This is really neat. I really like the way that Qdrant focuses on simplicity and performance while still trying to combine it with the insights from heavier machine learning innovations for meaning extraction and semantic search.

An open source engineer from @llamaindex.bsky.social shares trial-and-error-learned lessons. For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social! ✅ useful tips, from chunking to evals-related; ✅ projects applying each tip in the wild. 👉 qdrant.tech/blog/hitchhi...

Free 10-week course! Learn RAG, vector search, hybrid search, evaluation, and more. Hands-on lessons from Qdrant’s experts. Learn more 👉 qdrant.tech/blog/datatal...

☕ Guess what? We're sponsoring the coffee breaks at @berlinbuzzwords.de 2025!

⏰ 𝐎𝐧𝐞 𝐰𝐞𝐞𝐤 𝐭𝐢𝐥𝐥 𝐁𝐞𝐫𝐥𝐢𝐧 𝐁𝐮𝐳𝐳𝐰𝐨𝐫𝐝𝐬 I'll really try to make my talk (on the 17th at 11:10 am in Kesselhaus) fit this "𝘏𝘮𝘮𝘮𝘮, 𝘐 𝘴𝘩𝘰𝘶𝘭𝘥 𝘵𝘳𝘺 𝘵𝘩𝘪𝘴 𝘳𝘯" vibe of @berlinbuzzwords.de! To TLDR, it's about making 𝐬𝐩𝐚𝐫𝐬𝐞 𝐩𝐚𝐫𝐭 𝐢𝐧 𝐡𝐲𝐛𝐫𝐢𝐝 𝐬𝐞𝐚𝐫𝐜𝐡𝐞𝐬 as 𝐫𝐞𝐥𝐢𝐚𝐛𝐥𝐞 as BM25, but 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜𝐚𝐥𝐥𝐲 𝐚𝐰𝐚𝐫𝐞 (so 𝐛𝐞𝐭𝐭𝐞𝐫 than BM25)

🥨 Come to the Bavarian Search Meetup! The 2nd meeting of 𝐁avaria, 𝐀dvancements in 𝐒𝐞arch 𝐃evelopment meetup, co-organized by our @mrscoopers.bsky.social, is happening in #Munich on the 12th of June! 👇

Create smart chat apps with custom data and enjoy easy setup in Visual Studio, VS Code, or CLI. Preview 2 of the .NET AI Template is here, and now it's easier than ever to build cloud-native #AI apps with #dotNETAspire and #Qdrant vector DB integration. Learn. https://msft.it/63326S1eg4

🚀 Build a real RAG API with .NET 8, Semantic Kernel, Phi-3, and Qdrant! 🎯 Enrich LLMs with real product data ⚙️ Local ONNX inference with Phi-3 🔥 Full API endpoints ready! Dive into the architecture 👉 wp.me/p29SK-Yu #DotNet #SemanticKernel #RAG #Qdrant #Phi3 #AI #MachineLearning #ONNX

Want to see MCP in action? Learn how to orchestrate OpenAI agents using MCP, AugmentCode, and Qdrant. 📅 April 29 @ 11 am ET 🔗 Save your spot: try.qdrant.tech/mcp-agent-in...

Relevance feedback helps search systems iteratively improve results toward relevance. It’s been studied for 60+ years — yet remains rare in modern neural search. We explored the field to understand why — and gathered this summary of methods proposed over the years. ⬇️

MCP week: Learn to use LlamaIndex to prep docs for Claude with a pre-built MCP server for @qdrant.bsky.social, using @angular.dev docs. Set up vector DB, process AI-friendly docs, configure MCP server, implement RAG pipeline: https://www.aiboosted.dev/p/building-your-own-rag-system-typescript

🚧 We ran vector search over 400M CLIP embeddings from LAION-400M — using Qdrant and just 64GB RAM. We wanted to see how far we could push Qdrant with minimal hardware and how much we could squeeze out of quantization, indexing, and async I/O.

A lot of people ask us: “𝗪𝗵𝘆 𝘀𝗵𝗼𝘂𝗹𝗱 𝗜 𝘂𝘀𝗲 𝗮 𝗱𝗲𝗱𝗶𝗰𝗮𝘁𝗲𝗱 𝘃𝗲𝗰𝘁𝗼𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 when I can simply add a vector plugin or extension to my existing database?” We wrote an article addressing this very common question. Article: qdrant.tech/articles/ded...

If you're working with large-scale vector ingestion, you should know how to manage memory efficiently. 👉 Learn the best practices for optimizing memory in Qdrant: qdrant.tech/articles/ind...

Qdrant AI Builders: Agents in the Enterprise @ AWS Loft With @arize.bsky.social, CrewAI, and @n8n.io 🚀 An evening for executives and technical leaders to explore AI agents and RAG in the enterprise. 🔗RSVP: lu.ma/etufeex8?tk=... 📅 Monday, February 10

We built our own storage engine to replace RocksDB for payload and sparse vector storage. It eliminates compaction overhead, optimizes sequential key access, and provides direct control over data writes. Benchmarks show 2x faster ingestion with stable throughput. Now live in Qdrant 1.13!

Join us Feb 13 @ 11 AM ET for a live session on deploying DeepSeek for agentic RAG purely open-source and in your own environment. ✅ Deploy DeepSeek locally ✅ Secure vector search with Qdrant ✅ Optimize AI for privacy-first use cases 👉 RSVP: buff.ly/40SkyAf

Running Qdrant on Hybrid Cloud? By default, your Qdrant database cluster is only accessible within your Kubernetes environment. But… what if you need external access for applications or users? Learn how to expose your Qdrant database cluster to external applications: www.youtube.com/watch?v=ikof...

Qdrant 1.13 introduces GPU Accelerated Indexing 🚀 Enabling up to 10x faster HNSW index construction compared to CPU-based systems while remaining platform-agnostic, with support for NVIDIA, AMD, and Intel GPUs. Release Notes: qdrant.tech/blog/qdrant-... Documentation: qdrant.tech/documentatio...

🚀 Qdrant 1.13.0 is out! Let’s look at the main features for this version:

Agentic RAG With LangGraph and Qdrant 🚀 Built as a developer assistant for Hugging Face 🤗 and Transformers libraries, this AI agent retrieves guides, docs, and real-time info to answer complex technical queries instantly. 🧰 Begin the tutorial here: qdrant.tech/documentatio...

Kick off 2025 with an exciting Agentic RAG workshop! 🚀 Join Qdrant, CrewAI & @n8n.io at the AWS Startup Loft San Francisco to learn from experts how to build an Agentic RAG app from scratch. Meet like-minded folks, explore AI agents, and have fun! Food & drinks provided. 🍕 RSVP: lu.ma/66xbjkyq

🌟 We’re happy to welcome @cle-does-things.bsky.social as our newest Qdrant ambassador! 🎉 Clelia has already made waves in the Qdrant ecosystem, and we’re excited to have her officially on board. 🚀 If you love vector search and want to make an impact, join the Qdrant Stars! ✨

🚀 Our Developer Portal has officially launched with a brand-new design! We’ve redesigned the experience to make it faster, clearer, and more intuitive, helping you focus on what matters most: vectors. 👉 Tell us what you think: qdrant.tech/documentation/

🚀 Missed the live session? Evgeniya Sukhodolskaya and Max Tkacz demonstrated how to design and deploy production-ready AI agents with @n8n.io low-code AI starter kit and Qdrant’s vector database. 👉 Watch the full recording: www.youtube.com/watch?v=_BQT...

🔍 𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐖𝐞𝐛 𝐒𝐞𝐚𝐫𝐜𝐡, 𝐏𝐫𝐢𝐯𝐚𝐭𝐞 𝐚𝐧𝐝 𝐒𝐞𝐥𝐟-𝐇𝐨𝐬𝐭𝐞𝐝 PrAIvateSearch is a self-hosted, open-source search tool that delivers smarter, contextual answers. It runs entirely on your machine, ensuring full privacy and control. Built by @cle-does-things.bsky.social 🚀

Quick preview of the next release feature. It is Qdrant running in cluster mode on 𝐒𝐭𝐞𝐚𝐦 𝐃𝐞𝐜𝐤 😁 and leveraging 𝐆𝐏𝐔 𝐚𝐜𝐜𝐞𝐥𝐞𝐫𝐚𝐭𝐢𝐨𝐧 to construct the HNSW ANN index. Just a few seconds for 100K data points index building. Coming soon. 🚀

How would you approach fact-checking? Researchers from The University of Texas at Austin developed a method that achieved a 26% accuracy improvement compared to all previous state-of-the-arts using Qdrant and AskNews. 👉 Learn more in the blog: emergentmethods.medium.com/detecting-mi...

🧨We’ll soon host a webinar around building production-ready AI agents with @n8n.io. It’s going to cover: 1⃣ using Qdrant for anomaly detection and classification on multimodal embeddings 2⃣ using n8n for designing AI Agentic workflows with all the possible tools & connections.

We took ColPali and made it 13x faster 🔥 ➡️ Reduced 1,030 vectors per page to just 38 using mean pooling ➡️ Pooled embeddings fetch top candidates and high-res embeddings fine-tune the results ➡️ 95.2% of original quality (NDCG@20 = 0.952) with far less computational overhead

Qdrant's own take on Agentic RAG is here! Kacper Łukawski tried the most popular frameworks and reported his findings. Many of you are building agentic systems with Qdrant, so we wanted to try popular frameworks from your perspective. qdrant.tech/articles/age...

Building an HNSW index with multivectors can be computationally demanding at scale. The quadratic complexity of comparing vectors leads to slow & inefficient processes.