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-…

⏳ Starting in 1 hour: Qdrant Office Hours! Join us for a deep dive into Qdrant 1.17 with core engineer Luis Cossío 🚀 🕔 17:00 CEST / 08:00 PDT / 9:30 PM IST 📍 Qdrant Discord 👉 discord.gg/gFRtmG9F?event…

⏳ Reminder: Qdrant Office Hours - March 19 We’re diving into Qdrant 1.17 (Relevance Feedback + latency improvements) with our core engineer Luis Cossio. Ask questions, share what you’re building, and chat with the team. 🕔 17:00 CEST / 08:00 PDT / 9:30 PM IST 🔗 discord.gg/gFRtmG9F?event…

🚀 IIT Hack Winners built more than demos - they built systems that remember, reason, and improve over time. From dementia care → trend detection → smart agriculture 🌱 Common pattern? 👉 Memory + retrieval as core infra (powered by Qdrant) 📖 qdrant.tech/blog/iit-hack-…

Design team @qdrant_engine went crazy with this one

Tomorrow at @NVIDIAGTC I'm at the @Vultr stage to talk about edge to cloud video anomaly detection with @qdrant_engine Edge, @twelve_labs Marengo 3.0, and @nvidia Metropolis. Traditional video classifiers need labeled examples of every anomaly you want to catch. That breaks in the real world. So I took a different approach..

⏳ Just a few days left! 🇩🇪 Join us in Munich for “Unconference: Context Engineering with Open-Source” - an evening of open discussions on building better context layers for AI systems. Instead of traditional talks, we’ll dive into interactive conversations around: • Retrieval and vector search • Memory systems for AI agents • Designing robust context layers • Building production-grade AI with open-source tools Explore how tools like @deepset_ai, @qdrant_engine, and @cognee_ help engineers design better context pipelines for real-world AI applications. 📍 smartvillage Bogenhausen, Munich 🔗 luma.com/xg649r8v See you there! 👋

Agents don't make fewer retrieval calls than humans. They make orders of magnitude more. And they can't declare their retrieval strategy upfront. They shift from dense to hybrid search, tighten filters, and re-weight scores based on what prior steps returned. That's why we built Qdrant as composable primitives, not a fixed pipeline. Retrieval that adapts at query time, not configuration time. Or as @VentureBeat put it: Agents need vector search more than RAG ever did. venturebeat.com/data/agents-do…

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-…

New blog and guide just released! Try Gemini Embedding 2 with Qdrant on day one! 🔗qdrant.tech/blog/qdrant-ge…

We're back with monthly Office Hours Date 📅 : 19th March Time 🕔 : 17:00 CEST / 08:00 PDT / 9:30 PM IST Join us for a casual community hangout in the Qdrant Discord to share what you’re building, ask questions, meet the team, and connect with fellow developers. This month is extra special - we’ll be diving into our latest update Qdrant 1.17, including the new Relevance Feedback & Search Latency Improvements feature. If you have questions about how it works, when to use it, or how to integrate it into your applications, this is the perfect place to ask. Our core engineer, Luis Cossío, will also be joining the session to walk through the feature, answer questions, and discuss real-world use cases with the community. We’d love to have you drop by and chat. Discord event link: discord.gg/e5C47dNh?event… See you there! 👋

If your semantic search quality plateaus, don’t just tune the retriever; tune the system @glassdollar's platform turns enterprise problem statements into decision-ready shortlists of innovative startups. Search is an essential part of this. As their corpus grew to roughly 1M companies and ~10M documents, Elasticsearch-based vector search became a bottleneck. GlassDollar needed to scale retrieval, keep high recall, and reduce system complexity. Their key lesson: accuracy is not a single number from a retriever benchmark. It is the end-to-end outcome of the full RAG architecture, including query expansion, retrieval, ranking, and contextual ranking. After migrating from Elasticsearch to Qdrant, they: - Reduced infrastructure costs by ~40 percent for the same workload size - Unlocked faster retrieval that made query expansion practical at scale - Focused on end-to-end accuracy across query expansion, retrieval, ranking, and contextual ranking - Kept the stack simple for their Node.js and TypeScript-first engineering team The impact showed up in user behavior: GlassDollar saw a 3x increase in bookmarks in Q1, driven by higher engagement from existing users. Read the full story and architecture approach here: Case Study Link: qdrant.tech/blog/case-stud…

🇩🇪 Join us in Munich for Unconference: Context Engineering with Open-Source An interactive evening discussing the context layer behind modern AI systems - from retrieval and vector search to memory for agents. @qdrant_engine @deepset_ai @cognee_ 📍 Munich 🔗 luma.com/xg649r8v

Qdrant is now part of @Google's Agent Development Kit (ADK) integrations ecosystem In Google’s latest ADK announcement, Qdrant is highlighted as a supported integration for building AI agents with persistent semantic memory and vector search. As agents move from demos to production, retrieval and memory become critical. Being included in the ADK ecosystem means developers can integrate Qdrant’s vector search directly into their agent workflows - enabling scalable, low-latency semantic retrieval as a core capability. Agents that retrieve, reason, and remember with structure are the future of AI systems - and we’re excited to see Qdrant positioned as part of that foundation within the Google ADK ecosystem. Read the full announcement: developers.googleblog.com/supercharge-yo… #Qdrant #VectorSearch #AgenticAI #GoogleADK #RAG #AIInfrastructure

Fun day at the @mlopscommunity Coding Agent event teaching people about @qdrant_engine Sid Bidasaria from @claudeai with some advice: Markdown and planning is your friend when working with Claude. Always plan, and if you need to give your agent notes, use an md so it persists.

@usemyaskai builds AI customer support agents that needed retrieval for messy, always-changing support data. After narrowing in on customer support as the core use case, the team standardized on Qdrant Cloud as the vector search backbone for their platform: - RAG retrieval over docs + historical tickets - Hybrid search experimentation for tricky cases like product names and error codes - A self-learning loop: human resolutions after escalation get clustered into “self-learning articles” and re-indexed so the agent improves continuously In production, My AskAI reports ~75% ticket deflection, while keeping human handoff for low-confidence cases. Read the full case study for the technical details (and how they built self-improving retrieval pipelines): qdrant.tech/blog/case-stud…

New tutorial: Using Relevance Feedback in Qdrant Improve search quality without retraining models. Learn how to incorporate lightweight feedback directly into similarity computation to refine results at scale - perfect for RAG, agents, and semantic search systems. Read here: qdrant.tech/documentation/…

🚨 Happening Today! Join @itsclelia from @llama_index on the Qdrant Discord for: “Migrating to Qdrant Edge for On-Disk Vector Storage in Rust.” 🗓 Feb 27 ⏰ 4 PM CET / 7 AM PT / 8:30 PM IST On-disk trade-offs, Rust performance, edge deployments & real-world lessons. 👉 discord.gg/a8Z5GazC?event…