Query Agent
The Weaviate Cloud (WCD) Query Agent provides an interactive console for using the Weaviate Query Agent, a pre-built agentic service designed to answer natural language queries based on the data stored in Weaviate Cloud.
The user simply provides a prompt/question in natural language, and the Query Agent takes care of all intervening steps to provide an answer.
Query a collection
In order to use the Query Agent, log into your Weaviate Cloud account and select Agents in the sidebar panel.
Additional parameters for querying
In addition to selecting one or more collections to query, you can also:
- Specify API keys for external model providers (like OpenAI, Anthropic, etc.)
- Select which vectors in a collection to query (if there are multiple vectors in the collection)
- Specify a system prompt that provides additional information or instructions to the agent (for example, setting the tone, language, etc.)
Generate code snippets
After executing a query, you can also generate a code snippet that performs the same task through one of the available Query Agent client libraries, either Python or TypeScript.
Usage and limitations
Usage limits
Each Weaviate Cloud organization can make up to 1,000 Query Agent requests per month at no cost.
Requests are consumed based on query type:
Ask: 4 requests per querySearch: 1 request per querySuggest Queries: 1 request per query
This limit may change in the future. For questions about usage limits, contact product@weaviate.io.
You can track your organization's Query Agent usage directly in the Console.
Custom collection descriptions
The Query Agent makes use of each collection's description metadata as well as individual property descriptions in deciding what collection to query.
Both collection descriptions and property descriptions can be updated after the collection has been created. For detailed instructions on updating collection and property descriptions, see the update collection definition documentation.
We are investigating an ability to specify a custom collection description at runtime.
Execution times
The Query Agent performs multiple operations to translate a natural language query into Weaviate queries, and to process the response.
This typically requires multiple calls to generative models (e.g. LLMs) and multiple queries to Weaviate.
As a result, each Query Agent run may take some time to complete. Depending on the query complexity, it may not be uncommon to see execution times of ~10 seconds.
For long-running or complex queries, consider using streaming responses rather than non-streaming requests. Streaming provides progress updates and sends heartbeats to maintain the connection, preventing timeout issues that can occur with long-running non-streaming requests.
Multi-tenancy
The WCD Query Agent does not support multi-tenancy. In order to utilize multi-tenancy with the Query Agent, use a client library.
Further resources
Support
If you use Weaviate Cloud (Database cluster(s) or Weaviate product in the cloud) or have a self-hosted support package, open a ticket in the Support Portal or email Weaviate support directly. To add a support plan, contact Weaviate sales.
Use the Support Portal for direct help from the Weaviate team: open and track tickets, and we'll respond in line with your support plan. The Community Forum is open to everyone, and a great place to ask questions, get help with your cluster, and connect with other developers. For all the ways to get help, see the Support overview.