Generative AI

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

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

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

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

You must provide a valid OpenAI API key to Weaviate for this integration. Go to OpenAI to sign up and obtain an API key.

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

• Set the OPENAI_APIKEY environment 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 key

Configure a Weaviate index as follows to use an OpenAI generative AI model:

from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    generative_config=Configure.Generative.openai()    # Additional parameters not shown)

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

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

from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    generative_config=Configure.Generative.openai(        model="gpt-4-1106-preview"    )    # Additional parameters not shown)

await client.collections.create({  name: 'DemoCollection',  generative: weaviate.configure.generative.openAI({    model: 'gpt-4-1106-preview',  }),  // 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.

Configure the following generative parameters to customize the model behavior.

from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    generative_config=Configure.Generative.openai(        # # These parameters are optional        # model="gpt-4",        # frequency_penalty=0,        # max_tokens=500,        # presence_penalty=0,        # temperature=0.7,        # top_p=0.7,        # base_url="<custom_openai_url>",        # # For reasoning models such as the gpt-5 family:        # reasoning_effort="medium",  # One of "minimal", "low", "medium", "high"        # verbosity="medium",  # One of "low", "medium", "high"    )    # Additional parameters not shown)

await client.collections.create({  name: 'DemoCollection',  generative: weaviate.configure.generative.openAI({    // These parameters are optional    // model: 'gpt-4',    // frequencyPenalty: 0,    // maxTokens: 500,    // presencePenalty: 0,    // temperature: 0.7,    // topP: 0.7,  }),  // Additional parameters not shown});

Two additional parameters are available for reasoning models such as the gpt-5 family. They were added in v1.33.0, and backported to v1.31.15 and v1.32.9:

• reasoningEffort: How much reasoning the model does before it answers. One of minimal, low, medium, or high. If not set, the model provider default applies.
• verbosity: How detailed the generated answer is. One of low, medium, or high. If not set, the model provider default applies.

The Python client exposes these as the reasoning_effort and verbosity arguments, both when you configure the collection and when you select a model at runtime. The TypeScript client does not expose them yet, so set them with another client or through the REST collection configuration API.

For further details on model parameters, see the OpenAI API 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.openai(        # # These parameters are optional        # model="gpt-4",        # frequency_penalty=0,        # max_tokens=500,        # presence_penalty=0,        # temperature=0.7,        # top_p=0.7,        # base_url="<custom_openai_url>"    ),    # Additional parameters not shown)

import { generativeParameters } from 'weaviate-client';

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

• X-OpenAI-Api-Key: The OpenAI API key.
• X-OpenAI-Baseurl: The base URL to use (e.g. a proxy) instead of the default OpenAI URL.
• X-OpenAI-Organization: The OpenAI organization ID.

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");

You can also supply images as a part of the input when performing retrieval augmented generation in both single prompts and grouped tasks.

import base64import requestsfrom weaviate.classes.generate import GenerativeConfig, GenerativeParameterssrc_img_path = "https://upload.wikimedia.org/wikipedia/commons/thumb/b/b0/Winter_forest_silver.jpg/960px-Winter_forest_silver.jpg"base64_image = base64.b64encode(requests.get(src_img_path).content).decode('utf-8')prompt = GenerativeParameters.grouped_task(    prompt="Which movie is closest to the image in terms of atmosphere",    images=[base64_image],      # A list of base64 encoded strings of the image bytes    # image_properties=["img"], # Properties containing images in Weaviate)jeopardy = client.collections.use("DemoCollection")response = jeopardy.generate.near_text(    query="Movies",    limit=5,    grouped_task=prompt,    generative_provider=GenerativeConfig.openai(        max_tokens=1000    ),)# Print the source property and the generated responsefor o in response.objects:    print(f"Title property: {o.properties['title']}")print(f"Grouped task result: {response.generative.text}")

import { generativeParameters } from 'weaviate-client';

Weaviate does not validate the model name, so you can set any model that your OpenAI account can reach. Name validation was removed in v1.33.0, and backported to v1.31.17 and v1.32.10.

The server default is gpt-5-mini. It changed in v1.32.3, and was backported to v1.30.16 and v1.31.10. Earlier releases on each of those lines default to gpt-3.5-turbo.

See the OpenAI model documentation for the list of available models.

Weaviate stores a token limit for the models below. The limit caps the maxTokens value you can set for those models; it does not restrict which models you can use.

• OpenAI 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.

• OpenAI Chat API documentation

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