In this article, David delves into the integration of MinIO with #RAG pipelines & Weaviate • vector database vector storage, using LangChain. Learn how to create a robust #data handling framework that improves workflow & manages the complete data lifecycle. hubs.li/Q02wrTLg0

We're looking for senior full-stack product engineers to join LlamaIndex 🦙 to build out the new data stack for AI software.

You'll be:
- Working on LlamaCloud - a platform to process and centralize all your knowledge, across any storage system, for production LLM applications
-

Use RAG: Retrieval Augmented Generation to help large language models produce more specific and better results? Weaviate is built from the ground up for good search, so you can make the most out of RAG.

Get Bob van Luijt's thoughts on RAG and what comes next:

With Modal and Weaviate, you can embed and ingest 40+ million objects in 2 hours 🚀

Charles 🎉 Frye and Erika Cardenas share all the technical details in this blog post: weaviate.io/blog/modal-and…

They cover:
• Async Indexing
• Product Quantization
• Vector Index

This was a fun project! Check out the blog for details.

What are Vector Databases?

Femke Plantinga explains this in under 60 seconds ✨

Read more in Leonie's blog post: weaviate.io/blog/what-is-a…

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,

🧐 'Developers don't like marketing,' they said
🍺 Weaviate's growth team: #HoldMyBeer
🫵 O and, yes, we are hiring: careers.weaviate.io

Summer is around the corner in Berlin—and so is Weaviate!

We're heading to the 'dickes B' for the buzzing vibes of the city's tech scene. Join us for an opportunity to connect, learn, and share ideas with Berlin's thriving AI and Open Source communities. We'll be participating

Multimodal search and RAG systems are gaining more and more popularity - when you can combine images, videos, text, and audio into any system, the possibilities are endless!

Sebastian {W}italec ✊🏽✊🏾✊🏿 just published a course on DeepLearning.AI on how multimodal systems work and how to build a

With ollama and Weaviate, you can easily build an on-premise Retrieval-Augmented Generation pipeline for privacy preservation.

In our latest blog, our developer advocate, Leonie, shows you how to use local language models and a local vector database to build a simple

Berlin Buzzwords, we're so back!

Weaviate • vector database is partnering with @[email protected] again. Last year’s highlights included:
• Weaviate Barista Coffee ☕️
• The first-ever Weaviate Balloons 🎈
• Connecting with Berlin’s AI community

This year, we're going even bigger! 🚀

Go Erika Cardenas!! 🎉🎉🎉

Halftime in NYC! Super grateful for these opportunities to meet developers in person and discuss their unique perspectives on all things AI!🗽🙏

Bob van Luijt Business Insider 🔥♻️🔥

Meet Bob Van Luijt Bob van Luijt, CEO & Co-Founder at Weaviate • vector database, speaking at #GENAISummitSF2024 on 'VectorDB 2.0 with Longer Context Window'

More event info on genaisummit.ai. The clock is ticking.

#ai #artificialintelligence #ai revolution #machinelearning

💡 really enjoyed this conversation with Matthew S. Smith for his recent article in Business Insider!
💡 We dove into 'what's after RAG' by talking about Generative Feedback loops
👉 Matthew S. Smith's article: businessinsider.com/retrieval-augm…
👉 Connor Shorten's first blog on generative

Join Job Nijenhuis from Neople and Erika Cardenas from Weaviate for a webinar on May 29th at 1 pm ET / 7 pm CET

The key takeaways:
• How vector databases work and how to use vector search for quick retrieval
• All about ingesting and chunking your data (feedback documents, FAQ

Weaviate 1.25 is here! ⭐
Here’s what’s new:

• Dynamic Vector Index: Switch to HNSW dynamically for efficient scaling
• Raft: Enhances schema management and multi-node cluster reliability
• New Modules: Host open-source embedding and language models locally
• Batch

Product Quantization (PQ) is still one of my favorite types of vector compression algorithms because of its versatility, performance, and dynamic rates of compression. There’s a reason it was the first (but certainly not the last) type of quantization algorithm to be introduced

Join this week's Weaviate events! 🥳

22 May
• TEQNation 2024: 'Give your apps superpowers with an AI-native database' by JP Hwang
DOUCHELOKAAL: Wed 15:45 - 16:30
More info: conference.teqnation.com
• Building Multimodal Search Applications in Typescript with daniel phiri @vueconfus 🇺🇸