Generative AI

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

Configure a Weaviate collection to use a generative AI model with Ollama. Weaviate will perform retrieval augmented generation (RAG) using the specified model via your local Ollama instance.

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

This integration requires a locally running Ollama instance with your selected model available. Refer to the Ollama documentation for installation and model download instructions.

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

Your Weaviate instance must be able to access the Ollama endpoint. If you area a Docker user, specify the Ollama endpoint using host.docker.internal alias to access the host machine from within the container.

As this integration connects to a local Ollama container, no additional credentials (e.g. API key) are required. Connect to Weaviate as usual, such as in the examples below.

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

from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    generative_config=Configure.Generative.ollama(        api_endpoint="http://host.docker.internal:11434",  # If using Docker, use this to contact your local Ollama instance        model="llama3"  # The model to use, e.g. "phi3", or "mistral", "command-r-plus", "gemma"    )    # Additional parameters not shown)

await client.collections.create({  name: 'DemoCollection',  generative: weaviate.configure.generative.ollama({    apiEndpoint: 'http://ollama:11434',  // If using Docker you might need: http://host.docker.internal:11434    model: 'llama3',  // The model to use, e.g. 'phi3', or 'mistral', 'command-r-plus', 'gemma'  }),  // Additional parameters not shown});

The Weaviate server has to be able to reach the Ollama API endpoint. If Weaviate is running in a Docker container and Ollama is running locally, use host.docker.internal to redirect Weaviate from localhost inside the container to localhost on the host machine.

If your Weaviate instance and Ollama instance are hosted in a different way, adjust the API endpoint parameter so it points to your Ollama instance.

The default model is used if no model is specified.

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.ollama(        api_endpoint="http://host.docker.internal:11434",  # If using Docker, use this to contact your local Ollama instance        model="llama3"  # The model to use, e.g. "phi3", or "mistral", "command-r-plus", "gemma"    ),    # Additional parameters not shown)

import { generativeParameters } from 'weaviate-client';

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.ollama(),)# 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}")

See the Ollama documentation for a list of available models. Note that this list includes both generative models and embedding models; specify a generative model for the generative-ollama module.

Download the desired model with ollama pull <model-name>.

If no model is specified, the default model (llama3) is used.

• Ollama 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.

• Ollama models
• Ollama repository
• How to change the host and port of the Ollama server

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