Andre Zayarni

@taranjeetio @mem0ai Congrats!

Memory is what makes us human. It's also what makes AI truly intelligent. @mem0ai has raised $24M to build the universal memory layer for AI. Thousands of teams in production. 14M downloads. 41K GitHub stars. Intelligence needs memory & we're building it for everyone. More👇

Please welcome Qdrant Edge, @qdrant_engine, for the Physical AI age. 🤖 📟 🧠 🦀 🦾 linkedin.com/feed/update/ur…

I have 3 free tickets to the Vector Space Day conference from @qdrant_engine Want to win one? 🔸 Follow me 🔸 Retweet this tweet Winners selected randomly. Results on Friday Good luck 🍀 More info 👉 lu.ma/p7w9uqtz

🚀 Save the date! Join us for the first live 𝐕𝐞𝐜𝐭𝐨𝐫 𝐒𝐩𝐚𝐜𝐞 𝐃𝐚𝐲 conference on Sept 26 in 𝐁𝐞𝐫𝐥𝐢𝐧! 🎉 We’ll dive into Vectors, Search, LLMs & AI magic. Expect talks, workshops & an 🎉 After Party with DJ! 🎶 Grab limited tickets here: qdrant.to/vsd1 🎟️ Want to speak? Apply: lnkd.in/daP7Y_rS 📢 More info: qdrant.to/vsd1-info. For partnerships, DM me! PS: Repost with >=10 👍 for a free ticket! 😬

I've been asked if we fear cloud hyperscalers like AWS, GCP, or Azure forking our open-source engine. I believe these times are over; they prefer partnerships. But Yandex Cloud offers Qdrant without informing us: lnkd.in/dcTMg79d. Sberbank-Technology is building an enterprise version, while we already have it, but companies in your country can't use it. Also, other providers offer managed Qdrant services: lnkd.in/d8_wcFfE. Does North Korea have a cloud platform? 🤯

It is party time! Qdrant has been navigating the community through the Vector Space for four years already. 🎉 And it's summer, and we want to take care of your clothes, too. So, here is our official Qdrant Swag Giveaway campaign. Rules in 🧵

Qdrant is not a Graph Database, but graphs are still the backbone of vector search technology since HNSW is a graph-based ANN algorithm. I stumbled upon an interesting white paper that evaluates twelve state-of-the-art graph-based methods on large datasets, up to 1B vectors.⤵️

It is not only about the underlying algorithms, but also about the engine and features around it.

For 𝐡𝐨𝐫𝐢𝐳𝐨𝐧𝐭𝐚𝐥 𝐬𝐜𝐚𝐥𝐚𝐛𝐢𝐥𝐢𝐭𝐲, sharding and consensus logic need to be built around search. qdrant.to/d9d For flexible 𝐦𝐞𝐦𝐨𝐫𝐲 𝐫𝐞𝐬𝐨𝐮𝐫𝐜𝐞 𝐨𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧, quantization techniques need to be applied. qdrant.to/q10n For a more 𝐩𝐫𝐞𝐜𝐢𝐬𝐞 𝐫𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥, Hybrid Search with sparse vectors can be used. qdrant.to/hybrid For 𝐦𝐮𝐥𝐭𝐢𝐭𝐞𝐧𝐚𝐧𝐜𝐲 𝐬𝐮𝐩𝐩𝐨𝐫𝐭, payload-based partitioning is required. qdrant.to/m10y For even more 𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐭 𝐢𝐧𝐝𝐞𝐱𝐢𝐧𝐠, GPUs can be used. qdrant.to/gpu For combining similarity search with domain-specific logic, a score boosting reranker can be applied. qdrant.to/boosting. And many, many more production-critical aspects.

@kevin_scott, Microsoft's CTO, used @qdrant_engine as the vector engine for the #NLWeb demo at the opening keynote of the annual Build Conference. #opensource rules! 😜 🦀 🚀

Meet 𝐦𝒊𝒏𝒊𝑪𝑶𝑰𝑳 𝘪𝘴 𝘢 𝘤𝘰𝘯𝘵𝘦𝘹𝘵𝘶𝘢𝘭𝘪𝘻𝘦𝘥 𝘱𝘦𝘳-𝘸𝘰𝘳𝘥 𝘦𝘮𝘣𝘦𝘥𝘥𝘪𝘯𝘨 𝘮𝘰𝘥𝘦𝘭 by @qdrant_engine. 𝘐𝘵 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘦𝘴 𝘦𝘹𝘵𝘳𝘦𝘮𝘦𝘭𝘺 𝘴𝘮𝘢𝘭𝘭 𝘦𝘮𝘣𝘦𝘥𝘥𝘪𝘯𝘨𝘴 (8𝘥𝘪𝘮 𝘰𝘳 𝘦𝘷𝘦𝘯 4𝘥𝘪𝘮) 𝘸𝘩𝘪𝘭𝘦 𝘴𝘵𝘪𝘭𝘭 𝘱𝘳𝘦𝘴𝘦𝘳𝘷𝘪𝘯𝘨 𝘵𝘩𝘦 𝘸𝘰𝘳𝘥'𝘴 𝘤𝘰𝘯𝘵𝘦𝘹𝘵 𝘧𝘰𝘳 𝘦𝘢𝘤𝘩 𝘸𝘰𝘳𝘥 𝘪𝘯 𝘢 𝘴𝘦𝘯𝘵𝘦𝘯𝘤𝘦. 💡 qdrant.to/miniCOIL

@MongoDB is buying away content creators and community members of @qdrant_engine linkedin.com/feed/update/ur…

Score Boosting was introduced in Qdrant @qdrant_engine v 1.14. It is not solely about similarity anymore. ;) linkedin.com/feed/update/ur…

By popular demand, we’re excited to introduce an integration with @qdrant_engine! Retrieval powers most AI apps today, but it's so hard to get right. From simple KNN to agentic RAG, how do you know what search strategy works best for your use case? Enter HoneyHive + Qdrant 🤝

In 2022, as Qdrant was in its very early stages, I virtually met @ethansteininger from MongoDB and pitched him our vector search engine written in Rust. Now, three years later, he is using @qdrant_engine for his own product, Mixpeek. qdrant.tech/blog/case-stud…