Qdrant @qdrant.bsky.social · 14/01/2026Read here to see how Flipkart’s Trust & Safety team built real-time multimodal similarity search with Qdrant Link: qdrant.tech/blog/case-st... 000
Qdrant @qdrant.bsky.social · 07/01/2026Voice AI on live calls, powered by real-time retrieval. Community member Henryk Brzozowski built a demo where a dealership’s inventory is indexed in Qdrant - enabling sub-second answers like “Any Fords under $30k?” on live phone calls. RAG + voice. Real inventory. In production. 020
Qdrant @qdrant.bsky.social · 15/12/2025⏰ Reminder: Qdrant Office Hours - in 2 days! 🗓️ 18th December ⏰ 9:30 PM IST | 9:00 AM PST | 5:00 PM CET Speakers: - Kumar Shivendu - Qdrant v1.16 update - Clelia Astra Bertelli - StudyLlama updates Link to the event: discord.com/events/90756... #Qdrant #VectorSearch #Discord #AIInfrastructure #LLM 000
Qdrant @qdrant.bsky.social · 12/12/2025Get started on the Qdrant Essentials Course and get your Qdrant Certification here: qdrant.tech/course/essen... What would do want to see in an Qdrant Course? Let us know in the comments! 010
Qdrant @qdrant.bsky.social · 11/12/2025Qdrant’s ACORN fixes the “zero results” problem in filtered vector search. Smarter second-hop exploration = higher recall under strict filters. Shared by our star NiranjanAkella 🔥 Link: blog.stackademic.com/zero-results... 010
Qdrant @qdrant.bsky.social · 07/12/2025𝐊𝐲𝐥𝐢𝐞 - 𝐚 𝐦𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 𝐖𝐡𝐚𝐭𝐬𝐀𝐩𝐩 𝐀𝐈 𝐚𝐠𝐞𝐧𝐭 Spotted this cool project by Jonathan Mukhobe Sr. Kylie handles text, images, voice, tasks, search, and more - built with LangGraph + Groq. 🧠 Powered by Qdrant + MiniLM for long-term memory. Check it out: github.com/jonathanmuk/... 000
Qdrant @qdrant.bsky.social · 02/12/2025Multimodal Fashion Search with Qdrant + ScrapeGraphAI 👗⚡️ Francesco Zuppichini and our Head of DevRel Neil Kanungo just shared a slick walkthrough on building a multimodal clothing search engine using ScrapeGraphAI + CLIP + Qdrant. Full demo + write-up: 🔗 scrapegraphai.com/blog/scrapin... 010
Qdrant @qdrant.bsky.social · 27/11/2025Vector search is booming - and it’s powering accurate RAG and smarter AI apps. SE Radio’s new episode with Kacper Łukawski breaks down: ⚡ When to use embeddings ⚡ Real-world architectures ⚡ Lessons from scaling search ⚡ Why teams choose Qdrant 🎧 Listen: se-radio.net/2025/10/se-r... 020
Qdrant @qdrant.bsky.social · 23/11/2025Loved this project by M K Pavan Kumar - an AI-driven load-testing agent that runs tests, interprets results, and recalls past runs using Qdrant as its vector memory. A clean example of how semantic search can level up performance engineering. Read: 👉 towardsdev.com/designing-a-... 010
Qdrant @qdrant.bsky.social · 21/11/2025Cosmos built an editorial-grade visual search engine on Qdrant Cloud - blending text, color, and hybrid queries in under 500 ms. Art meets engineering. 🔗 qdrant.tech/blog/case-st... 020
Qdrant @qdrant.bsky.social · 19/11/2025Qdrant 1.16 is out! 🎉 It brings tiered multitenancy, smarter filtered search with ACORN, faster disk-based HNSW via inline storage, better full-text search, safer conditional updates, and a refreshed Web UI. Read the full release overview to dive deeper: github.com/qdrant/qdran... 120
Qdrant @qdrant.bsky.social · 14/11/2025Xaver used a two-tier AI engine on Qdrant to cut latency by 2–3 seconds and deliver sub-second answers - letting their team focus on better advisory experiences, not infra. Full story: qdrant.tech/blog/case-st... 010
Qdrant @qdrant.bsky.social · 13/11/2025An AI HR Assistant that finds the perfect opportunities from “Python dev (FinTech)” to “AI intern.” 🌌 Built by Chetan Kumar using Next.js, FastAPI, LangChain, OpenAI & Qdrant. 🎥 Demo: www.loom.com/share/257ed8... 010
Qdrant @qdrant.bsky.social · 12/11/2025Quantization isn’t a trade-off anymore, it’s a must for scalable AI. Niranjan Akella breaks down how Qdrant’s 1.5-bit Quantization kills the Float32 tax with 24× compression, no recall loss, and sub-40 ms latency, all powered by Rust for real-time performance. Read more: qdrant.tech/documentatio... 010
Qdrant @qdrant.bsky.social · 11/11/2025Powering next-gen e-commerce recommendations with hybrid sparse + dense vectors in Qdrant Sayanteka Chakraborty shares how combining keyword + semantic search boosted relevance and speed ⚡ 3× faster recs 📈 30–40% higher engagement Hybrid search = smarter personalization Read more: t.co/dlVzDhdc1o 010
Qdrant @qdrant.bsky.social · 06/11/2025🧩 Community highlight: Matthieu Nicolescu built a fully self-hosted, cloud-native RAG stack using Qdrant, KServe, and Envoy AI Gateway - all on Kubernetes, no external APIs. A great blueprint for scalable, data-sovereign AI pipelines. Check here: medium.com/h7w/cloud-na... 010
Qdrant @qdrant.bsky.social · 04/11/2025🗞️ The October Qdrant Newsletter is live! 🚀 Highlights: • Launch of Qdrant Academy & “Essentials” course • New tools, tutorials & integrations • Community projects & ecosystem growth 👉 Read: try.qdrant.tech/october-news... 📩 Subscribe: qdrant.tech/subscribe #Qdrant #VectorSearch #AI #OpenSource 020
Qdrant @qdrant.bsky.social · 04/11/2025📅 Nov 12, 6 PM CET - Join Dat Daryl Ngo (Arize AI) to explore how to make Agentic RAG systems observable, accountable & self-improving with open-source tools and real-world insights. 👉 Register here: #AI #RAG #Observability #ArizeAI 040
Qdrant @qdrant.bsky.social · 30/10/2025Exciting news from our partner @confluent.io! Confluent’s new Streaming Agents and Real-Time Context Engine bring live context to AI agents and enterprise apps. Together, Qdrant × Confluent enable developers to build real-time, AI powered by streaming data and vector search. 👉 t.co/DurLLwYMXO 010
Qdrant @qdrant.bsky.social · 29/10/2025Qdrant joins the AI-Powered Search course as a guest lecturer! Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull. 🔗 Details: aipoweredsearch.com/articles/ai-... 031
Qdrant @qdrant.bsky.social · 17/10/2025🫶 Big thanks to everyone who joined Qdrant’s Discord Office Hours! Loved the energy, ideas, and stories - and special thanks to Brian, Joshua, Clelia, and Tarun for the great insights. See you next month for more tech, chats, and demos! 💬 020
Qdrant @qdrant.bsky.social · 10/07/2025An 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... 040
Qdrant @qdrant.bsky.social · 10/06/2025☕ Guess what? We're sponsoring the coffee breaks at @berlinbuzzwords.de 2025! 130
Qdrant @qdrant.bsky.social · 02/06/2025🥨 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! 👇 120
Qdrant @qdrant.bsky.social · 14/04/2025Want 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... 010
Qdrant @qdrant.bsky.social · 02/04/2025Relevance 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. ⬇️ 100
Qdrant @qdrant.bsky.social · 28/03/2025🚧 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. 110
Qdrant @qdrant.bsky.social · 19/02/2025A 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... 131
Qdrant @qdrant.bsky.social · 06/02/2025We 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! 130
Qdrant @qdrant.bsky.social · 31/01/2025Join 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 010
Qdrant @qdrant.bsky.social · 24/01/2025Qdrant 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... 000
Qdrant @qdrant.bsky.social · 23/01/2025Our New Storage Architecture 🌐 There are four elements: the Data Layer, Mask Layer, the Region and Tracker Layer. This new backend ensures constant-time reads/writes, even for massive datasets. 200
Qdrant @qdrant.bsky.social · 23/01/2025HNSW Graph Compression 📈 We’ve now adapted Delta Encoding for the HNSW graph structure. In our experiments, the memory footprint of the HNSW graph was reduced by up to 30% with no measurable performance degradation. 100
Qdrant @qdrant.bsky.social · 23/01/2025Strict Mode for Operational Control 🖥️ Additional config for consistent performance in multi-tenant setups. Set advanced operational restrictions and ensure detailed error feedback. api.qdrant.tech/api-referenc... 100
Qdrant @qdrant.bsky.social · 23/01/2025GPU Accelerated Indexing ⚡️ Index up to 10x faster with architecture-free support for NVIDIA, AMD, and Intel GPUs! Here is a picture of us, running Qdrant with GPU support on a SteamDeck (AMD Van Gogh GPU): 100
Qdrant @qdrant.bsky.social · 13/01/2025Agentic 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... 120
Qdrant @qdrant.bsky.social · 06/01/2025🌟 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! ✨ 220
Qdrant @qdrant.bsky.social · 30/12/2024🚀 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/ 120
Qdrant @qdrant.bsky.social · 18/12/2024🔍 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 🚀 210
Qdrant @qdrant.bsky.social · 16/12/2024Quick 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. 🚀 031
Qdrant @qdrant.bsky.social · 03/12/2024🧨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. 1122
Qdrant @qdrant.bsky.social · 02/12/2024We 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 151
Qdrant @qdrant.bsky.social · 21/11/2024Results? - Recall@20: 0.92, - NDCG@20: 0.95 Want to see how we did it? The webinar starts soon! 100
