Int𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗤𝗱𝗿𝗮𝗻𝘁 𝗘𝗱𝗴𝗲, 𝗻𝗼𝘄 𝗶𝗻 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗯𝗲𝘁𝗮 😎 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗤𝗱𝗿𝗮𝗻𝘁 𝗘𝗱𝗴𝗲? It's a lightweight, in-process vector search engine designed for embedded devices, autonomous systems, and mobile agents. 𝗪𝗵𝘆 𝗤𝗱𝗿𝗮𝗻𝘁 𝗘𝗱𝗴𝗲? As

⏳ Early bird pricing ends tomorrow for Vector Space Day in Berlin. Hear from engineers pushing the limits of vector search, hybrid retrieval, and agentic systems, and get hands-on with real-world architectures. 🎟️ Save 25% before July 31: lu.ma/p7w9uqtz

🌟 𝟮𝟱,𝟬𝟬𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝗦𝘁𝗮𝗿𝘀! 🌟 We just hit this huge milestone! From a small project to powering vector search at scale for teams around the world…this is all thanks to YOU. 💜 To every contributor, issue opener, stargazer, and believer in open-source AI

SpoonOS now integrates Qdrant the blazing-fast, open-source vector database! With Qdrant powering semantic search and long-term memory, SpoonOS devs can build smarter AI agents, stronger RAG pipelines, and real-time contextual apps — all on Web3 infra. The sentient OS

Can you deliver real-time intelligence in crypto, one of the fastest and noisiest markets in the world? 𝗣𝗼𝗿𝘁𝗳𝗼𝗹𝗶𝗼𝗠𝗶𝗻𝗱 𝗰𝗮𝗻. 🚀 This Web3-native AI research copilot, built with the SpoonOS 👅🥄 framework, created a dynamic curiosity engine for crypto using

In case you missed it: Qdrant Edge is now in private beta. 🚀 It’s a lightweight, embedded vector search engine built for on-device AI, no cloud required. Perfect for: 🤖 Robotics 📱 Mobile apps 🛒 POS systems 🌐 IoT devices If you’re building AI at the edge, we’d love to hear

🚀 Improving RAG Accuracy with Hierarchical Reranking Merging internal and external retrieval in a single pass often lets noise from one source weaken the other, lowering relevance and increasing hallucinations. In his latest blog, ManthaPavanKumar explains a two-stage reranking

📢 Now available: August pricing for Vector Space Day! You will hear talks from great teams at LlamaIndex 🦙, Jina AI, Baseten, Arize AI, Delivery Hero, deepset, Qdrant, of course, and many more upcoming! 🚀 Get 10% off your ticket before August 31st:

I often forget that I set up Roo Code code search. I'll sometimes see in my LLM responses that it performed a query against my locally-hosted Qdrant vector DB, and that reminds me it's there. This is how software *should* work, transparently! 🦘

💡 Scaling GitHub Issue Management with a Multi-Agent RAG Pipeline Benito Martin built a full-stack system for automated search, classification, and enrichment of GitHub issues. Architecture: 1️⃣ Ingestion → Pulls issues + comments from the GitHub API into PostgreSQL. 2️⃣ Hybrid

🚨 Ending Soon: Call for Speakers 🚨 Want to join us at Vector Space Day 2025 in Berlin in September? We have a slot or two remaining for standout community talks. If you’re working on scalable RAG, agentic AI, real-time retrieval, you’ll want to submit. 🚀 Submit by Friday,

Do you prefer your vectors faster, cheaper, or smarter? 👨‍🔬 Because when it comes to large-scale vector search, you can’t have all three. Quantization is where that trade-off begins. 📊 How you choose to quantize your vectors affects everything: ➡️ How similarity is calculated

🚀 The line up for Vector Space Day is getting better and better. Don’t miss out: lu.ma/p7w9uqtz Amazon Web Services, Microsoft, Vultr, Baseten, Jina AI, deepset, LlamaIndex 🦙, TwelveLabs (twelvelabs.io), n8n.io, Neo4j, Mistral AI, DataTalksClub, and MLOps Community.

🚀 One API. Full-stack multimodal search. If you missed Kacper Łukawski live, the full webinar recording is now available. ▶️ A Guide to Cloud Inference: youtube.com/watch?v=A8BBdG…

After seeing 3 questions full of confusion (me all the time) on Qdrant's Discord, I finally got a hint🫡 Threw together a guide on using decay functions for #relevance score boosting, aka fresher by time/closer by geo/etc 🪄medium.com/qdrant/untangl…

🎙 It's 𝐥𝐢𝐯𝐞! "In information retrieval, we tend to be really bad about coming up with names for things." So we’re just calling this episode "that good one." ➡️ youtu.be/oiX7F1qi62Y

🎙️ Ava: Your Multimodal AI Companion From Miguel Otero Pedrido and The Neural Maze: a hands-on, open-source course on building an AI that sees, hears, remembers, and talks with you on WhatsApp. 🚀 Learn LangGraph, Groq Inc, Together AI, Qdrant, Whisper STT, ElevenLabs TTS,

🚀 Spin up Qdrant in under 10 minutes. With Docker or Python you can go from zero to a production-ready vector database: • High-throughput similarity search • Structured payload filters • A working city-similarity finder Sustaining ~24 ms search latency across millions of