kanungle

"#pgvector doesn't scale" is what most vector database companies say to postgres users. But there's more to it... #Postgres is great, and there are plenty of reasons to use it. However, through a careful community analysis of 110+ posts, we've distilled down to 6 conditions that must hold true for pgvector to make sense for your search needs. Read more: qdrant.tech/blog/pgvector-…

⏳ Just a few days left! 🇩🇪 Join us in Munich for “Unconference: Context Engineering with Open-Source” - an evening of open discussions on building better context layers for AI systems. Instead of traditional talks, we’ll dive into interactive conversations around: • Retrieval and vector search • Memory systems for AI agents • Designing robust context layers • Building production-grade AI with open-source tools Explore how tools like @deepset_ai, @qdrant_engine, and @cognee_ help engineers design better context pipelines for real-world AI applications. 📍 smartvillage Bogenhausen, Munich 🔗 luma.com/xg649r8v See you there! 👋

Tomorrow at @NVIDIAGTC I'm at the @Vultr stage to talk about edge to cloud video anomaly detection with @qdrant_engine Edge, @twelve_labs Marengo 3.0, and @nvidia Metropolis. Traditional video classifiers need labeled examples of every anomaly you want to catch. That breaks in the real world. So I took a different approach..

@SouptikSen08 Could you tell me more about the issue you ran into?

Added Pinecone for embeddings today. Originally tried Qdrant but ran into a weird region URL issue — couldn’t even create a collection from the official UI. After enough debugging, just switched. Pinecone worked immediately. Vector search pipeline running now.

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-…

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

QDRANT NEWS - FEBRUARY 2026 🚀 PRODUCT • Qdrant 1.17 Release Blog -> Full release notes with all features qdrant.tech/blog/qdrant-1.… • Relevance Feedback Article -> Methodology and experiments behind the new query type qdrant.tech/articles/relev… • Relevance Feedback Tutorial -> Hands-on implementation guide qdrant.tech/documentation/… • Qdrant Cloud Inference -> Free cloud-hosted embedding models qdrant.tech/cloud-inferenc… 💥 CONTENT • Hallucination Mitigation in RAG using LLM Steering youtube.com/watch?v=UqyOaO… • Modernizing Legacy Search: Elastic vs Qdrant Demo youtube.com/watch?v=-IHb9D… • Smarter Chunking Methods with POMA-AI youtube.com/watch?v=u-AaCm… • Agentic GraphRAG: PubMed Navigator youtube.com/watch?v=3NWTi9… • Interactive SPLADE Visualizer -> Browser-based tool to explore sparse lexical expansion nathanleroy.dev/spladeviz/ 👨‍🚀 COMMUNITY • Sketch & Search Hackathon Winners qdrant.tech/blog/sketch-n-… • Getting Started with Qdrant -> Bi-weekly onboarding webinar tinyurl.com/qdrant-onboard… 📅 EVENTS • Migrating to Qdrant Edge for On-Disk Vector Storage in Rust (Discord) discord.gg/HSfFDeW3?event… • MLOps: Coding Agents Conference (SF) luma.com/codingagents • Context Engineering Meetup (Amsterdam) luma.com/dtswysbb • NVIDIA GTC (Vultr Booth 1631) - SF discover.vultr.com/nvidia-gtc-2026

Relevance feedback, propagated directly into similarity scoring, Qdrant 1.17 New Relevance Feedback Query interface: + for all data modalities + for a whole vector space (not rescoring a subset) + cheap to run, feedback on 3-5 results + customizable + works with fuzzy signals

Qdrant 1.17 ships the first-ever vector index-native Relevance Feedback implementation. Relevance feedback distills signals from current search results into the next retrieval iteration, surfacing better results over time. Most approaches only rerank a subset of retrieved results. Ours operates on the entire vector space. Fully data type agnostic (texts, images, code, molecules, you name it) since it works directly on embeddings. Cheap to run with minimal time and resources needed. Customizable to your dataset, retriever, and feedback model

Live on Discord now! discord.gg/qdrant

We have a really cool hashtag#VectorSpaceTalk coming up next week with POMA AI Founder Dr. Alex Kihm will be joining us to talk chunking strategies, especially with novel hierarchical chunking approaches. While chunking is not core to Qdrant usage, it's something relevant to many devs using Qdrant in their workflows. Dr. Kihm has prepared a colab notebook, some benchmarks, and great discussion topics. Be sure to join us at the link below. streamyard.com/watch/nnX8QFXS…

January 2026 recap for @qdrant_engine below. Stay ahead of the curve and subscribe for our monthly updates: qdrant.tech/subscribe. 1/ Qdrant Edge (Public Beta) is live—a lightweight, embedded vector search engine for devices like robots and kiosks that works without internet . qdrant.tech/documentation/…. 2/ Inference is now flexible for everyone. Free tier clusters can use external embedding models with OpenRouter now an official provider . qdrant.tech/cloud-inferenc…. 3/ Scale with control using new metadata labels to identify cost centers, and Hybrid Cloud control plane labels for Kubernetes compliance. cloud.qdrant.io 4/ Efficiency first. Kumar Shivendu’s walkthrough on Tiered Multi-tenancy shows how to isolate large tenants while co-locating small ones . youtube.com/watch?v=72Ux-L…. 5/ Build multimodal systems with Pavan Kumar’s guide on vision and text retrieval using Qwen-VL and Qdrant Multivector Search. @manthapavankumar11/end-to-end-multimodal-retrieval-with-qwen-embeddings-and-qdrant-88a6c04723c4" target="_blank" rel="nofollow noopener">medium.com/@manthapavanku… 6/ AI agent optimization with skill.md and REPL-first approaches help agents discover schemas and use APIs perfectly. qdrant.tech/articles/skill… 7/ OSS Hero: TY0909’s PR #7887 adds an enable_hnsw option to slash indexing time. github.com/qdrant/qdrant/… 8/ Prove your expertise with the new Qdrant Essentials Certification . qdrant.tech/blog/qdrant-ce…. 9/ New to vector search? Join our Feb 5th Getting Started webinar for a live chat and Q&A. tinyurl.com/qdrant-onboard… 10/ Welcome Nathan LeRoy as our new Developer Advocate! We also bid a fond farewell to Kacper Lukawski after 4 years of incredible work. Nathan: linkedin.com/in/nathanjlero… Kacper: linkedin.com/in/kacperlukaw… Join the mission. We’re hiring 20+ roles in Engineering, DevRel, Sales, and more . join.com/companies/qdra….

Oh wow, this is literally what I built with @Haystack_AI and @qdrant_engine 😄 A movie recommendation agent that understands intent and creates the right search queries + metadata

𝐐𝐝𝐫𝐚𝐧𝐭 𝐌𝐨𝐧𝐭𝐡𝐥𝐲 𝐎𝐟𝐟𝐢𝐜𝐞 𝐇𝐨𝐮𝐫𝐬 𝐢𝐬 𝐛𝐚𝐜𝐤 👨🏼‍🚀 📅 15th January 2026 🕔 17:00 CEST / 08:00 PDT 📍 Qdrant Discord Join us for a casual community hang-out to share what you’re building, ask questions, and connect with the Qdrant team & fellow devs. Special Guest: @not_so_lain from @ChonkieAI What is @ChonkieAI? Chonkie is a fast, developer-friendly tool for chunking and preparing data for AI apps, especially RAG pipelines. It helps break large documents into clean, efficient chunks so they can be embedded, indexed, and retrieved more accurately with vector search engines like Qdrant. 👉 Discord event: discord.gg/5C7K79fZ?event… See you there! 👋

Multimodal Fashion Search with Qdrant + ScrapeGraphAI Francesco Zuppichini and our Head of DevRel, Neil Kanungo, just shared a great walkthrough on building a multimodal clothing search engine using ScrapeGraphAI + CLIP + Qdrant. Here’s what makes it powerful: - ScrapeGraphAI collects product data from Zalando reliably. - CLIP embeddings turn product images and text into rich semantic vectors. - Qdrant stores and searches those vectors with high performance - enabling natural-language search and image-based “find me something similar.” The result? - A fast, intelligent, production-ready way to turn raw product pages into a semantic search experience. Check out the demo and full write-up here: 🔗 scrapegraphai.com/blog/scraping-…

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 for real engineers: ➡️ Day 1 • Get on Qdrant Cloud & build your first basic vector search. ➡️ Day 2 • Master Points, Vectors, Payloads, & Chunking. • Project: Build a Semantic Movie Search. ➡️ Day 3 • Learn HNSW Indexing fundamentals. • Project: Benchmark HNSW for actual recall vs. latency. ➡️ Day 4: • Master Hybrid Search (sparse + dense) with score fusion. • Project: Build a Hybrid Search Engine that actually finds keywords. ➡️ Day 5: • Learn Vector Quantization to slash memory costs. • Master high-throughput ingestion & accuracy with rescoring. • Project: Quantization Performance Optimization. ➡️ Day 6: • Use Multivectors for advanced reranking. • Learn the Universal Query API. • Project: Build a Recommendation System. ➡️ Day 7: • Final Project: Synthesize all 6 days to ship a production-ready doc search. ➡️ Bonus: ➕  Full integration guides for LlamaIndex, Tensorlake, camelAI, Jina AI, Unstructured(dot)io, and more. This is the syllabus that separates the "demo builder" from the "production engineer." This is how you build RAG that actually scales. (I will put the playlist in the comments.) ♻️ Repost to save someone $$$ and a lot of confusion. ✔️ You can follow @techNmak, for more insights.

🚀 Exciting news! We’ve just launched the Qdrant Academy 🎓 Dive into interactive courses and level up your vector search skills with Qdrant. Ready to learn, contribute, and grow with us? Link to the announcement: qdrant.tech/blog/qdrant-ac… #Qdrant #VectorSearch #DataScience #MachineLearning

📷 We’re thrilled to announce our second Gold Sponsor – Qdrant We are happy to have @qdrant_engine contribute to the biggest #Python conference in the country. Read more in our blog: in.pycon.org/blog/2025/spon… #sponsor #python #conference #bengaluru #gold