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-…

The call for proposals for Vector Space Day 2026 in San Francisco closes May 6. You’re almost out of time! If you're building something worth talking about in retrieval, agents, memory, or edge AI, we want to hear from you. 300+ engineers will be gathered at The Midway on June 11. This is the audience that will actually understand what you built, ask hard questions, and remember your talk. Submit your proposal before May 6: forms.gle/SQ4phv4bPH1yDX… Event details: luma.com/vsd-sf

Most "Graph RAG" implementations are vector retrieval with extra steps. @datagraphs built something different. Their UK-based knowledge graph platform combines a proprietary graph database engine with Qdrant-powered semantic search, orchestrated by an agentic layer that picks the right retrieval path for each prompt. The insight from CEO Paul Wilton: vector and graph aren't competitors. They're complementary. Vector excels at semantic similarity over unstructured content. Graphs excel at empirical queries: negation, date ranges, mathematical operations on connected data. Force one to do the other's job and the system breaks. What they built: - Real-time embedding from the graph into Qdrant collections via streaming and queuing - Schema-first retrieval where the agent pulls the full graph schema before deciding how to query - Parallel execution across graph queries and vector retrieval, blended for the LLM - Every answer cited back to source for verifiable provenance Why Qdrant specifically: - Hybrid Cloud kept the entire stack inside their own AWS environment - Payload filtering DSL closely matched their existing OpenSearch patterns, so common metadata structures worked across the graph, OpenSearch, and Qdrant without translation - Terraform support and infrastructure automation fit their existing CI/CD workflows 18 months in production. Zero significant issues. The retrieval layer determines the ceiling of your AI's intelligence. Choose the right components. Compose them well. Full case study: qdrant.tech/blog/case-stud…

Vector search - now at the edge With Qdrant Edge: → Run vector search locally (no cloud) → Process sensor data in real time → Retrieve similar patterns instantly Vector search = on-device intelligence pub.towardsai.net/vector-search-…

Want to speak at Vector Space Day 2026? We're hosting our second full-day in-person event in San Francisco on June 11, and we're looking for engineers, researchers, and builders working on: - Search & AI Retrieval - Agents & Memory - Edge & Robotics AI The call for proposals closes May 6. Submit yours: forms.gle/SQ4phv4bPH1yDX… Already know you want to attend? Early bird tickets are selling out soon: luma.com/vsd-sf Last year we had 400+ people in Berlin. San Francisco is going to be even better!

We’re live at AI Dev Conference! Great to be here with the community - amazing energy and conversations so far 🙌 If you’re around for Day 2, come say hi at the Qdrant booth, we’d love to meet, chat about what you’re building, or just connect. Big thanks to @DeepLearningAI for organizing such a great event 👏 See you there 👋

As Qdrant continues to be used in critical enterprise workloads, we want to continue helping users build these applications. That’s why we have launched three new features to address common challenges for enterprise customers: 1. If you need to increase indexing, GPU-accelerated indexing in Qdrant Cloud increases indexing speeds up to 4x (according to our benchmarks). That’s helpful for high-write workloads (e.g. dynamic content catalogs, real-time recommendation systems, agentic). 2. For teams needing vector search with stronger guarantees on availability and higher uptime commitments, Qdrant Cloud offers Multi-AZ. This enables an SLA of up to 99.95%. 3. For applications that need to meet compliance requirements, audit logging is now available. It captures operations performed through the Qdrant API: queries, upserts, deletes, collection management, and snapshot operations. All are now generally available in Qdrant Cloud. Learn more here: qdrant.tech/blog/qdrant-cl…

Vector search ≠ just similarity This deep dive by Pavan Kumar, our star - shows how relevance feedback makes retrieval smarter 👇 → Learn from user signals → Refine results dynamically → Improve RAG accuracy @manthapavankumar11/beyond-similarity-search-advanced-relevance-feedback-retrieval-in-qdrant-for-rag-250d2f46ac2e" target="_blank" rel="nofollow noopener">medium.com/@manthapavanku…

Tomorrow: SF Happy Hour (AI Dev Week) If you’re in San Francisco, this is your last call 👇 We’re hosting an unofficial AI Dev Happy Hour, a relaxed space to meet others building in AI, Agents, and vector search. Stop by after the first day of the conference DeepLearning.AI RSVP: luma.com/yjb156c2 See you there!

Vector search in prod ≠ just embeddings A 5-part series by Pavan Vemuri breaks it down 👇 → Hybrid search → Quantization (40× memory ↓) → Filterable HNSW → Multi-vector → Reranking Real systems = combining these Link: dzone.com/articles/essen…

Search Relevance Built Into the Vector Index x.com/i/broadcasts/1…

SF Happy Hour on April 28 In town for AI Dev? Come hang with the Qdrant team 👇 → Meet builders → Talk AI / RAG → No talks, just good convos 🔗 luma.com/yjb156c2

Reranking can only take you so far. What if relevance was built into your vector search? Join our Vector Space Talk with @krotenWanderung and @NathanJLeRoy to see how this works in real systems. 🗓️ Today ⏰ 6:00 PM CEST / 9:00 AM PDT / 9:30 PM IST We’ll cover: → Why reranking hits limits → How to inject relevance into vector search → Real production use cases Live Q&A included! 🔗 youtube.com/watch?v=Z5j1wx…

Persistent memory for AI agents = vector search Instead of stuffing context into prompts: → store interactions as embeddings → retrieve when needed → maintain memory across sessions Powered by Qdrant (fully local setup) Link: mem0.ai/blog/adding-pe…

Next Week at AI Dev 2026 - Edge → Cloud Video Anomaly Detection If you’re attending AI Dev, don’t miss this session from @ptdamiba at Qdrant. A practical walkthrough of building a real-time video anomaly detection system - from edge to cloud. 🗓️ April 29 🕐 1:45 PM – 2:25 PM Register here: ai-dev.deeplearning.ai

Vector Space Day is coming to San Francisco. June 11, 2026. One full day. 300+ engineers, researchers, and AI builders. Last year we brought the community together in Berlin to go deep on retrieval and AI infrastructure. Now we're taking it to SF. The agenda covers: - Search & AI Retrieval - Agents & Memory - Edge & Robotics AI Speakers from @llama_index, @mem0ai, @arizeai, @twelve_labs, @neo4j and more will be released over the coming weeks. Grateful to @awscloud and @Vultr for their continued support. Read more on the blog: qdrant.tech/blog/vector-sp… Get your early bird ticket now: luma.com/vsd-sf

Today at 5pm CEST, @qdrant_engine and @neo4j

Tomorrow at 11 AM EDT, we’re going live with @neo4j to demo a Biomedical GraphRAG AI Copilot - combining vector search with knowledge graphs for explainable reasoning over PubMed. See how vector search powers grounded retrieval in complex scientific workflows. Register now: luma.com/a7ai1y4t

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: discord.gg/EMXFadQv?event… Join us, ask questions, and learn from real-world experience!

SF Happy Hour - April 28 In town for AI Dev by @DeepLearningAI? Come hang with the Qdrant team 👇 → Meet builders → Talk AI / RAG / vector search → Or just chill No talks, just good convos 🔗 luma.com/yjb156c2

Edge → Cloud Video Anomaly Detection Catch @ptdamiba (Qdrant) at AI Dev 👇 🗓️ 29th April 🕐 1:45–2:25 PM → Vector search for anomalies → Edge + cloud systems 🔗 ai-dev.deeplearning.ai