingFaceHubEmbeddings( model=model, task="feature-extraction", huggingfacehub_api_token="my-api-key", ) """ client: Any #: :meta private: model: Optional[str] = None """Model name to use.""" repo_id: Optional[str] = None """Huggingfacehub repository id, for backward compatibility.""" task: Optional[str] = "feature-extraction" """Task to call the model with.""" model_kwargs: Optional[dict] = None """Keyword arguments to pass to the model.""" huggingfacehub_api_token: Optional[str] = None class Config: """Configuration for this pydantic object.""" extra = Extra.forbid @root_validator() def validate_environment(cls, values: Dict) -> Dict: """Validate that api key and python package exists in environment.""" huggingfacehub_api_token = get_from_dict_or_env( values, "huggingfacehub_api_token", "HUGGINGFACEHUB_API_TOKEN" ) try: from huggingface_hub import InferenceClient if values["model"]: values["repo_id"] = values["model"] elif values["repo_id"]: values["model"] = values["repo_id"] else: values["model"] = DEFAULT_MODEL values["repo_id"] = DEFAULT_MODEL client = InferenceClient( model=values["model"], token=huggingfacehub_api_token, ) if values["task"] not in VALID_TASKS: raise ValueError( f"Got invalid task {values['task']}, " f"currently only {VALID_TASKS} are supported" ) values["client"] = client except ImportError: raise ImportError( "Could not import huggingface_hub python package. " "Please install it with `pip install huggingface_hub`." ) return values
[docs] def embed_documents(self, texts: List[str]) -> List[List[float]]: """Call out to HuggingFaceHub's embedding endpoint for embedding search docs. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. """ # replace newlines, which can negatively affect performance. texts = [text.replace("\n", " ") for text in texts] _model_kwargs = self.model_kwargs or {} responses = self.client.post( json={"inputs": texts, "parameters": _model_kwargs, "task": self.task} ) return json.loads(responses.decode())
[docs] def embed_query(self, text: str) -> List[float]: """Call out to HuggingFaceHub's embedding endpoint for embedding query text. Args: text: The text to embed. Returns: Embeddings for the text. """ response = self.embed_documents([text])[0] return response