SentenceTransformersTextEmbedder

Embed strings using Sentence Transformers models. Use this component in query pipelines to transform user queries into vectors for embedding-based retrieval.

Key Features

• Works with any model available on Hugging Face that is compatible with Sentence Transformers.
• Outputs a float vector embedding suitable for use with embedding retrievers.
• Supports multiple embedding precisions including float32, int8, uint8, binary, and ubinary.
• Supports model quantization and custom backends (PyTorch, ONNX, OpenVINO).
• The embedding model must match the one used by SentenceTransformersDocumentEmbedder in the indexing pipeline.

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.

Configuration

1. Drag the SentenceTransformersTextEmbedder component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Set the model to the Sentence Transformers model you want to use (for example, sentence-transformers/all-mpnet-base-v2).
   2. Optionally set a Hugging Face token if using private or gated models.
4. Go to the Advanced tab to configure prefix, suffix, normalize_embeddings, truncate_dim, precision, and backend.

Connections

SentenceTransformersTextEmbedder receives the user query as a text string, typically from the Input component. It outputs a float vector through its embedding output, which you connect to an embedding retriever such as OpenSearchEmbeddingRetriever.

Source Code

To check this component's source code, open sentence_transformers_text_embedder.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  SentenceTransformersTextEmbedder:
    type: haystack_integrations.components.embedders.sentence_transformers.SentenceTransformersTextEmbedder
    init_parameters:
      model: sentence-transformers/all-mpnet-base-v2
      normalize_embeddings: false
      progress_bar: true

Using the Component in a Pipeline

# haystack-pipeline
components:
  SentenceTransformersTextEmbedder:
    type: haystack_integrations.components.embedders.sentence_transformers.SentenceTransformersTextEmbedder
    init_parameters:
      model: sentence-transformers/all-mpnet-base-v2
      normalize_embeddings: false
      token:
        type: env_var
        env_vars:
        - HF_API_TOKEN
        - HF_TOKEN
        strict: false

  OpenSearchEmbeddingRetriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      top_k: 10
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: my-index
          embedding_dim: 768

connections:
- sender: SentenceTransformersTextEmbedder.embedding
  receiver: OpenSearchEmbeddingRetriever.query_embedding

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - SentenceTransformersTextEmbedder.text

Parameters

Inputs

Parameter	Type	Description
text	str	The text to embed.

Outputs

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

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str	sentence-transformers/all-mpnet-base-v2	The name of the Sentence Transformers model from Hugging Face.
device	Optional[ComponentDevice]	None	The device to run the model on. If not set, automatically detected.
token	Optional[Secret]	Secret.from_env_var(["HF_API_TOKEN", "HF_TOKEN"])	A Hugging Face token for accessing private or gated models.
prefix	str	""	A string to add at the beginning of the text before embedding.
suffix	str	""	A string to add at the end of the text before embedding.
batch_size	int	32	The number of texts to process in each batch.
progress_bar	bool	True	Whether to show a progress bar during embedding.
normalize_embeddings	bool	False	Whether to normalize embedding vectors to unit length.
trust_remote_code	bool	False	Whether to trust remote code when loading models with custom code.
local_files_only	bool	False	Whether to use only local files, without downloading from Hugging Face.
truncate_dim	Optional[int]	None	The dimension to truncate the embedding to.
model_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments passed to the model constructor.
tokenizer_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for the tokenizer.
config_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for the model configuration.
precision	Literal["float32", "int8", "uint8", "binary", "ubinary"]	"float32"	The precision of the output embeddings.
encode_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for the encode() method.
backend	Literal["torch", "onnx", "openvino"]	"torch"	The backend to use for inference.
revision	Optional[str]	None	The model revision to use.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
text	str		The text to embed.

Related Information

• Pipeline Components