Generative AI
Weaviate's integration with OpenAI-style APIs allows you to access KubeAI models' directly from Weaviate.
Configure a Weaviate collection to use a generative AI model with KubeAI. Weaviate will perform retrieval augmented generation (RAG) using the specified model.
More specifically, Weaviate will perform a search, retrieve the most relevant objects, and then pass them to the KubeAI generative model to generate outputs.
Requirements
Section titled “Requirements”KubeAI configuration
Section titled “KubeAI configuration”KubeAI must be deployed in a Kubernetes cluster with an embedding model. For more specific instructions, see this KubeAI deployment guide.
Weaviate configuration
Section titled “Weaviate configuration”Your Weaviate instance must be configured with the OpenAI generative AI integration (generative-openai) module.
For Weaviate Cloud (WCD) users
This integration is enabled by default on Weaviate Cloud (WCD) 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
Section titled “API credentials”The OpenAI integration requires an API key value. To use KubeAI, provide any value for the API key, as this value is not used by KubeAI.
Provide the API key to Weaviate using one of the following methods:
- Set the
OPENAI_APIKEYenvironment variable that is available to Weaviate. - Provide the API key at runtime, as shown in the examples below.
# Recommended: save sensitive data as environment variables
openai_key = os.getenv("OPENAI_API_KEY")const openaiApiKey = process.env.OPENAI_API_KEY || ''; // Replace with your inference API keyConfigure collection
Section titled “Configure collection”Configure Weaviate to use a KubeAI generative AI model:
from weaviate.classes.config import Configureclient.collections.create( "DemoCollection", generative_config=Configure.Generative.openai( # Setting the model and base_url is required model="gpt-3.5-turbo", base_url="http://kubeai/openai", # Your private KubeAI API endpoint # These parameters are optional # frequency_penalty=0, # max_tokens=500, # presence_penalty=0, # temperature=0.7, # top_p=0.7, ) # Additional parameters not shown)await client.collections.create({ name: 'DemoCollection', generative: weaviate.configure.generative.openAI({ // Setting the model and base_url is required model: 'gpt-3.5-turbo', baseURL: 'http://kubeai/openai', // These parameters are optional // frequencyPenalty: 0, // maxTokens: 500, // presencePenalty: 0, // temperature: 0.7, // topP: 0.7, }), // Additional parameters not shown});Any model that is supported by vLLM or Ollama can be used with KubeAI.
Refer to the KubeAI docs on model management for more information on available models and how to configure them.
Select a model at runtime
Section titled “Select a model at runtime”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.openai( # Setting the model and base_url is required model="gpt-3.5-turbo", base_url="http://kubeai/openai", # Your private KubeAI API endpoint # These parameters are optional # frequency_penalty=0, # max_tokens=500, # presence_penalty=0, # temperature=0.7, # top_p=0.7, ), # Additional parameters not shown)import { generativeParameters } from 'weaviate-client';Retrieval augmented generation
Section titled “Retrieval augmented generation”After configuring the generative AI integration, perform RAG operations, either with the single prompt or grouped task method.
Single prompt
Section titled “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.
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 objectlet response;
const myCollection = client.collections.use("DemoCollection");Grouped task
Section titled “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.
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");Further resources
Section titled “Further resources”Other integrations
Section titled “Other integrations”Code examples
Section titled “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 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.
External resources
Section titled “External resources”Questions and feedback
Section titled “Questions and feedback”Have a question or feedback? Here's how to reach us.