One Prompt AI and Agentic Apps, and Gemini Embedding 2

Hello Weaviate Community! 💚

Is your AI-powered search still stuck in separate silos for text, video, and PDFs? The era of juggling multiple embedding models and complex preprocessing is over. This week, we’re diving into the latest Google Gemini Embedding 2 integration and showing you how to turn natural language prompts into production-ready agentic apps with Weaviate Agent Skills. From multimodal RAG to one-prompt app building, we’ll cover all the blueprints to help you build faster.

Latest AI & tech insights

Explore our recent Weaviate content:

• ✍️ Weaviate 1.36 Release: This release introduces HFresh vector index (Preview), and brings Server-side Batching, Object TTL, Async Replication Improvements, Drop Inverted Indices, and Backup Restoration Cancellation to general availability. Read the blog

• 🗞️ Google’s Gemini Embedding 2 unifies text, images, video, and audio into a single vector space, simplifying complex RAG pipelines through its seamless integration with Weaviate. Read Google's Announcement

• 🎙 Doug Turnbull and Trey Grainger on AI-Powered Search - Weaviate Podcast #133!: They explore the future of AI-powered search, covering everything from Minority Report-style dynamic UIs and multi-tier RAG to wormhole vectors and self-learning systems. Watch the full podcast

• 📽️ Build AI and Agentic apps in ONE prompt: In this video, Victoria demonstrates how to use the new Weaviate Agent Skills to turn natural language prompts into production-ready collections and RAG workflows. Watch the video walkthrough

Product highlights

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

• ✨ Google Gemini Embedding 2 Integration: Simplify your RAG pipelines by unifying text, images, video, and audio into a single vector space with our Google integration. See how it works or check out these recipes to get started:

  • Semantic search/RAG over video

  • Semantic search/RAG over audio

  • Multimodal PDF RAG

• 🧠 Engram is Now in Preview: Engram - Weaviate’s memory and context management layer for agents is now in preview! Sign up for the preview here to help shape our direction and features!

Company updates

Join our team — We're hiring across various teams! ➡️ Check out our career page for exciting opportunities in engineering, research, and more.✨

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