Qdrant

Livestream: from idea through research to a feature in production, cause #search #relevance is a) interesting b) useful TL;DR: how we built #relevance #feedback right into the #search engine and why it matters, live, April 23rd, 18:00-19:00 CEST, links at the bottom. Next Thursday, Nathan LeRoy will guide me with PhD-level questions (from "Can you re-share the screen, it's frozen(?)" to "Is there a comparative analysis of rel feedback methods?") through an overview of the 👆Vector Index Native Relevance Feedback API👆 Rough plan: + general overview of search relevance tooling (!) beyond (!) reranking and query rewriting, + reasoning behind the method we implemented in Qdrant, + showing API in practice, +++ and of course, answering them, PhD-level questions! 6 pm CEST, 23rd of April - YouTube: https://lnkd.in/g-cZHXwA - LinkedIn: https://lnkd.in/g-cZHXwA

 Happening in few hours: Qdrant Office Hours We’re going live today with a real-world session on running Qdrant in production. 🎙️ Tony Skorik will present: “Vigilante - Cluster Guardian for Self-Hosted Qdrant” If you’re managing or planning to run self-hosted Qdrant clusters, this is highly relevant. 👉 Built from 2+ years of operating multiple production clusters 👉 Think Patroni, but for Qdrant We’ll cover: • Scaling and maintaining clusters • Handling updates in production • Monitoring health and performance • Practical lessons from real deployments 🗓️ Today (April 16) 📍 Qdrant Discord Link: https://lnkd.in/gWWmBadz Join us, ask questions, and learn from real-world experience! #Qdrant #VectorSearch #OfficeHours #DevOps #AIInfrastructure

 Introducing the Qdrant Customers Page We’ve launched a new page highlighting how teams are using Qdrant in production - across industries and use cases. From search and recommendations to AI agents and real-time systems, it’s exciting to see how builders are pushing the boundaries of what’s possible with vector search. Explore how companies are using Qdrant to power: • Retrieval-Augmented Generation (RAG) • Recommendation systems • Semantic search • AI agents and real-time applications Check it out: https://lnkd.in/g2MSvRfp Deutsche Telekom HubSpot Tripadvisor OpenTable Alhena.ai Anima Aracor Bazaarvoice ConvoSearch Dragonfruit AI Dust Flipkart GlassDollar GoodData Lyzr AI Sprinklr Xaver, etc #Qdrant #VectorSearch #RAG #AIEngineering #GenAI #CustomerStories

If you’re in San Francisco for AI Dev Conference, come hang out with us for a relaxed evening with the community DeepLearning.AI We’re hosting an UNOFFICIAL happy hour on April 28, a great chance to: - Meet other builders working on AI, RAG, and vector search - Connect with the Qdrant team - Talk shop (or not 😄) over drinks No slides, no presentations - just good conversations. Register here: https://luma.com/yjb156c2 See you there 👋🏻 #Qdrant #AIDev #SanFrancisco #AICommunity #VectorSearch

Edge → Cloud Video Anomaly Detection with Qdrant At the AI Dev 2026, Thierry Damiba from Qdrant will walk through a real-world system for detecting anomalies in video streams. 🗓️ 29th April 🕐 1:45 PM – 2:25 PM (40 min) This session will cover how to: • Detect “what looks different from normal” using vector similarity • Combine edge-based processing + cloud infrastructure • Use Qdrant for fast, low-latency retrieval across video data • Move from prototype → production in real-time AI systems 🔗 Register now: https://lnkd.in/e5-GXM5s #Qdrant #EdgeAI #ComputerVision #VectorSearch #AIEngineering

Please join us in welcoming Ewa Szyszka and Dylan Couzon - two amazing additions to our DevRel team, focused on improving developer experience and growing the Qdrant ecosystem. - Ewa Szyszka is a Developer Relations professional based in San Francisco with a background in Computer Science and Hardware Engineering, passionate about bridging the gap between technology and the developer community. She holds a BSc in Computer Science and an MSc in Electronics, bringing a strong blend of deep technical foundations and communication skills to her work. Her DevRel experience spans technical content creation, community engagement, and public outreach - with a focus on delivering high-quality content at pace. Eva is also a polyglot, speaking Polish, English, German, French, Spanish, Japanese, and Korean, enabling her to connect authentically with developer communities around the world. Outside of tech, she enjoys aviation, motorcycles, and tennis - always chasing the horizon. - Dylan Couzon is based in New York City, and he helps developers build better AI applications. He is passionate about AI, programming, open source, and robotics, and enjoys sharing what he’s building and learning along the way. He’s always on the lookout for great networking events and meetups, especially in NYC - and loves connecting with the developer community.

What if vector search had its own “SQL”? One of the biggest challenges in vector search today isn’t retrieval - it’s how we express queries. This amazing article by Kameshwara Pavan Kumar Mantha introduces QQL (Qdrant Query Language) - an attempt to bring a familiar, structured query language to vector search. Instead of stitching together APIs, filters, and embedding calls, QQL lets you write queries like: → Search semantically → Apply filters → Combine dense + sparse retrieval → All in a single, readable query Under the hood, it performs hybrid retrieval (dense + sparse) and merges results, but from a developer’s perspective, it feels like writing one clean query. This is part of a broader shift: Making vector search more accessible, composable, and production-friendly Because today, the gap isn’t just performance - it’s developer experience. 📖 Read the full article: https://lnkd.in/gQsguzHC #Qdrant #VectorSearch #SearchEngineering #RAG #AIEngineering

What if you could push relevance signals directly into your vector search, instead of fixing results around retrieval? That’s exactly what we’ll explore in our next Vector Space Talk. 🎙️ Hosted by Nathan LeRoy, featuring Evgeniya Sukhodolskaya In this session, we’ll cover: - Why traditional approaches like reranking or query rewriting are not everything that one can use - The intuition behind relevance feedback in information retrieval - How to propagate relevance signals directly into the vector index using Qdrant’s Universal Query API Method that works across any data type, because it operates at the embedding level! 💬 Live Q&A included - bring your toughest search problems 📅 April 23 ⏰ 6:00 PM CEST / 9:00 AM PDT / 9:30 PM IST Join us on YouTube: https://lnkd.in/g-cZHXwA Linkedin Live Event: https://lnkd.in/gBH8vK6T #Qdrant #VectorSearch #SearchRelevance #IR #RAG #AIEngineering

Most search systems plateau at reranking. This talk explores what comes next. Join Nathan and Jenny (Sr. DevRel at Qdrant) as they break down Relevance Feedback in Vector Search - from its roots in IR research to its implementation using Qdrant’s Query API. You’ll learn how to: • Move beyond surface-level optimizations • Inject relevance signals directly into your vector index • Build adaptive, feedback-driven retrieval systems • Apply these concepts in production environments If you’re serious about search relevance, this is where things start to get interesting.