Reranker

Weaviate's integration with Cohere's APIs allows you to access their models' capabilities directly from Weaviate.

Configure a Weaviate collection to use a Cohere reranker model, and Weaviate will use the specified model and your Cohere API key to rerank search results.

This two-step process involves Weaviate first performing a search and then reranking the results using the specified model.

Your Weaviate instance must be configured with the Cohere reranker integration (reranker-cohere) module.

You must provide a valid Cohere API key to Weaviate for this integration. Go to Cohere to sign up and obtain an API key.

Provide the API key to Weaviate using one of the following methods:

• Set the COHERE_APIKEY environment variable that is available to Weaviate.
• Provide the API key at runtime, as shown in the examples below.

# Recommended: save sensitive data as environment variables
cohere_key = os.getenv("COHERE_API_KEY")

const cohereApiKey = process.env.COHERE_API_KEY || '';  // Replace with your inference API key

Configure a Weaviate collection to use a Cohere reranker model as follows:

from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    reranker_config=Configure.Reranker.cohere()    # Additional parameters not shown)

await client.collections.create({  name: 'DemoCollection',  reranker: weaviate.configure.reranker.cohere(),});

You can specify which model Weaviate uses, as shown in the following configuration example:

from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    reranker_config=Configure.Reranker.cohere(        model="rerank-english-v3.0"    )    # Additional parameters not shown)

await client.collections.create({  name: 'DemoCollection',  reranker: weaviate.configure.reranker.cohere({    model: 'rerank-english-v3.0',  }),});

The default model is used if no model is specified.

You can provide the API key as well as some optional parameters at runtime through additional headers in the request. The following headers are available:

• X-Cohere-Api-Key: The Cohere API key.
• X-Cohere-Baseurl: The base URL to use (e.g. a proxy) instead of the default Cohere URL.

Any additional headers provided at runtime will override the existing Weaviate configuration.

Provide the headers as shown in the API credentials examples above.

Once the reranker is configured, Weaviate performs reranking operations using the specified Cohere model.

More specifically, Weaviate performs an initial search, then reranks the results using the specified model.

Any search in Weaviate can be combined with a reranker to perform reranking operations.

from weaviate.classes.query import Rerankcollection = client.collections.use("DemoCollection")response = collection.query.near_text(    query="A holiday film",  # The model provider integration will automatically vectorize the query    limit=2,    rerank=Rerank(        prop="title",                   # The property to rerank on        query="A melodic holiday film"  # If not provided, the original query will be used    ))for obj in response.objects:    print(obj.properties["title"])

let myCollection = client.collections.use('DemoCollection');const results = await myCollection.query.nearText(  ['A holiday film'],  {    limit: 2,    rerank: {      property: 'title',                // The property to rerank on      query: 'A melodic holiday film'   // If not provided, the original query will be used    }  });for (const obj of results.objects) {  console.log(obj.properties['title']);}

Weaviate does not validate the model name, so you can set any model that your Cohere account can reach. Name validation was removed in v1.33.0, and backported to v1.31.17 and v1.32.10.

The server default is rerank-v3.5.

See the Cohere model documentation for the list of available models.

You can also specify a fine-tuned reranker by its model ID, for example 500df123-afr3-.... For details, see Fine-Tuning Cohere's Reranker.

For further details on model parameters, see the Cohere API documentation.

• Cohere text embedding models + Weaviate.
• Cohere multimodal embedding models + Weaviate.
• Cohere generative models + Weaviate.

Once the integrations are configured at the collection, the data management and search operations in Weaviate work identically to any other collection. See the following model-agnostic examples:

• The How-to: Manage collections and How-to: Manage objects guides show how to perform data operations (i.e. create, read, update, delete collections and objects within them).
• The How-to: Query & Search guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.

• Cohere Rerank API documentation

Have a question or feedback? Here's how to reach us.