You can use Cohere's embedding and ranking models as well as LLMs. For a full list of supported models, see Cohere documentation.

Prerequisites

You need an active Cohere API key to use Cohere's models.

Use Cohere Models

First, connect deepset Cloud to Cohere through the Connections page:

Click your initials in the top right corner and select Connections.
Click Connect next to the provider.
Enter your user access token and submit it.

Then, add a component that uses a Cohere model to your pipeline. Here are the components by the model type they use:

Embedding models:
- CohereTextEmbedder: Calculates embeddings for text, like query. Often used in query pipelines to embed a query and pass the embedding to an embedding retriever.
- CohereDocumentEmbedder: Calculates embeddings for documents. Often used in indexing pipeline to embed documents and pass them to DocumentWriter.

ℹ️
Embedding Models in Query and Indexing Pipelines
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.

LLMs:
- CohereGenerator: Generates text using a Cohere model, often used in RAG pipelines.
Ranking models:
- CohereRanker: Ranks documents based on their similarity to the query. Often used in query pipelines to rank documents from the retriever and pass them on to PromptBuilder.

Usage Examples

This is an example of how to use Cohere's embedding and ranking models and an LLM in indexing and query pipelines (each in a separate tab):

components:
  ...
    splitter:
      type: haystack.components.preprocessors.document_splitter.DocumentSplitter
      init_parameters:
        split_by: word
        split_length: 250
        split_overlap: 30

    document_embedder:
      type: haystack_integrations.components.embedders.cohere.document_embedder.CohereDocumentEmbedder
      init_parameters: 
        model: embed-english-v3.0

    writer:
      type: haystack.components.writers.document_writer.DocumentWriter
      init_parameters:
        document_store:
          type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
          init_parameters:
            embedding_dim: 768
            similarity: cosine
        policy: OVERWRITE
        
connections:  # Defines how the components are connected
  ...
  - sender: splitter.documents
    receiver: document_embedder.documents
  - sender: document_embedder.documents
    receiver: writer.documents

components:
  ...
    query_embedder:
      type: haystack_integrations.components.embedders.cohere.text_embedder.CohereTextEmbedder
      init_parameters:
        model: embed-english-v3.0
        
    retriever:
      type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
      init_parameters: 
        document_store:
          init_parameters:
            use_ssl: True
            verify_certs: False
            http_auth:
              - "${OPENSEARCH_USER}"
              - "${OPENSEARCH_PASSWORD}"
          type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        top_k: 20 
       
      ranker:
        type: haystack_integrations.components.rankers.cohere.ranker.CohereRanker
        init_parameters:
          model: rerank-english-v3.0
        
    prompt_builder:
      type: haystack.components.builders.prompt_builder.PromptBuilder
      init_parameters:
        template: |-
          You are a technical expert.
          You answer questions truthfully based on provided documents.
          For each document check whether it is related to the question.
          Only use documents that are related to the question to answer it.
          Ignore documents that are not related to the question.
          If the answer exists in several documents, summarize them.
          Only answer based on the documents provided. Don't make things up.
          If the documents can't answer the question or you are unsure say: 'The answer can't be found in the text'.
          These are the documents:
          {% for document in documents %}
          Document[{{ loop.index }}]:
          {{ document.content }}
          {% endfor %}
          Question: {{question}}
          Answer:

    generator:
      type: haystack_integrations.components.generators.cohere.generator.CohereGenerator
      init_parameters:
         generation_kwargs:
         temperature: 0.0
         model: command
          
    answer_builder:
      init_parameters: {}
      type: haystack.components.builders.answer_builder.AnswerBuilder
   
      ...
      
  connections:  # Defines how the components are connected
  ...
  - sender: query_embedder.embedding # AmazonBedrockTextEmbedder sends the embedded query to the retriever
    receiver: retriever.query_embedding 
  - sender: retriever.documents
    receiver: ranker.documents
  - sender: ranker.documents
    receiver: prompt_builder.documents
  - sender: prompt_builder.prompt
    receiver: generator.prompt
  - sender: generator.replies
    receiver: answer_builder.replies
    ...
    
  inputs:
   query:
   ..
   - "query_embedder.text" # TextEmbedder needs query as input and it's not getting it
   - "retriever.query"     # from any component it's connected to, so it needs to receive it from the pipeline.
   - "prompt_builder.question"
   - "answer_builder.query"  
   - "ranker.query"
	
    ...													 
   ...

This is where you pass the model in these components in Pipeline Builder:

Prerequisites

Use Cohere Models

ℹ️Embedding Models in Query and Indexing Pipelines

Usage Examples

ℹ️
Embedding Models in Query and Indexing Pipelines