LangChain just released their new integrations Hub! Give Weaviate AI Database some ❤️!! integrations.langchain.com

Curious about Weaviate AI Database or vector DBs? Join us at our free 🛠️ online workshop on 6 July You'll get 🎓: 🤖 A demo - Weaviate + LLMs 🧠 Theory - about vector DBs 💻 Practical - Set up Weaviate 🔎 Practical - Ingest & search data Sign up ⬇️ form.jotform.com/231792470367866

A thread on TimescaleDB (by Tiger Data)'s performance claims regarding Weaviate 🧵

For the first time, I'm able to vote in the U.S elections. While this is a privilege not many have, it's also a huge responsibility. David de Matheu and I built electiongpt.ai to help navigate uncertainty and stay grounded with information from each candidate in an

🔥 this is why Weaviate is one of the few (only?) vector databases that offers hybrid search out of the box! 💡 did you know that this is why Weaviate has a custom-built vector index _and_ the LSM store does not rely on third-party stores? 🧠 Learn more: weaviate.io/developers/wea…

Vector databases are a key part of many LLM applications that need search or data retrieval, for example with Retrieval Augmented Generation (RAG). Learn how they work + how to use them in our new short course, taught by Weaviate • vector database's Sebastian {W}italec ✊🏽✊🏾✊🏿! deeplearning.ai/short-courses/…

How to semantically search over documents in an S3 bucket with real-time changes? Instructions and step by step 👇 If an application requires to semantically search a corpus of data, chances are that you are dealing with vector embeddings and vector databases to store these

🗽 Amazing turnout during the Weaviate AI Database presentation at the NYC AICamp meetup! 🤘the one and only Byron Voorbach killing it! 🙏 thanks for hosting us Microsoft

Excited!! 🎉

🤩 the Weaviate team has access to Google for Developers's Gemini Pro 1.5! 📦 I'm super excited about the multimodal possibilities that can be used for RAG and for Generative Feedback Loops (i.e., on import time) into the database. 💡 We'll keep you posted in the coming weeks and ensure

Bonjour Ollama! Friends and Ollama are heading to Paris. If you are in the area, please join us for a developer meetup on Thursday, March 21st 6pm at Station F! lu.ma/devs3

RAG with Llama 3 + DSPy + Weaviate!

Jo Kristian Bergum Qdrant There is more github.com/qdrant/vector-…

Great evening at the Cloudflare office together with Adam / AJ Chan! Thanks for hosting RAG night Lizzie Siegle 🙏 Great conversations about the state of vector DBs and advanced RAG techniques used in production. Plus, finally had a chance to see the entropy wall in real life 😁✌️

Matryoshka Representation Learning (MRL) is a super exciting approach to improving the quality and efficiency of embedding models and strategies ✨ MRL allows models to store more information in the earlier dimensions of their data vectors. This method not only boosts

Announcing our new RAG++ course, now available in collaboration with @CohereAI and @Weaviate_io. Created for engineers looking to build production-ready RAG systems. The course covers everything from evaluation strategies and data preprocessing to advanced retrieval techniques

Time for day 0! GitHub #GitHubUniverse

ColPali is changing the game for PDF retrieval by eliminating the need for OCR and chunking methods 🚀 Inspired by ColBERT’s success with text, ColPali splits an image of a document into patches, which are then processed through a vision LLM called PaliGemma. The embeddings for

Hey everyone! I am super excited to share our new research report is live on ArXiv! 🎉 Querying Databases with Function Calling! Thread with more details! 🧵(1/8)

AI Agents in production! Had a great conversation with Byron Voorbach from Weaviate AI Database to break it all down: 💡 Where enterprises can deploy AI agents today to cut costs and scale. 🔍 How Weaviate uses agents to transform data and drive better AI outcomes. 🚀 How we built