Here are the LEGO blocks of AI agents. Let’s build some 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲𝘀 with them!. Our new (and FREE!) eBook covers:. • Single vs multi-agent systems.• Patterns in multi-agent systems.• 6 examples of agentic architectures .…and much more!. 📌

Think you need to code to build agentic AI systems?. Not anymore. 𝗪𝗲 𝗷𝘂𝘀𝘁 𝗹𝗮𝘂𝗻𝗰𝗵𝗲𝗱 𝗮 𝗳𝗿𝗲𝗲 @n8n_io 𝘁𝗲𝗺𝗽𝗹𝗮𝘁𝗲 𝘁𝗵𝗮𝘁 𝗽𝗿𝗼𝘃𝗲𝘀 𝗶𝘁. It's an agentic workflow that automatically sends you a weekly email summarizing the latest in AI research. But what

We are so excited to welcome David to our team today! 🎉. David Tran - Client-Focused SRE 🚀. Welcome to Weaviate! 💚

𝘎𝘦𝘮𝘪𝘯𝘪 𝘌𝘮𝘣𝘦𝘥𝘥𝘪𝘯𝘨𝘴 🤜🤛 𝘞𝘦𝘢𝘷𝘪𝘢𝘵𝘦. We just published a new recipe notebook showing you how to use Google's Gemini embeddings with Weaviate. • 𝟭𝟬𝟬+ 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲𝘀 𝘀𝘂𝗽𝗽𝗼𝗿𝘁𝗲𝗱: Build truly multilingual search experiences.• 𝗠𝗧𝗘𝗕

Multi-vector embeddings like ColBERT and ColPali are amazing for retrieval quality. But they come with a massive headache: memory costs that can explode your infrastructure budget. Here's how MUVERA solves this problem by converting multi-vector embeddings into single

No code Weaviate is here. And it’s part of the world’s favorite automation platform: @n8n_io. Our new community node changes everything. Here’s what it can do:. 1. Insert documents into a Weaviate collection. 2. Return ranked documents based on queries from a Weaviate

Mistral AI. Orq AI. Weaviate. If you don't know these names, you're missing Europe's AI revolution. Join 100 builders in Amsterdam next weekend for a hackathon that's all about showcasing what Europe's AI ecosystem can do!. 𝗪𝗵𝗮𝘁'𝘀 𝗵𝗮𝗽𝗽𝗲𝗻𝗶𝗻𝗴?.The Hackathon Power of

Introducing the new Weaviate Confluent Apache Kafka® Connector!. We’re excited to announce the launch of the Weaviate Kafka Connector — built by Weaviate, and verified by @confluentinc. Making it easier than ever to stream data directly into your Weaviate vector database from

Weaviate 1.31 dropped new BM25 operators that give you surgical precision over your search results. Here's the problem with normal keyword search: When you search for "noise cancelling microphone", most systems return ANY document containing at least one of those words. So you

100 milliseconds doesn't sound like much. But it's the difference between an app that feels instant and one that feels. off. When building with vector databases, latency optimization isn't just about picking the closest server. It's about understanding a complex chain of

Need to keep your data on-prem?. Deploy Weaviate on your own Kubernetes cluster in 3 steps. Need more details? .Then, check out our docs:.

Ever felt overwhelmed in finding your perfect skincare routine?. We just launched 𝗚𝗹𝗼𝘄𝗲 - an AI-powered Korean skincare app that actually understands what your skin needs. Try it out here: Here's what makes Glowe special:. 🎯

Most AI initiatives in healthcare are a HIPAA violations waiting to happen. The tension between innovation and risk has paralyzed the industry. Until now. Teams are either:. 1. Scrambling to bolt on security to tools never designed for Protected Health Information (PHI). 2.

🤔 What does it really take to build AI-native applications—from Day Zero to Day Two? Whether you're starting from a notebook or running at enterprise scale, the stack matters…. In this post, our CEO @bobvanluijt shares how Weaviate empowers developers to move from prototype to

We are so excited to welcome Nick to our team today! 🎉. - Nick Wong - Solution Engineer 🧑💻. Welcome to Weaviate! 💚

Your vector searches could be 100x faster. But most developers choose the wrong vector index. 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗮 𝘃𝗲𝗰𝘁𝗼𝗿 𝗶𝗻𝗱𝗲𝘅?. A vector index is a data structure designed to make searching through millions (or billions) of vectors lightning fast. Instead of comparing

RT @AWS_Partners: @FactSet’s journey with @weaviate_io and #AWS EKS is a masterclass in scaling #AI. 🚀 🤖 . A federated approach to data and….

Still stuffing the top-k chunks into your prompt and praying for a good answer?. Well, it’s time to level up and try out some agentic stuff!. Why? Because not all queries are created equal. Some need basic fact-finding. Others require reasoning, filtering, even multi-source

"We can't use AI with patient data.".Yes, you can. Here's how. Live demo: Our Verba app processes medical records, research papers, and clinical guidelines with full HIPAA compliance and signed BAAs. What you see in 3 minutes:.✅ Semantic search across patient histories.✅

"We tried running vector search on mobile. It broke down fast.". So @heyconstella did something brilliant instead. They offloaded to centralized Weaviate and achieved blazing fast search across ALL devices. Now users don’t just store notes… they think with them. Voice memos,

Why does your RAG system return irrelevant results?.The wrongdoer might be your chunking strategy. 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗰𝗵𝘂𝗻𝗸𝗶𝗻𝗴? .Chunking is the pre-processing step of splitting texts into smaller pieces, or "chunks.” Each chunk is the unit of information that is vectorized