Skip to main content

Text Embeddings

Added in v1.26.3

Databricks Embeddings with Weaviate

Weaviate's integration with Databricks' APIs allows you to access models hosted on their platform directly from Weaviate.

Configure a Weaviate vector index to use a Databricks embedding model, and Weaviate will generate embeddings for various operations using the specified endpoint and your Databricks token. 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 Databricks vectorizer integration (text2vec-databricks) module.

For Weaviate Cloud (WCD) users

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

For self-hosted users

Databricks Personal Access Token​

You must provide a valid Databricks Personal Access Token (PAT) to Weaviate for this integration. Refer to the Databricks documentation for instructions on generating your PAT in your workspace.

Provide the Dataricks token to Weaviate using one of the following methods:

  • Set the DATABRICKS_TOKEN environment variable that is available to Weaviate.
  • Provide the token at runtime, as shown in the examples below.
import weaviate
from weaviate.classes.init import Auth
import os

# Recommended: save sensitive data as environment variables
databricks_key = os.getenv("DATABRICKS_TOKEN")
headers = {
    "X-Databricks-Token": databricks_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()

Configure the vectorizer​

Configure a Weaviate index to use a Databricks serving model endpoint by setting the vectorizer as follows:

from weaviate.classes.config import Configure

databricks_vectorizer_endpoint = os.getenv("DATABRICKS_VECTORIZER_ENDPOINT")
client.collections.create(
    "DemoCollection",
    vectorizer_config=[
        Configure.NamedVectors.text2vec_databricks(
            name="title_vector",
            source_properties=["title"],
            endpoint = databricks_vectorizer_endpoint,
        )
    ],
    # Additional parameters not shown
)

This will configure Weaviate to use the vectorizer served through the endpoint you specify.

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 model.

Embedding integration at search illustration

Vector (near text) search​

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​

  • endpoint: The URL of the embedding model hosted on Databricks.
  • instruction:An optional instruction to pass to the embedding model.

For further details on model parameters, see the Databricks documentation.

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. See the following model-agnostic examples:

  • 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​

Questions and feedback​

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