Weaviate (vector search)

Connect Weaviate as a vector provider for the Semantic Search built-in tool. Weaviate is not a standalone integration — it is a provider option within the Semantic Search tool available to Agents.

What is Weaviate?

Weaviate is a vector database for semantic search. Use it for RAG (Retrieval Augmented Generation) at scale with millions of documents.

When to use Weaviate vs Records

• Use Runtype Records with platform vector search (pgvector): Up to 100k documents, simple setup
• Use Weaviate: 100k+ documents, advanced filtering, production scale

Setting up Weaviate

1. Create a Weaviate cluster at console.weaviate.cloud
2. Get your cluster URL and API key
3. Add your Weaviate credentials in Settings → Integrations

Using Weaviate with the Semantic Search tool

Weaviate is configured as a vector provider when adding the Semantic Search built-in tool to an Agent:

1. Add the Semantic Search tool to your Agent
2. Under Vector Provider, select Weaviate
3. Enter your Collection Name (the Weaviate class to search)
4. Optionally configure the similarity threshold and display name

The tool supports multiple instances, so you can add several Semantic Search tools pointing to different Weaviate collections in the same Agent.

RAG with Weaviate

Build retrieval-augmented generation by enabling the Semantic Search tool (with Weaviate provider) on an Agent. The Agent can autonomously query the Weaviate collection for relevant documents and use them as context for generating answers.

Next steps

• What are Agents? to build Agents that use the Semantic Search tool