Weaviate โข vector database
@weaviate_io
The easiest way to build and scale AI applications. ๐ http://github.com/weaviate/weaviate ๐ฐ https://newsletter.weaviate.io/
Here are the LEGO blocks of AI agents. Letโs build some ๐ฎ๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐ฎ๐ฟ๐ฐ๐ต๐ถ๐๐ฒ๐ฐ๐๐๐ฟ๐ฒ๐ with them! Our new (and FREE!) eBook covers: โข Single vs multi-agent systems โข Patterns in multi-agent systems โข 6 examples of agentic architectures โฆand much more! ๐โฆ
@FactSetโs journey with @weaviate_io and #AWS EKS is a masterclass in scaling #AI. ๐ ๐ค A federated approach to data and chatbot integration are helping FactSet bring next-gen search to clients. Watch more on AWS TV โถ๏ธ go.aws/44tc8zT
Multi-vector embeddings sound complexโmultiple models, extra infrastructure, right? But there's a simpler, elegant solution hiding in plain sight. Named vectors let you store multiple vector embeddings per object, then search using any of those vector spaces. Think of it asโฆ
๐ฉ๐ฒ๐ฐ๐๐ผ๐ฟ ๐ฑ๐ฎ๐๐ฎ๐ฏ๐ฎ๐๐ฒ ๐บ๐ฒ๐บ๐ผ๐ฟ๐ ๐๐๐ฎ๐ด๐ฒ ๐ฑ๐ฟ๐ผ๐ฝ๐ ๐๐ถ๐๐ต ๐ป๐ฒ๐ ๐ฟ๐ผ๐๐ฎ๐๐ถ๐ผ๐ป๐ฎ๐น ๐พ๐๐ฎ๐ป๐๐ถ๐๐ฎ๐๐ถ๐ผ๐ป. With Weaviate 1.32, weโre introducing memory footprint reduction, seamless collection migrations with aliases, and accelerated cost-aware sorting. Keyโฆ
Think you need to code to build agentic AI systems? Not anymore. ๐ช๐ฒ ๐ท๐๐๐ ๐น๐ฎ๐๐ป๐ฐ๐ต๐ฒ๐ฑ ๐ฎ ๐ณ๐ฟ๐ฒ๐ฒ @n8n_io ๐๐ฒ๐บ๐ฝ๐น๐ฎ๐๐ฒ ๐๐ต๐ฎ๐ ๐ฝ๐ฟ๐ผ๐๐ฒ๐ ๐ถ๐. It's an agentic workflow that automatically sends you a weekly email summarizing the latest in AI research. But whatโฆ
We are so excited to welcome David to our team today! ๐ David Tran - Client-Focused SRE ๐ Welcome to Weaviate! ๐
๐๐ฆ๐ฎ๐ช๐ฏ๐ช ๐๐ฎ๐ฃ๐ฆ๐ฅ๐ฅ๐ช๐ฏ๐จ๐ด ๐ค๐ค ๐๐ฆ๐ข๐ท๐ช๐ข๐ต๐ฆ We just published a new recipe notebook showing you how to use Google's Gemini embeddings with Weaviate. โข ๐ญ๐ฌ๐ฌ+ ๐น๐ฎ๐ป๐ด๐๐ฎ๐ด๐ฒ๐ ๐๐๐ฝ๐ฝ๐ผ๐ฟ๐๐ฒ๐ฑ: Build truly multilingual search experiences โข ๐ ๐ง๐๐โฆ
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 singleโฆ
No code Weaviate is here. And itโs part of the worldโs favorite automation platform: @n8n_io. Our new community node changes everything. Hereโs what it can do: 1. Insert documents into a Weaviate collection. 2. Return ranked documents based on queries from a Weaviateโฆ
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! ๐ช๐ต๐ฎ๐'๐ ๐ต๐ฎ๐ฝ๐ฝ๐ฒ๐ป๐ถ๐ป๐ด? The Hackathon Power ofโฆ
Introducing the new Weaviate Confluent Apache Kafkaยฎ Connector! Weโre excited to announce the launch of the Weaviate Kafka Connector โ built by Weaviate, and verified by @confluentinc. Making it easier than ever to stream data directly into your Weaviate vector database fromโฆ
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 youโฆ
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 ofโฆ
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: weaviate.io/developers/weaโฆ
Ever felt overwhelmed in finding your perfect skincare routine? We just launched ๐๐น๐ผ๐๐ฒ - an AI-powered Korean skincare app that actually understands what your skin needs. Try it out here: glowe.app/?utm_source=chโฆ Here's what makes Glowe special: ๐ฏโฆ
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.โฆ
๐คย What does it really take to build AI-native applicationsโfrom Day Zero to Day Two? Whether you're starting from a notebook or running at enterprise scale, the stack mattersโฆ In this post, our CEO @bobvanluijt shares how Weaviate empowers developers to move from prototype toโฆ
We are so excited to welcome Nick to our team today! ๐ - Nick Wong - Solution Engineer ๐ง๐ป Welcome to Weaviate! ๐
Your vector searches could be 100x faster. But most developers choose the wrong vector index. ๐ช๐ต๐ฎ๐ ๐ถ๐ ๐ฎ ๐๐ฒ๐ฐ๐๐ผ๐ฟ ๐ถ๐ป๐ฑ๐ฒ๐ ? A vector index is a data structure designed to make searching through millions (or billions) of vectors lightning fast. Instead of comparingโฆ
Still stuffing the top-k chunks into your prompt and praying for a good answer? Well, itโs 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-sourceโฆ
"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: โ Semantic search across patient histories โ โฆ