Contextual AI Reranker Models with Weaviate

Added in v1.34.0

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

Configure a Weaviate collection to use a Contextual AI reranker model, and Weaviate will use the specified model and your Contextual AI 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.

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the Contextual AI reranker integration (reranker-contextualai) module.

For Weaviate Cloud (WCD) users

This integration is enabled by default on Weaviate Cloud (WCD) serverless instances.

For self-hosted users

• Check the cluster metadata to verify if the module is enabled.
• Follow the how-to configure modules guide to enable the module in Weaviate.

API credentials

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

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

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

PythonJavaScript/TypeScript

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

import weaviate
from weaviate.classes.init import Auth
import os

# Recommended: save sensitive data as environment variables
contextual_key = os.getenv("CONTEXTUAL_API_KEY")
headers = {
    "X-ContextualAI-Api-Key": contextual_key,
}

client = weaviate.connect_to_weaviate_cloud(
    cluster_url=weaviate_url,                       # `weaviate_url`: your Weaviate URL
    auth_credentials=Auth.api_key(weaviate_key),      # `weaviate_key`: your Weaviate API key
    headers=headers
)

# Work with Weaviate

client.close()

import weaviate from 'weaviate-client'

const contextualApiKey = process.env.CONTEXTUAL_API_KEY || '';  // Replace with your inference API key

const client = await weaviate.connectToWeaviateCloud(
  'WEAVIATE_INSTANCE_URL',  // Replace with your instance URL
  {
    authCredentials: new weaviate.ApiKey('WEAVIATE_INSTANCE_APIKEY'),
    headers: {
      'X-ContextualAI-Api-Key': contextualApiKey,
    }
  }
)

// Work with Weaviate

client.close()

Configure the reranker

Reranker model integration mutable from v1.25.23, v1.26.8 and v1.27.1

A collection's reranker model integration configuration is mutable from v1.25.23, v1.26.8 and v1.27.1. See this section for details on how to update the collection configuration.

Configure a Weaviate collection to use a Contextual AI reranker model as follows:

PythonJavaScript/TypeScript

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    reranker_config=Configure.Reranker.contextualai()
    # Additional parameters not shown
)

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

Reranker parameters

Configure the reranker behavior, including the model to use, through the following parameters:

PythonJavaScript/TypeScript

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    reranker_config=Configure.Reranker.contextualai(
        model="ctxl-rerank-v2-instruct-multilingual",
        instruction="Prioritize internal sales documents over market analysis reports. More recent documents should be weighted higher.",
        top_n=5
    )
    # Additional parameters not shown
)

await client.collections.create({
  name: 'DemoCollection',
  reranker: weaviate.configure.reranker.contextualai({
    model: 'ctxl-rerank-v2-instruct-multilingual',
    instruction: 'Prioritize internal sales documents over market analysis reports. More recent documents should be weighted higher.',
    topN: 5,
  }),
});

The default model is used if no model is specified.

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

Header parameters

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-ContextualAI-Api-Key: The Contextual AI API key.

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

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

Reranking query

Once the reranker is configured, Weaviate performs reranking operations using the specified Contextual AI 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.

PythonJavaScript/TypeScript

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.query import Rerank

collection = 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']);
}

Available models

• ctxl-rerank-v1-instruct
• ctxl-rerank-v2-instruct-multilingual-mini
• ctxl-rerank-v2-instruct-multilingual (default)

Further resources

Other integrations

• Contextual AI generative models + Weaviate.

Code examples

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.

References

• Contextual AI Rerank API documentation

Questions and feedback

If you have any questions or feedback, let us know in the user forum.

Technical questions

If you have questions feel free to post on our Community forum.

Documentation feedback

Leave feedback by opening a GitHub issue.