CohereTextEmbedder

Embeds strings using Cohere models. Use this component in query pipelines to transform the user query into a vector for embedding retrieval.

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.

Key Features

• Embeds text strings using Cohere's embedding models.
• Designed for query pipelines to enable embedding-based retrieval.
• Configurable input type for different use cases such as search queries or classification.
• Supports truncation of long inputs from the start or end.
• For a list of supported models, see the Cohere documentation.
• The embedding model must match the one used by CohereDocumentEmbedder in your index.

Configuration

Authentication

To use this component, connect Haystack Platform with Cohere first. For detailed instructions, see Use Cohere Models.

1. Drag the CohereTextEmbedder component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name, for example embed-english-v3.0.
4. Go to the Advanced tab to configure the API key, API base URL, input type, truncation, timeout, and embedding type.

Connections

CohereTextEmbedder accepts a text string as input. It outputs the embedding as a list of floats (embedding) and request metadata (meta).

Connect the text input to the pipeline's query input. Connect the embedding output to an embedding retriever such as OpenSearchEmbeddingRetriever.

Usage Example

Using the Component in a Pipeline

This is an example of a query pipeline with CohereTextEmbedder that receives a query to embed and then sends the embedded query to OpenSearchEmbeddingRetriever to find matching documents.

components:
  CohereTextEmbedder:
    type: haystack_integrations.components.embedders.cohere.text_embedder.CohereTextEmbedder
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - COHERE_API_KEY
        - CO_API_KEY
        strict: false
      model: embed-english-v2.0
      input_type: search_query
      api_base_url: https://api.cohere.com
      truncate: END
      use_async_client: false
      timeout: 120
      embedding_type:
  OpenSearchEmbeddingRetriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      filters:
      top_k: 10
      filter_policy: replace
      custom_query:
      raise_on_failure: true
      efficient_filtering: true
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: Standard-Index-English
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:

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

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - CohereTextEmbedder.text

Parameters

Inputs

Parameter	Type	Description
text	str	The text to embed.

Outputs

Parameter	Type	Default	Description
embedding	List[float]		The embedding of the text.
meta	Dict[str, Any]		Metadata about the request.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var(['COHERE_API_KEY', 'CO_API_KEY'])	The Cohere API key.
model	str	embed-english-v2.0	The name of the model to use. Choose a model from the list on the component card.
input_type	str	search_query	Specifies the type of input you're giving to the model. Supported values are "search_document", "search_query", "classification", and "clustering". Not required for older versions of the embedding models (meaning anything lower than v3), but is required for more recent versions (meaning anything bigger than v2).
api_base_url	str	https://api.cohere.com	The Cohere API base url.
truncate	str	END	Truncates embeddings that are too long from start or end, ("NONE"|"START"|"END"). Passing "START" discards the start of the input. "END" discards the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model. If "NONE" is selected, when the input exceeds the maximum input token length, an error is returned.
timeout	int	120	Request timeout in seconds.
embedding_type	Optional[EmbeddingTypes]	None	The type of embeddings to return. Defaults to float embeddings. Note that int8, uint8, binary, and ubinary are only valid for v3 models.

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.