• Weaviate Newsletter
  • Posts
  • Verba: local RAG with Ollama, 1.25 Weaviate Release, and AI Events 🚀

Verba: local RAG with Ollama, 1.25 Weaviate Release, and AI Events 🚀

Author

Femke Plantinga
May 23, 2024

Hey Weaviate Community, 🤗

This week's newsletter is packed with exciting news! We've got new job openings, the coolest RAG open-source project of the year (Verba 🐕), and a brand new Weaviate 1.25 release with awesome features. Plus, there are plenty of opportunities to learn with the new DeepLearning.AI course, connect with the team, and join us at upcoming events, both online and in person!

Buckle up, because we're diving right in! ✨

Verba 1.0

Verba 1.0 is finally here!

With our latest release, you can now run a state-of-the-art Retrieval Augmented Generation (RAG) application locally on your computer, thanks to the new integration with Ollama. This allows you to use fantastic open-source models like Llama 3, MistralAI's 7B, or Command R from Cohere.

Check out our new video featuring Victoria, Edward, and Philip. In just a few minutes, they explain everything you need to know about setting up a fully advanced RAG application. They’ll also show you our major UI upgrades and go through some example use cases for handling sensitive data RAG.

✨ Try Verba

Learn more about Verba:

Weaviate 1.25

✨ Release highlights ✨

  • Dynamic Vector Index: Dynamically switch from flat indexes to HNSW to efficiently scale as your data grows.

  • Raft: Improves schema management and makes multi-node clusters more reliable.

  • New Modules: Loads of new modules, like Ollama, OctoAI, and Cohere’s Command R, that empower you to host and run open source embedding and language models locally!

  • Batch Vectorization: Faster and more efficient use of APIs during data import.

  • Automatic Tenant Creation: Easier data uploads and tenant creation for your application.

  • Search Improvements: Hybrid search gets vector similarity search and grouping. method. Keyword search also gets grouping.

AI tips, tricks, and tech

Are you excited about learning how to build multimodal search and RAG applications? Then don’t miss your chance to get hands on and complete our newest DeepLearningAI course with Sebastian Witalec.

How-to

Newest AI & data technology developments

Videos

  • 🎥 DSPy End-to-End: Meetup in San Francisco

    • This recording covers Cohere, Weaviate, Arize, and DSPy. DSPy is a framework for optimizing large language model (LLM) systems, with a programming model to define LLM components and compilers to enhance quality and cost. It integrates with Cohere's Command R LLM, Arize Phoenix, and Weaviate.

Listen to the Weaviate podcast on YouTube, Spotify, or Apple Podcasts. ✨🎧

Upcoming events

Vibes of AI and Open Source - Buzzwords from Berlin

Weaviate is heading to Berlin! Join us for the chance to connect, learn, and share ideas with Berlin's thriving AI and Open Source communities. We'll be participating in talks and meetups, including:

  • AI Buzzwords - Weaviate & Aiven Data & AI Meetup Berlin: Join us on June 11th at 18:00 for another AI Meetup! Connect and network with speakers from Berlin Buzzwords, developers, data scientists, AI innovators, and practitioners from Berlin's tech community.

    Oliver Huber from Aiven will talk on "Reducing Generative AI Hallucination with RAG," and Weaviate's Zain Hasan will present about "Multimodal RAG."

  • Berlin Buzzwords 2024: Catch Zain Hasan’s "Advanced Retrieval Augmented Generation Techniques" talk at the Frannz Salon on June 11th from 11:10 AM to 11:50 AM.

Many of the Weaviate team will be in town, and we can’t wait to meet you in person! 💚

Office Hours

Weaviate office hours are a great chance to meet different Weaviate experts to learn about a specific topic or get help with all your questions. Our office hours are live and not recorded!

In Person Events

Live Online Learning

Remember to check out the provided links for all the details on how to sign up. We can't wait to meet you!

Community

Community Feedback Survey - Share Feedback with us!

Sharing is caring, and feedback is a gift! So, we'd love your honest feedback on your experience with Weaviate. What do you love? How can we improve? What do you need more of? Tell us in our Community Feedback Survey.

Welcoming new faces

  • Meet Sebastián Neira, joining as our new Client-Focused SRE

  • Meet Joe Green, he is joining us as a Product Support Engineer

Join our team!

We’ve got a bunch of new open roles - check them out and apply today:

Have a look at our career page for more details on our hiring process! ✨

Want to dive in deeper?

We've got you covered! Got questions about Weaviate, vector databases, or anything else? Chat with us on the Community Slack or join the conversation on the Weaviate Forum.

Looking forward to seeing you there in the next two weeks!

P.S. Weaviate is open source! Check out our GitHub repo, and give us a star while you're there. ⭐

Thanks 💚