Generative AI

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

Configure a Weaviate collection to use a generative AI model with Databricks. Weaviate will perform retrieval augmented generation (RAG) using the specified endpoint and your Databricks token.

More specifically, Weaviate will perform a search, retrieve the most relevant objects, and then pass them to the Databricks generative model to generate outputs.

Your Weaviate instance must be configured with the Databricks generative AI integration (generative-databricks) module.

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 Databricks 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.

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

const databricksToken = process.env.DATABRICKS_TOKEN || '';  // Replace with your inference API key

Configure a Weaviate collection to use a Databricks generative AI endpoint as follows:

from weaviate.classes.config import Configuredatabricks_generative_endpoint = os.getenv("DATABRICKS_GENERATIVE_ENDPOINT")client.collections.create(    "DemoCollection",    generative_config=Configure.Generative.databricks(endpoint=databricks_generative_endpoint)    # Additional parameters not shown)

const databricksGenerativeEndpoint = process.env.DATABRICKS_VECTORIZER_ENDPOINT || '';  // If saved as an environment variableawait client.collections.create({  name: 'DemoCollection',  generative: weaviate.configure.generative.databricks({    endpoint: databricksGenerativeEndpoint,  // Required for Databricks  }),  // Additional parameters not shown});

This will configure Weaviate to use the generative AI model served through the endpoint you specify.

Configure the following generative parameters to customize the model behavior.

from weaviate.classes.config import Configuredatabricks_generative_endpoint = os.getenv("DATABRICKS_GENERATIVE_ENDPOINT")client.collections.create(    "DemoCollection",    generative_config=Configure.Generative.databricks(        endpoint=databricks_generative_endpoint        # # These parameters are optional        # max_tokens=500,        # temperature=0.7,        # top_p=0.7,        # top_k=0.1    )    # Additional parameters not shown)

const databricksGenerativeEndpoint = process.env.DATABRICKS_VECTORIZER_ENDPOINT || '';  // If saved as an environment variable

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

Aside from setting the default model provider when creating the collection, you can also override it at query time.

from weaviate.classes.config import Configurefrom weaviate.classes.generate import GenerativeConfigcollection = client.collections.use("DemoCollection")response = collection.generate.near_text(    query="A holiday film",    limit=2,    grouped_task="Write a tweet promoting these two movies",    generative_provider=GenerativeConfig.databricks(        # # These parameters are optional        # max_tokens=500,        # temperature=0.7,        # top_p=0.7,        # top_k=0.1    ),    # Additional parameters not shown)

import { generativeParameters } from 'weaviate-client';

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

• X-Databricks-Token: The Databricks API token.
• X-Databricks-Endpoint: The endpoint to use for the Databricks model.
• X-Databricks-User-Agent: The user agent to use for the Databricks model.

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

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

After configuring the generative AI integration, perform RAG operations, either with the single prompt or grouped task method.

To generate text for each object in the search results, use the single prompt method.

The example below generates outputs for each of the n search results, where n is specified by the limit parameter.

When creating a single prompt query, use braces {} to interpolate the object properties you want Weaviate to pass on to the language model. For example, to pass on the object's title property, include {title} in the query.

collection = client.collections.use("DemoCollection")response = collection.generate.near_text(    query="A holiday film",  # The model provider integration will automatically vectorize the query    single_prompt="Translate this into French: {title}",    limit=2)for obj in response.objects:    print(obj.properties["title"])    print(f"Generated output: {obj.generated}")  # Note that the generated output is per object

let response;
const myCollection = client.collections.use("DemoCollection");

To generate one text for the entire set of search results, use the grouped task method.

In other words, when you have n search results, the generative model generates one output for the entire group.

collection = client.collections.use("DemoCollection")response = collection.generate.near_text(    query="A holiday film",  # The model provider integration will automatically vectorize the query    grouped_task="Write a fun tweet to promote readers to check out these films.",    limit=2)print(f"Generated output: {response.generative.text}")  # Note that the generated output is per queryfor obj in response.objects:    print(obj.properties["title"])

let response;
const myCollection = client.collections.use("DemoCollection");

• Databricks embedding 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.

• Databricks foundation model documentation

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