Changelog
Follow new updates and improvements to weaviateagents.
March 4th, 2025
New
We’re incredibly excited to announce that we’ve released a brand new service for our Serverless Weaviate Cloud users (including free Sandbox users) to preview, currently in Alpha: the Weaviate Query Agent! Ready to use now, this new feature provides a simple interface for users to ask complex multi-stage questions about your data in Weaviate, using powerful foundation LLMs. Check out our blog post to learn more about it and what you can build. You can also check out this recipe for an end-to-end example of using the Query Agent against multiple collections.
Getting Started
Query Agent is currently in alpha and is free to use for Weaviate Cloud sandboxes and serverless clusters. During this alpha, there will be a daily usage cap of 100 queries per day for each organization.
The Query Agent is compatible with all existing sandbox and serverless clusters in Weaviate Cloud. To get started, install or update the official Weavite Python client with the install syntax below:
pip install weaviate-client[agents]Usage
The Query Agent is designed to be simple to setup, and you can get started running complex queries utilizing it with just a few lines of code:
from weaviate.agents.query import QueryAgent
from weaviate.agents.utils import print_query_agent_response
agent = QueryAgent(
client=client, collections=["Ecommerce", "Brands", "Financial_contracts"],
)
response = agent.run("I like the vintage clothes, can you list me some options that are less than $200?")
print_query_agent_response(response)Docs
Throughout the Alpha the syntax and usage of the Query Agent may change; make sure to check in on the docs if something has stopped working, and make sure your client SDK is up to date.
To learn more about how to use and customize the Query Agent, check out our docs here.
Feedback
We’d love to hear your thoughts and suggestions, if there’s a feature or piece of functionality you’d love to see let us know here.