langchain_community.embeddings.huggingface.HuggingFaceInferenceAPIEmbeddings¶
- class langchain_community.embeddings.huggingface.HuggingFaceInferenceAPIEmbeddings[source]¶
Bases:
BaseModel,EmbeddingsEmbed texts using the HuggingFace API.
Requires a HuggingFace Inference API key and a model name.
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- param additional_headers: Dict[str, str] = {}¶
Pass additional headers to the requests library if needed.
- param api_key: SecretStr [Required]¶
Your API key for the HuggingFace Inference API.
- Constraints
type = string
writeOnly = True
format = password
- param api_url: Optional[str] = None¶
Custom inference endpoint url. None for using default public url.
- param model_name: str = 'sentence-transformers/all-MiniLM-L6-v2'¶
The name of the model to use for text embeddings.
- async aembed_documents(texts: List[str]) List[List[float]]¶
Asynchronous Embed search docs.
- Parameters
texts (List[str]) – List of text to embed.
- Returns
List of embeddings.
- Return type
List[List[float]]
- async aembed_query(text: str) List[float]¶
Asynchronous Embed query text.
- Parameters
text (str) – Text to embed.
- Returns
Embedding.
- Return type
List[float]
- embed_documents(texts: List[str]) List[List[float]][source]¶
Get the embeddings for a list of texts.
- Parameters
texts (Documents) – A list of texts to get embeddings for.
- Returns
- Embedded texts as List[List[float]], where each inner List[float]
corresponds to a single input text.
- Return type
List[List[float]]
Example
from langchain_community.embeddings import ( HuggingFaceInferenceAPIEmbeddings, ) hf_embeddings = HuggingFaceInferenceAPIEmbeddings( api_key="your_api_key", model_name="sentence-transformers/all-MiniLM-l6-v2" ) texts = ["Hello, world!", "How are you?"] hf_embeddings.embed_documents(texts)