Skip to main content
Weaviate Docs (migrated from docs.weaviate.io) Docs

Search documentation

Type to search this documentation.

On this pageOverview

Connect with Query Agent

Weaviate Cloud only

The fastest way to query data in Weaviate Cloud (WCD) without writing code is the Query Agent, a natural-language interface that translates a prompt into a multi-step search against your collections and returns a grounded answer.

The Query Agent lets you ask natural-language questions over one or more collections in your Weaviate Cloud cluster. Behind the scenes it plans a hybrid search strategy, executes it, and returns an answer along with the matching source objects.

In your WCD Dashboard, select Agents in the left-hand sidebar, choose the cluster and collection(s) you want to query, and type a natural-language prompt. The agent picks the right collections, runs the underlying searches, and returns an answer along with the objects that backed it.

Beyond picking collections, you can also provide API keys for external model providers (OpenAI, Anthropic, etc.), choose which named vector to query when a collection has more than one, and set a system prompt to steer tone, language, or output format.

After running a query in the console, you can copy a Python or TypeScript snippet that reproduces the same call through the weaviate-agents client libraries. This makes it easy to move from exploration into application code.

  • The Cloud-console Query Agent does not support multi-tenant collections. To use the Query Agent with multi-tenancy, call it from a client library.
  • Standard Query Agent usage limits apply.

For a deeper walkthrough including additional screen recordings, see the Query Agent tool docs.

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

Suggest an edit

Propose a replacement for this page. The site team reviews it before applying any changes.

Export
Documentation menu