Skip to main content

Cohere Embeddings with Weaviate

New Documentation

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

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

Configure a Weaviate vector index to use a Cohere embedding model, and Weaviate will generate embeddings for various operations using the specified model and your Cohere API key. This feature is called the vectorizer.

At import time, Weaviate generates text object embeddings and saves them into the index. For vector and hybrid search operations, Weaviate converts text queries into embeddings.

Embedding integration illustration

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the Cohere vectorizer integration (text2vec-cohere) 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 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.
import weaviate
from weaviate.auth import AuthApiKey
import os

# Recommended: save sensitive data as environment variables
cohere_key = os.getenv("COHERE_APIKEY")
headers = {
"X-Cohere-Api-Key": cohere_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
headers=headers
)

# Work with Weaviate

client.close()

Configure the vectorizer

Configure a Weaviate index to use a Cohere embedding model by setting the vectorizer as follows:

from weaviate.classes.config import Configure

client.collections.create(
"DemoCollection",
vectorizer_config=[
Configure.NamedVectors.text2vec_cohere(
name="title_vector",
source_properties=["title"]
)
],
# Additional parameters not shown
)

You can specify one of the available models for the vectorizer to use. The default model (embed-multilingual-v3.0) is used if no model is specified.

Data import

After configuring the vectorizer, import data into Weaviate. Weaviate generates embeddings for text objects using the specified model.

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

with collection.batch.dynamic() as batch:
for src_obj in source_objects:
weaviate_obj = {
"title": src_obj["title"],
"description": src_obj["description"],
}

# The model provider integration will automatically vectorize the object
batch.add_object(
properties=weaviate_obj,
# vector=vector # Optionally provide a pre-obtained vector
)
Re-use existing vectors

If you already have a compatible model vector available, you can provide it directly to Weaviate. This can be useful if you have already generated embeddings using the same model and want to use them in Weaviate, such as when migrating data from another system.

Searches

Once the vectorizer is configured, Weaviate will perform vector and hybrid search operations using the specified Cohere model.

Embedding integration at search illustration

When you perform a vector search, Weaviate converts the text query into an embedding using the specified model and returns the most similar objects from the database.

The query below returns the n most similar objects from the database, set by limit.

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

response = collection.query.near_text(
query="A holiday film", # The model provider integration will automatically vectorize the query
limit=2
)

for obj in response.objects:
print(obj.properties["title"])
What is a hybrid search?

A hybrid search performs a vector search and a keyword (BM25) search, before combining the results to return the best matching objects from the database.

When you perform a hybrid search, Weaviate converts the text query into an embedding using the specified model and returns the best scoring objects from the database.

The query below returns the n best scoring objects from the database, set by limit.

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

response = collection.query.hybrid(
query="A holiday film", # The model provider integration will automatically vectorize the query
limit=2
)

for obj in response.objects:
print(obj.properties["title"])

References

Vectorizer parameters

The following examples show how to configure Cohere-specific options.

from weaviate.classes.config import Configure

client.collections.create(
"DemoCollection",
vectorizer_config=[
Configure.NamedVectors.text2vec_cohere(
name="title_vector",
source_properties=["title"],
# Further options
# model="embed-multilingual-v3.0",
# truncate="END", # "NONE", "START" or "END"
# base_url="<custom_cohere_url>"
)
],
# Additional parameters not shown
)

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

Available models

  • embed-multilingual-v3.0 (Default)
  • embed-multilingual-light-v3.0
  • embed-multilingual-v2.0 (previously embed-multilingual-22-12)
  • embed-english-v3.0
  • embed-english-light-v3.0
  • embed-english-v2.0
  • embed-english-light-v2.0
Deprecated models

The following models are available, but deprecated:

  • multilingual-22-12
  • large
  • medium
  • small

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.

External resources

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