Andre Zayarni

Co-Founder at Qdrant, an open-source, high-performance Vector Database written in Rust. 🦀
I am mostly active on LinkedIn

[Andre Zayarni @andre_z]

@taranjeetio @mem0ai Congrats!

[Andre Zayarni @andre_z]

Please welcome Qdrant Edge, @qdrant_engine, for the Physical AI age. 🤖 📟 🧠 🦀 🦾
https://t.co/tc7TZC2kBz

[Alexey Grigorev @Al_Grigor]

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 👉 https://t.co/jMr6CLXfsS

[Andre Zayarni @andre_z]

🚀 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: https://t.co/NaCxAPeEox 🎟️

Want to speak? Apply: https://t.co/GPT8pCvRhs 📢 More info: https://t.co/NQHWYObaE5. For partnerships, DM me! PS: Repost with >=10 👍 for a free ticket! 😬

[Andre Zayarni @andre_z]

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: https://t.co/Tjfr8Q1LbO.

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: https://t.co/W521H4nzhz.

Does North Korea have a cloud platform? 🤯

[Qdrant @qdrant_engine]

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 🧵

[Andre Zayarni @andre_z]

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.⤵️

[Andre Zayarni @andre_z]

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

[Andre Zayarni @andre_z]

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.⤵️

[Andre Zayarni @andre_z]

For 𝐡𝐨𝐫𝐢𝐳𝐨𝐧𝐭𝐚𝐥 𝐬𝐜𝐚𝐥𝐚𝐛𝐢𝐥𝐢𝐭𝐲, sharding and consensus logic need to be built around search. https://t.co/eL0BRYTaog
For flexible 𝐦𝐞𝐦𝐨𝐫𝐲 𝐫𝐞𝐬𝐨𝐮𝐫𝐜𝐞 𝐨𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧, quantization techniques need to be applied. https://t.co/NZxiuTrhuK
For a more 𝐩𝐫𝐞𝐜𝐢𝐬𝐞 𝐫𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥, Hybrid Search with sparse vectors can be used. https://t.co/zDdytJP8FS
For 𝐦𝐮𝐥𝐭𝐢𝐭𝐞𝐧𝐚𝐧𝐜𝐲 𝐬𝐮𝐩𝐩𝐨𝐫𝐭, payload-based partitioning is required. https://t.co/Ir19TfBKAj
For even more 𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐭 𝐢𝐧𝐝𝐞𝐱𝐢𝐧𝐠, GPUs can be used. https://t.co/wcczDPthy4
For combining similarity search with domain-specific logic, a score boosting reranker can be applied. https://t.co/T7YWhqCE1x. And many, many more production-critical aspects.

[Andre Zayarni @andre_z]

@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! 😜 🦀 🚀

[Andre Zayarni @andre_z]

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. 💡
https://t.co/I8OX5yAvUj

[Andre Zayarni @andre_z]

@MongoDB is buying away content creators and community members of @qdrant_engine https://t.co/tx64kOwV19

[Andre Zayarni @andre_z]

Score Boosting was introduced in Qdrant @qdrant_engine v 1.14. It is not solely about similarity anymore. ;) https://t.co/tLKimmjOVj

[HoneyHive @honeyhiveai]

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 🤝

[Andre Zayarni @andre_z]

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.
https://t.co/PeIL0KNNkS