Anyscale Generative AI with Weaviate

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

Configure a Weaviate collection to use an Anyscale generative AI model, and Weaviate will perform retrieval augmented generation (RAG) using the specified model and your Anyscale API key.

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

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the Anyscale generative AI integration (generative-anyscale) 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 Anyscale API key to Weaviate for this integration. Go to Anyscale to sign up and obtain an API key.

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

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

Python API v4

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

# Recommended: save sensitive data as environment variables
anyscale_key = os.getenv("ANYSCALE_APIKEY")
headers = {
    "X-Anyscale-Api-Key": anyscale_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()

JS/TS API v3

import weaviate from 'weaviate-client'

const anyscaleApiKey = process.env.ANYSCALE_APIKEY || '';  // 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-Anyscale-Api-Key': anyscaleApiKey,
    }
  }
)

// Work with Weaviate

client.close()

Configure collection

Generative model integration mutability

A collection's generative 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 index as follows to use an Anyscale generative model:

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    generative_config=Configure.Generative.anyscale()
    # Additional parameters not shown
)

JS/TS API v3

await client.collections.create({
  name: 'DemoCollection',
  generative: weaviate.configure.generative.anyscale(),
  // Additional parameters not shown
});

You can specify one of the available models for Weaviate to use. The default model is used if no model is specified.

Select a model

You can specify one of the available models for Weaviate to use, as shown in the following configuration example:

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    generative_config=Configure.Generative.anyscale(
        model="mistralai/Mixtral-8x7B-Instruct-v0.1"
    )
    # Additional parameters not shown
)

JS/TS API v3

await client.collections.create({
  name: 'DemoCollection',
  generative: weaviate.configure.generative.anyscale({
    model: 'mistralai/Mixtral-8x7B-Instruct-v0.1'
  }),
  // Additional parameters not shown
});

Generative parameters

Configure the following generative parameters to customize the model behavior.

Python API v4

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    generative_config=Configure.Generative.anyscale(
        # # These parameters are optional
        # model="meta-llama/Llama-2-70b-chat-hf",
        # temperature=0.7,
    )
    # Additional parameters not shown
)

JS/TS API v3

await client.collections.create({
  name: 'DemoCollection',
  generative: weaviate.configure.generative.anyscale({
    // // These parameters are optional
    // model: 'meta-llama/Llama-2-70b-chat-hf',
    // temperature: 0.7,
  }),
  // Additional parameters not shown
});

For further details on model parameters, see the Anyscale Endpoints API documentation.

Retrieval augmented generation

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

Single prompt

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.

Python API v4

collection = client.collections.get("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

JS/TS API v3

let myCollection = client.collections.get('DemoCollection');

const singlePromptResults = await myCollection.generate.nearText(
  ['A holiday film'],
  {
    singlePrompt: `Translate this into French: {title}`,
  },
  {
    limit: 2,
  }
);

for (const obj of singlePromptResults.objects) {
  console.log(obj.properties['title']);
  console.log(`Generated output: ${obj.generated}`);  // Note that the generated output is per object
}

Grouped task

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.

Python API v4

collection = client.collections.get("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.generated}")  # Note that the generated output is per query
for obj in response.objects:
    print(obj.properties["title"])

JS/TS API v3

let myCollection = client.collections.get('DemoCollection');
const groupedTaskResults = await myCollection.generate.nearText(
  ['A holiday film'],
  {
    groupedTask: `Write a fun tweet to promote readers to check out these films.`,
  },
  {
    limit: 2,
  }
);

console.log(`Generated output: ${groupedTaskResults.generated}`);  // Note that the generated output is per query
for (const obj of groupedTaskResults.objects) {
  console.log(obj.properties['title']);
}

References

Available models

• meta-llama/Llama-2-70b-chat-hf (default)
• meta-llama/Llama-2-13b-chat-hf
• meta-llama/Llama-2-7b-chat-hf
• codellama/CodeLlama-34b-Instruct-hf
• mistralai/Mistral-7B-Instruct-v0.1
• mistralai/Mixtral-8x7B-Instruct-v0.1

Further resources

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.

References

• Anyscale Endpoints API documentation

Questions and feedback

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

• Technical questions
• Documentation feedback