CohereDocumentEmbedder

Calculate document embeddings using Cohere models. Use this component in indexing pipelines to embed documents before writing them to a document store.

Key Features

Uses Cohere models to embed a list of documents.
Adds the computed embeddings to the document's embedding metadata field.
Supports multiple Cohere embedding models. For a full list, see the Cohere documentation.
Configurable batch size and progress bar for large document sets.
Supports embedding additional metadata fields alongside document content.

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

Drag the CohereDocumentEmbedder component onto the canvas from the Component Library.
Click on the component to open the configuration panel.
On the General tab:
1. Select the embedding model to use. Make sure Haystack Platform is connected to your Cohere account. For details, see Use Cohere Models.
2. Set the input_type to search_document for indexing pipelines.
Go to the Advanced tab to configure additional settings such as truncate, timeout, batch_size, meta_fields_to_embed, and embedding_type.

Connections

CohereDocumentEmbedder receives documents from converters such as TextFileToDocument or preprocessors such as DocumentSplitter. It outputs embedded documents through its documents output, which you connect to DocumentWriter to write them into a document store.

Source Code

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

Usage Examples

Basic Configuration

  CohereDocumentEmbedder:
    type: haystack_integrations.components.embedders.cohere.document_embedder.CohereDocumentEmbedder
    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_document
      api_base_url: https://api.cohere.com
      truncate: END
      use_async_client: false
      timeout: 120
      batch_size: 32
      progress_bar: true
      embedding_separator: \n

Using the Component in an Index

In this index, CohereDocumentEmbedder receives documents from DocumentSplitter and embeds them. It then sends the embedded documents to DocumentWriter that writes them into a document store. The index is configured to use the embed-english-v2.0 model, which means CohereTextEmbedder used in the query pipeline must also use the embed-english-v2.0 model.

components:
  DocumentSplitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: word
      split_length: 200
      split_overlap: 0
      split_threshold: 0
      splitting_function:
  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: Standard-Index-English
          max_chunk_bytes: 104857600
          embedding_dim: 1024
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
          similarity: cosine
      policy: NONE

  CohereDocumentEmbedder:
    type: haystack_integrations.components.embedders.cohere.document_embedder.CohereDocumentEmbedder
    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_document
      api_base_url: https://api.cohere.com
      truncate: END
      use_async_client: false
      timeout: 120
      batch_size: 32
      progress_bar: true
      meta_fields_to_embed:
      embedding_separator: \n
      embedding_type:
  TextFileToDocument:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8
      store_full_path: false

connections:
- sender: DocumentSplitter.documents
  receiver: CohereDocumentEmbedder.documents
- sender: CohereDocumentEmbedder.documents
  receiver: DocumentWriter.documents

- sender: TextFileToDocument.documents
  receiver: DocumentSplitter.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - TextFileToDocument.sources

Parameters

Inputs

Parameter	Type	Default	Description
documents	List[Document]		Documents to embed.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		Documents with their embeddings added to `embedding` field.
meta	Dict[str, Any]		Metadata related to the embedding process.

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. Supported Models are: `"embed-english-v3.0"`, `"embed-english-light-v3.0"`, `"embed-multilingual-v3.0"`, `"embed-multilingual-light-v3.0"`, `"embed-english-v2.0"`, `"embed-english-light-v2.0"`, `"embed-multilingual-v2.0"`. For supported models, see Cohere model documentation.
input_type	str	search_document	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 any model lower than v3), but is required for more recent versions (meaning any model later than v2).
api_base_url	str	https://api.cohere.com	The Cohere API Base url.
truncate	str	END	Truncate 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.
batch_size	int	32	The number of Documents to encode at once.
progress_bar	bool	True	Whether to show a progress bar or not. Can be helpful to disable in production deployments to keep the logs clean.
meta_fields_to_embed	Optional[List[str]]	None	List of meta fields that should be embedded along with the Document text.
embedding_separator	str	\n	Separator used to concatenate the meta fields to the Document text.
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
documents	List[Document]		Documents to embed.

Was this page helpful?

Key Features​

Embedding Models in Query Pipelines and Indexes

Configuration​

Connections​

Source Code​

Usage Examples​

Basic Configuration​

Using the Component in an Index​

Parameters​

Inputs​

Outputs​

Init Parameters​

Run Method Parameters​

Related Information​