Overview
Weaviate’s Query Agent is a Weaviate-native data agent that turns natural-language questions into precise database operations, making full use of dynamic filters, cross-collection routing, query optimization, and aggregations. It returns accurate and relevant results with source citations.
It replaces manual query construction and ad-hoc logic with runtime, context-aware planning that optimizes and executes queries across user collections. It supports two modes:
- Ask mode: for developers building agentic applications that require conversational interactions and answers backed by data stored in Weaviate.
- Search mode: for developers who need out of the box, high quality information retrieval with strong recall and controlled precision.
The Query Agent can be accessed through Python and TypeScript client SDKs to integrate retrieval directly into applications, or via the Weaviate Cloud Console for fast exploration, validation, and experimentation.
Query Agent is Generally Available
Read more in the announcement about how the interface to databases is shifting with the introduction of agentic retrievers, domain experts that use Weaviate’s APIs with your data.
Available as a 14-day free Weaviate Cloud sandbox trial. No credit card required.
Stay up to date with the latest news, product updates, and best practices for the Query Agent and other Weaviate Agents.