Qdrant

Most vector databases treat retrieval as a single operation. That's the wrong abstraction. Storing embeddings and returning nearest neighbors is a solved problem. The hard problem is what happens next. We solve it through composable vector search, built in Rust. Today, led by AVP, with Bosch Ventures, Unusual Ventures, Spark Capital, and 42CAP, we're announcing our $50M Series B to accelerate it. Learn more about Qdrant’s composable vector search and our latest funding round here: qdrant.tech/blog/series-b-…

How do you run vector search at 20B+ vectors across 5 regions for 38 teams? @HubSpot built VAST - Vector as a Service, entirely on Qdrant. 150 clusters, 2K+ pods, 9.5B vectors in a single collection, 5K writes/sec with spikes to 100K. the real story: they outgrew Helm fast. Helm can't call the Qdrant API to transfer shards, maintain replication factor, or handle state-aware scaling. cluster creation took hours. so they built a Kubernetes operator specifically for Qdrant. shard management, replication, lifecycle automation, all handled automatically. cluster spin-up: hours → minutes. result: 65% reduction in resource skew on a 3B+ point BM42 sparse vector collection. full talk here: youtube.com/watch?v=46aQff… thanks Oleg Tereshin and Xin Liu from @HubSpot team, for sharing at Vector Space Day SF 🙌

congrats to @Haystack_AI on 3.0 🎉. If you're building with Haystack 3.0, Qdrant integrates natively with dense, sparse, and hybrid retrieval. the Haystack team put together a great movie recommendation agent demo showing exactly this pattern with Qdrant: qdrant.tech/course/essenti…

Join us for an upcoming webinar on “Why does my RAG-agent get worse? A live autopsy” As collections grow, documents change, chunks get duplicated, and retrieval pipelines evolve, Agent's quality can decline without an obvious breaking point. @DylanCouzon from Qdrant and Rishabh Hada from Future AGI will build, debug, and fix RAG agents through a single end-to-end workflow. Qdrant powers the retrieval layer, while Future AGI will trace and evaluate the agent throughout the same workflow. What we’ll cover: - Build a RAG agent and observe where the agent is losing quality - Migrate to a new embedding model with zero downtime - Remove duplicate and fragmented chunks from the collection - Add late interaction reranking - Compare evaluation scores before and after each change to verify what actually worked Date & Time: Thursday, August 6 at 6:30 PM CEST | 9:30 AM PDT | 10:00 PM IST Register for the webinar now: luma.com/future-pq6q

"Continual learning isn't a training problem. It's a memory problem." @taranjeetio (co-founder & CEO, @mem0ai) breaks down why agents need memory before they need retraining at our Vector Space Day conducted in SF. - Weights = stable, general stuff (skills, reasoning patterns) - Memory = everything tied to a specific user/team/org - fast, inspectable, reversible, portable His 5-step loop for agent memory: observe → extract → retrieve → act → forget/update Built on real lessons scaling @mem0ai (open-source memory layer, running on @qdrant_engine under the hood) in production. Full talk: youtube.com/watch?v=yw-7Of…

If you're building a system for multiple customers or teams and need to keep their data isolated, multitenancy is what you need. Pavan put together a great guide on building a scalable multitenant search system with Qdrant and @llama_index. The guide shows how to: → Isolate each customer's data within a single Qdrant collection (yes, you don't need multiple collections) → Build secure, payload-filtered retrieval pipelines → Implement hybrid search with Qdrant and @llama_index → Scale to many tenants without the overhead of managing hundreds of collections Read Pavan's article: towardsdev.com/scaling-search… We also have a full guide covering tiered multitenancy, tenant isolation patterns, and performance tuning for your production use cases: qdrant.tech/documentation/…

Don’t forget to join today’s Qdrant Office Hours on Discord! We’ll be having an open discussion, and we’d love to hear your opinions, feedback, questions, or anything else you’d like to talk about. We host Office Hours every 3rd Thursday of the month, and going forward, we’ll keep them more discussion-oriented so everyone has a chance to bring up topics they’d like to discuss. Time: 6:00 PM CEST | 9:00 AM PDT | 9:30 PM IST Link to the event: discord.gg/pVDGNpjuB?even… See you there!

Products aren’t one-dimensional, your embeddings shouldn’t be either. Divy Yadav shows how to build a multi-aspect semantic search engine using Qdrant Multivectors for richer, more relevant e-commerce retrieval. pub.towardsai.net/multi-aspect-e…

What if your AI could remember your life, completely offline? Satyam Sahu from our community built an offline life memorizer using Gemini 2.0 + Qdrant Edge for private, on-device AI memory and semantic retrieval. A great example of what’s possible with edge AI and vector search. pub.towardsai.net/building-an-of…

The qdrant-advisor skill is now easily installed to any of your coding assistants: npx skills add qdrant/skills/meta/qdrant-advisor Installing this one skill keeps your agents primed with the latest skills context for your projects and deployments. Even as we continually improve and add to said skills. Read more here: github.com/qdrant/skills

Our next Qdrant Office Hours is coming up, and we’ve got a great lineup of community demos and discussions! Date: July 16 Time: 9:30 PM IST | 6:00 PM CEST | 9:00 AM PDT Here’s what’s on the agenda: - Qdrant Edge – updates, demos, and discussions. - How to Implement Multitenant Search in Qdrant Our Star Kameshwara Pavan kumar Mantha will walk us through building efficient multitenant search with Qdrant. - Semantic AI Bookmarking with Qdrant Our Star Mohammed Arbi Nsibi will showcase a Chrome extension he’s been using daily to save and semantically search AI resources. We’ll also have an open discussion on benchmarking, retrieval quality, and whatever questions the community brings. Link to register: discord.gg/pVDGNpjuB?even… See you on July 16!

AI has gotten better at reasoning, but it still forgets almost everything. Join @DylanCouzon from Qdrant and James Le from @twelve_labs on July 28 for an evening dedicated to AI memory, video intelligence, and retrieval systems. Hear from engineers building production AI systems as they cover: → Persistent memory for video AI → Collective memory for Edge AI with Qdrant Edge → Practical retrieval architectures and live demos Want to showcase your own project? We’re also hosting community demos, and only 2 demo slots remain! If you’re building with AI, retrieval, video intelligence, or agentic workflows, we’d love to have you present your work. 📅 July 28 📍 Bellevue, WA 🎟️ Register here: luma.com/kyksgkak See you there!

Benchmark results:

Elastic's benchmark claims Qdrant is 7x slower on disk search. They never enabled the two features built for that workload. We turned them on and found 2x throughput, half the latency, 1/3 the compute. Read more: qdrant.tech/blog/benchmark…

Most retrieval agents follow the same pipeline for every query. Join us tomorrow to learn how to build retrieval agents that evaluate, adapt, and improve mid-query. In this live session, you’ll learn how to: → Choose the right retrieval strategy for each question → Detect weak retrieval early with lightweight signals → Route queries using ColBERT reranking and IRCoT query decomposition → Build a STOP decision so your agent abstains instead of guessing 📅 Tomorrow, July 9 🕣 8:30 AM PT | 5:30 PM CEST Register now: luma.com/fdok2snb

Qdrant is heading to WeAreDevelopers World Congress! If you’re joining us in Berlin, here’s where you can find the team: July 9 - The Retrieval Layer for Edge AI Chadha Sridi and Sasha Denisov will explore how retrieval powers edge AI applications, featuring a live demo of Qdrant Edge running on smart glasses. July 10 - Workshop: Retrieval Layer in Context Engineering – From Intuition to Production Join @krotenWanderung for a hands-on workshop where you’ll build the context-engineering layer for a medical AI copilot while learning: → Semantic vs. lexical search → Hybrid retrieval → Knowledge graphs & GraphRAG → Context engineering patterns for production AI July 9–11 - Visit the Qdrant Booth Stop by throughout the event for live Qdrant Edge demos, chat with the team, and see how lightweight, privacy-first vector search enables modern AI applications. See you at WeAreDevelopers World Congress! 👋

semantic code search has an issue nobody talks about: the index doesn't know what branch you're on. you can build it from 'main' and every query answers from main, even on a branch that rewrote the function. So @DylanCouzon built a tutorial for scoped queries per branch: qdrant.tech/blog/branch-aw…

On-device AI RAG using Qdrant Edge x.com/i/broadcasts/1…

Going live in 15 minutes. Don't forget to join!