Query Agent, AI Benchmarks, and Live Demo Projects

Hello Weaviate Community, 🤗

Talk to your database in plain English? Sounds too good to be true, but after six months of development and user feedback, Query Agent proves it’s possible.

This week, we’re diving into Query Agent going GA, the latest AI search benchmarks, and live demos showcasing how developers are building with Weaviate.

Earlier this year, we released the Query Agent for early preview. After six months of feedback and iteration, we’re thrilled to announce it’s GA! This marks a new chapter for developers interacting with their data in Weaviate.

👉 Read the announcement post

🎧 Listen to Charles Pierse on Query Agent - Weaviate Podcast #12

Try it with your own data - Query Agent is available via our Weaviate Cloud Console.

Latest AI & tech insights

Explore our recent Weaviate content:

Read

• ✍️ Evals and Guardrails in Enterprise workflows (Part 2): Hands-on patterns: LLM-as-Judge with LangChain and W&B. Read the blog

• 🔖 Weaviate is now ISO 27001 compliant: Security matters. Learn how we achieved ISO 27001 compliance. Read the announcement post

• ✍️ Search Mode Benchmarking: How does Search Mode stack against Hybrid Search across BEIR, LoTTe, BRIGHT, EnronQA, and WixQA? Read the blog

Watch

• 📽️ Building AI in London: London AI Hack brought builders and innovators together for a day of AI-powered creativity and MVP launches, follow Weaviate and {Tech: Europe} to catch the next one! Watch the event recap video

Product highlights

Check out our latest product updates. Or follow along in the #announcement channel in the Weaviate Community Slack.

• Transformers Inference v1.13.1: Added support for google/embeddinggemma-300m and jhu-clsp/mmBERT-small models.

• Weaviate Core v1.31.15 & v1.32.9: Improvements to LSM segment initialization and commit log condensing.

• Weaviate Core v1.31.16: Fixed hybrid search with generate and added coordinator replication metrics.

• Weaviate Core v1.32.10: Fixed LSM store and async replication issues; added support for Cohere vision models in the generative module.

Upcoming events

Join us online or in person for expert-led AI workshops and networking events. Connect, learn, and build with the community!

Online

• 📚 Weaviate Office Hours | 1 October. Weaviate Office Hours are a great chance to meet our experts personally and ask them all the questions you ever wanted. Register here

• 🛠️ Intro to building AI-native applications with Weaviate | 2 October. Join this hands-on workshop to learn how Weaviate, enables you to build scalable, enterprise-grade AI applications using RAG, agentic architectures, and advanced search to make your data more actionable. Register here

• 🛠️ Building Intelligent Chatbots with Pydantic AI and Weaviate | 7 October. Learn hands-on how to build an intelligent chatbot system from scratch. Register here

• ⚡ Agentic RAG Workflows with Weaviate in JavaScript | 16 October. Join to learn hands-on how agents can improve consistency and accuracy on your RAG system’S retrieval outcomes. Register here

In-person

• 🌵 Palo Alto, California | 30 September | Building Startups with AI: Meet & Greet. Save your spot

• 🌃 San Francisco | 1 October | Hack Night at GitHub. Save your spot

• 🌉 San Francisco | 22 October | AWS AI Hack Day Micro Conference. Save your spot

Build with Weaviate

Discover how developers use Weaviate in community projects and industry applications.

Community spotlights

• UnbAIsed: A full-stack app that generates company ethics scores using AI analysis of public data. Weaviate powers semantic search, allowing the system to understand the meaning behind company policies, practices, and statements. GitHub

Hungry for more?

Have a question or want to connect? Say hi in the Community Slack or join our Weaviate Forum to engage in community conversations.

Follow our Blog, LinkedIn, Twitter, and YouTube for more content updates.

See you in two weeks,

Femke