Bob van Luijt
@bobvanluijt
Co-Founder and CEO of @weaviate_io. I ๐ all things related to tech, machine learning, digital business, open-source, fashion, and music
Everyone is talking about building AI agents. But what if you donโt code? Thanks to @n8n_io thatโs no longer a problem. With the new Weaviate Community Node, you can build powerful agents that run on your entire knowledge base by just clicking, dragging, and dropping. Hereโsโฆ
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
Watch this #SASInnovate On Demand session to learn how SAS and Weaviate are unlocking enterprise knowledge with #GenerativeAI. #artificialintelligence #AgenticAI #GenAI #RAG #AI 2.sas.com/6014fz5iq
Manually creating GitHub issues from Slack messages is a productivity killer. @PriteshKiri decided to fix it with @ToolJet and Weaviate. ๐ค The context for a new issue often lives in a Slack thread, a customer email, or a quick note. Translating that into a perfectlyโฆ
Your vector database is growing faster than expected. Now what? If you're like most teams building AI applications, you've probably hit that moment where your vector DB starts showing signs of strain. Letโs break down your scaling options. ๐ ๐ง๐๐ผ ๐ฝ๐ฎ๐๐ต๐ ๐ณ๐ผ๐ฟ๐๐ฎ๐ฟ๐ฑ:โฆ
๐ Here we go!
Vibe coding vector search with @weaviate_io works pretty well with Gemini in Google Colab. What are your tips for working with coding assistants and Jupyter Notebooks?
Here's how to build your own AI research assistant that spots trends and automatically sends you a weekly summary ๐ @n8n_io and @weaviate_io make the best combo ๐ The workflow functions in two parts: ๐ฃ๐ฎ๐ฟ๐ ๐ญ: ๐ง๐ต๐ฒ ๐๐ฎ๐๐ฎ ๐ฃ๐ถ๐ฝ๐ฒ๐น๐ถ๐ป๐ฒ Every week, this workflowโฆ
Vibe coding vector search with @weaviate_io works pretty well with Gemini in Google Colab. What are your tips for working with coding assistants and Jupyter Notebooks?
How do you feed a 500,000-word novel to an AI? You can't. Not all at once, anyway. This is where ๐ฐ๐ต๐๐ป๐ธ๐ถ๐ป๐ด comes in. ๐ช๐ต๐ฎ๐ ๐ถ๐ ๐๐ต๐๐ป๐ธ๐ถ๐ป๐ด? Chunking is the pre-processing step of splitting texts into smaller pieces of texts, i.e. "chunks". Each chunk becomes theโฆ
Get started with Gemini Embedding using @weaviate_io, which supports over 100+ languages and flexible dimensions for performance and storage needs. Check out the notebook. github.com/weaviate/recipโฆ
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
Vector embeddings all the way down
What really runs LLM models.. IYKYK @weaviate_io
Berlin or San Francisco? Why not both?! It doesnโt matter as long as youโre bringing the right people together ๐ค @PrimeIntellect in Berlin and for sure @weaviate showed up ๐ It's time for decentralised Weaviate I would say.
Using Weaviate's cloud offering for RAG significantly reduced infrastructure overhead and costs for my AI app. Storing only encrypted data references in Weaviate, while users manage their own decryption keys, simplifies data ownership. Supplementing it with a r โ via @fleckchat
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