HuggingFaceAPITextEmbedder

Embed strings using Hugging Face APIs.

Basic Information

• Type: haystack.components.embedders.hugging_face_api_text_embedder.HuggingFaceAPITextEmbedder
• Components it can connect with:
  • Retrievers: HuggingFaceAPITextEmbedder can send embeddings to retrievers for semantic search.
  • Input: HuggingFaceAPITextEmbedder can receive query text to embed from the Input component.

Inputs

Parameter	Type	Default	Description
text	str		Text to embed.

Outputs

Parameter	Type	Default	Description
embedding	List[float]		The embedding of the input text.

Overview

HuggingFaceAPITextEmbedder embeds strings using Hugging Face APIs. Use it to embed queries for semantic search in retrieval pipelines.

info

This component embeds plain text. To embed a list of documents, use HuggingFaceAPIDocumentEmbedder.

Embedding Models in Query Pipelines and Indexes

The embedding model you use to embed documents in your indexing pipeline must be the same as the embedding model you use to embed the query in your query pipeline.

This means the embedders for your indexing and query pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

You can use it with the following Hugging Face APIs:

• Free Serverless Inference API: Experiment with models hosted on Hugging Face Hub. It's rate-limited and not meant for production.
• Paid Inference Endpoints: A private instance of the model deployed by Hugging Face.
• Self-hosted Text Embeddings Inference: A toolkit for efficiently deploying and serving text embedding models on-premise.

Authorization

Connect Haystack Platform to your Hugging Face account on the Integrations page. For detailed instructions, see Use Hugging Face Models. A token is required for the Serverless Inference API and Inference Endpoints.

Usage Example

Using the component in a pipeline

This query pipeline uses HuggingFaceAPITextEmbedder to embed a query and retrieve documents using semantic search:

components:
  query_embedder:
    type: haystack.components.embedders.hugging_face_api_text_embedder.HuggingFaceAPITextEmbedder
    init_parameters:
      api_type: serverless_inference_api
      api_params:
        model: BAAI/bge-small-en-v1.5
      token:
        type: env_var
        env_vars:
          - HF_API_TOKEN
          - HF_TOKEN
        strict: false
      prefix:
      suffix:
      truncate: true
      normalize: false

  embedding_retriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
            - ${OPENSEARCH_HOST}
          http_auth:
            - ${OPENSEARCH_USER}
            - ${OPENSEARCH_PASSWORD}
          use_ssl: true
          verify_certs: false
      top_k: 20

connections:
  - sender: query_embedder.embedding
    receiver: embedding_retriever.query_embedding

inputs:
  query:
    - query_embedder.text
  filters:
    - embedding_retriever.filters

outputs:
  documents: embedding_retriever.documents

Parameters

Init parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_type	Union[HFEmbeddingAPIType, str]		The type of Hugging Face API to use. Options: serverless_inference_api, inference_endpoints, text_embeddings_inference.
api_params	Dict[str, str]		A dictionary containing either model (Hugging Face model ID, required for serverless_inference_api) or url (URL of the inference endpoint, required for inference_endpoints or text_embeddings_inference).
token	Optional[Secret]	Secret.from_env_var(['HF_API_TOKEN', 'HF_TOKEN'], strict=False)	The Hugging Face token to use as HTTP bearer authorization. Check your HF token in your account settings.
prefix	str		A string to add at the beginning of each text.
suffix	str		A string to add at the end of each text.
truncate	Optional[bool]	True	Truncates the input text to the maximum length supported by the model. Applicable when api_type is text_embeddings_inference or inference_endpoints if the backend uses Text Embeddings Inference. Ignored for serverless_inference_api.
normalize	Optional[bool]	False	Normalizes the embeddings to unit length. Applicable when api_type is text_embeddings_inference or inference_endpoints if the backend uses Text Embeddings Inference. Ignored for serverless_inference_api.

Run method parameters

These are the parameters you can configure for the run() method. You can pass these parameters at query time through the API, in Playground, or when running a job.

Parameter	Type	Default	Description
text	str		Text to embed.