🚗 𝐖𝐡𝐲 𝐭𝐫𝐚𝐝𝐢𝐭𝐢𝐨𝐧𝐚𝐥 𝐬𝐮𝐩𝐩𝐥𝐲 𝐜𝐡𝐚𝐢𝐧 𝐚𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐚𝐫𝐞𝐧’𝐭 𝐞𝐧𝐨𝐮𝐠𝐡, 𝐚𝐧𝐝 𝐡𝐨𝐰 𝐚𝐠𝐞𝐧𝐭𝐢𝐜 𝐀𝐈 𝐜𝐡𝐚𝐧𝐠𝐞𝐬 𝐭𝐡𝐞 𝐠𝐚𝐦𝐞 In complex industries like automotive manufacturing, visibility across parts, suppliers, and risk factors is

i guess market @yandex go uses @qdrant_engine ? https://t.co/sAjnHERCQT

💡 Supercharge your .NET apps with local RAG! Combine Qdrant + Semantic Kernel + Ollama for context-aware, reference-backed answers in legal & knowledge-heavy domains. Read more: https://t.co/xKAIQq8kfJ #dotnet #semantickernel #ollama #llm

Building a Biomedical GraphRAG: When Knowledge Graphs Meet Vector Search When Benito Martin started ingesting PubMed papers into a vector database, he thought he had it figured out. Semantic search would handle everything — just throw abstracts at Qdrant, retrieve similar

𝐊𝐲𝐥𝐢𝐞 - 𝐚 𝐌𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 𝐖𝐡𝐚𝐭𝐬𝐀𝐩𝐩 𝐀𝐈 𝐀𝐠𝐞𝐧𝐭 We recently came across this project shared by Jonathan Mukhobe Sr. on LinkedIn and wanted to highlight it for the community. Kylie is a fully functional WhatsApp AI agent built with a practical, end-to-end

🧬 𝐒𝐞𝐦𝐚𝐧𝐭𝐢𝐜 𝐬𝐞𝐚𝐫𝐜𝐡 𝐚𝐥𝐨𝐧𝐞 𝐢𝐬𝐧’𝐭 𝐞𝐧𝐨𝐮𝐠𝐡 𝐟𝐨𝐫 𝐝𝐞𝐞𝐩 𝐬𝐜𝐢𝐞𝐧𝐭𝐢𝐟𝐢𝐜 𝐝𝐢𝐬𝐜𝐨𝐯𝐞𝐫𝐲! When you ask real research questions - like “who collaborates with whom on CRISPR-related work?” - pure vector search retrieves relevant text, but it can’t

Wrapped up two exciting builds today: 1. AI RAG Agent: an PDF knowledge retriever powered by FastAPI, Inngest, Qdrant & OpenRouter. This one showed me premium Shege😭😭 2. Safari Zoo Web App : A clean, animated React + Tailwind experience with AOS integration.

been hands-on with Qdrant for the past 2 days — digging into how it handles high-dimensional vector search at scale. under the hood, it’s a beast — built in Rust, uses HNSW for ANN, supports payload filtering, quantization, and on-disk vector storage without compromising latency

I successfully ran a Claude Code instance for 24-hours without any action from me. I gave it long(qdrant) and short(sqlite) -term memory, and access to a browser. The run generated: - 500 projects - ~450k LOC - 20 long-term records - 1500+ screenshots https://t.co/2LmXnQpUJC

Stop paying for $3,000 "RAG" bootcamps. Qdrant just put a full, production-grade vector search course on YouTube. For free. This isn't a demo. It's a 7-day sprint where the final project is to ship a complete, production-ready documentation search engine. The full curriculum

Setting up @qdrant_engine through @Docker was so clean, perfection 🤌

Community Win Spotlight: Best Use of Qdrant at STATION F Hackathon! Big congratulations to the LumiereAI team (Achraf Ez, Imad Ez, and Safouane Chergui) for an outstanding double win at the Pioneers AI Lab Hackathon hosted at STATION F, the largest hackathon ever organized at

Thanks for all the love for the new Long-term Memory video! The code is now open-source and you can star, fork and play with it. (repo in comments) It is a minimalist feature-complete implementation of the Mem0 memory system using DSPy and Qdrant. It already does user-scoped,

choosing the right ann index for vector search is always a trade-off. hsnw gives you excellent recall and speed for high-dimensional data, but qdrant's disk usage can be substantial. faiss ivfpq is more memory-efficient but can sacrifice query latency for very large datasets.

ベクトルデータベースの年表 ちなみに私の推しはQdrantです

𝐄𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐧𝐠 𝐑𝐀𝐆 𝐏𝐢𝐩𝐞𝐥𝐢𝐧𝐞𝐬 𝐭𝐡𝐞 𝐑𝐢𝐠𝐡𝐭 𝐖𝐚𝐲 - 𝐄𝐧𝐝 𝐭𝐨 𝐄𝐧𝐝 One of our Qdrant Stars ⭐, Tarun R Jain, shared an excellent deep dive on evaluating, tracing, and monitoring RAG workflows. This walkthrough demonstrates how to build a

You see @korrektly mentioned? My new product (WIP) 👀 Coming to @coolifyio docs very soon! I built this product in less than a week using laravel, pgvector, OpenAI embeddings, tsvector, etc. The next step is Qdrant and Sparse embeddings for even faster hybrid search.

#Day12 | Agentic & GenAI: Nebula ❇️Topic: Two phases of RAG: 1. Vector DB setup (qdrant) 2. About Lang chain and there setup to load pdf files @Hiteshdotcom @piyushgarg_dev @ChaiCodeHQ #AI #ML #ChatGPT

Day 29 of building in public (blog platform) Did R&D on different types of communication between microservices (for my case HTTP works well). Created a new fastAPI service, created a qdrant cloud cluster and connected it to service