Skip to main content


New Documentation

The model provider integration pages are new and still undergoing improvements. We appreciate any feedback on this forum thread.

Voyage AI reranker models with Weaviate

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

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

Reranker integration illustration


Weaviate configuration

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

For Weaviate Cloud (WCD) users

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

For self-hosted users

API credentials

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

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

  • Set the VOYAGEAI_APIKEY environment variable that is available to Weaviate.
  • Provide the API key at runtime, as shown in the examples below.
import weaviate
from weaviate.auth import AuthApiKey
import os

# Recommended: save sensitive data as environment variables
voyageai_key = os.getenv("VOYAGEAI_APIKEY")
headers = {
"X-VoyageAI-Api-Key": voyageai_key,

client = weaviate.connect_to_wcs(
cluster_url=weaviate_url, # `weaviate_url`: your Weaviate URL
auth_credentials=AuthApiKey(weaviate_key), # `weaviate_key`: your Weaviate API key

# Work with Weaviate


Configure the reranker

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

# # This parameter is optional
# model="rerank-lite-1"
# Additional parameters not shown

You can specify one of the available models for the reranker to use. Currently, rerank-lite-1 is the only available model.

Reranking query

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

Reranker integration illustration

from weaviate.classes.query import Rerank

collection = client.collections.get("DemoCollection")

response = collection.query.near_text(
query="A holiday film", # The model provider integration will automatically vectorize the query
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:


Available models

  • rerank-lite-1

Further resources

Other integrations

Code examples

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

  • The how-to: manage data guides show how to perform data operations (i.e. create, update, delete).
  • The how-to: search guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.


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