Skip to main content

Ollama Generative AI with Weaviate

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

Configure a Weaviate collection to use an Ollama generative AI model, and 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.

RAG integration illustration

Requirements​

Ollama​

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

Weaviate configuration​

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

For Weaviate Cloud (WCD) users

This integration is not available for Weaviate Cloud (WCD) serverless instances, as it requires a locally running Ollama instance.

For self-hosted users

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.

Credentials​

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.

import weaviate

client = weaviate.connect_to_local()

# Work with Weaviate

client.close()
py docs  API docs

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 Ollama generative model:

from weaviate.classes.config import Configure

client.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
)
py docs  API docs

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.

Retrieval augmented generation​

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

Single prompt​

Single prompt RAG integration generates individual outputs per search result

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.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
py docs  API docs

Grouped task​

Grouped task RAG integration generates one output for the set of search results

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.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"])
py docs  API docs

References​

Available models​

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.

Further resources​

Other integrations​

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​

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