Top all-time · #1296
Technical Articles on Qdrant
Company blog · qdrant.tech/articlesaidataprogramming
Technical Articles on Qdrant is the company blog at qdrant.tech, writing about ai, data and programming. Since 2021, 55 different Hacker News readers have linked it 131 times, most often “Qdrant – Vector Search Engine”. It is still writing: the last post was on 2026-10-12, and you can follow it by feed.
Rarely recommended · 3 of 40 sampled comments recommend it?
Why HN links it
HN readers link Qdrant's articles, benchmarks and docs in discussions of vector databases and vector search, citing the benchmarks and an article on filtrable HNSW. Many links are job postings.
Summarised by Claude from a sample of 40 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Qdrant is an Open-Source Vector Search Engine written in Rust. It provides fast and scalable vector similarity search service with convenient API.
Most-linked posts?
- Qdrant – Vector Search Engine14 people · 14 mentions · first linked 2022-01-14
- Which vector search engine is the fastest?9 people · 15 mentions · first linked 2022-08-23
- /3 people · 15 mentions · first linked 2021-12-15
- /articles/dedicated-service/3 people · 3 mentions · first linked 2023-12-12
- RAG is dead Long live RAG3 people · 3 mentions · first linked 2024-02-28
- Are You Vendor Locked?3 people · 3 mentions · first linked 2024-05-06
- Metric Learning for Anomaly Detection2 people · 3 mentions · first linked 2022-05-04
- Triplet Loss has additional tricks that help it work better2 people · 3 mentions · first linked 2022-04-14
- On Hybrid Search with Qdrant2 people · 2 mentions · first linked 2023-03-07
- /documentation/quick-start/2 people · 2 mentions · first linked 2023-06-21
What Hacker News says?
btw qdrant did some interesting benchmarks against redis and elasticsearch here https://qdrant.tech/benchmarks/
Comment linking /benchmarks/
on “From where I left”Submitted We were not accepted into Google Summer of Code. So, we started our own as a story · 146 points
HN discussionQdrant | Open Source Vector DB | Remote | Full-time | https://qdrant.tech SRE, Engineering Manager, DevOps, Cloud Engineer, Support Engineer, Rust Core Engineer (contribute first approach) All positions: https://qdrant.join.com
Comment linking /
on “Ask HN: Who is hiring? (February 2024)”Submitted Qdrant, the Vector Search Database, raised $28M in a Series A round as a story · 131 points
HN discussionQdrant | Rust Engineers, DevOps, Cloud Backend, SRE, ML Engineers, Sales, Marketing | Remote/Berlin/US | full-time | https://qdrant.tech Qdrant is an open-source massive-scale Vector Database. https://github.com/qdrant/qdrant All Positions: https://qdrant.join.com
Comment linking /
on “Ask HN: Who is hiring? (January 2024)”Submitted Immutable Data Structures in Qdrant as a story · 46 points
HN discussionWe are developing open-source vector search technology. https://github.com/qdrant/qdrant It is a neural search engine with extended filtering support that implements a custom modification of the HNSW algorithm for Approximate Nearest Neighbour search. It allows applying search filters, including geolocation, without compromising on results. Developed entirely in Rust language. You can find some demos and documentati…
Comment linking /
on “Find anything fast with Google's vector search technology”Submitted Serverless Semantic Search, Free tier only as a story · 23 points
HN discussionQdrant | https://qdrant.tech | Full-time | Remote (global) | Rust Engineers Qdrant is an advanced Vector Search Engine. It is open-source and written in Rust. Check it out on GitHub. https://github.com/qdrant/qdrant We develop both the project itself as well as the AI solutions built on its basis. We are looking for Rust developers to support us with the development of new engine features and to take care of perform…
Comment linking /
on “Ask HN: Who is hiring? (November 2022)”Submitted Vector Similarity Beyond Search as a story · 22 points
HN discussionHardware is a vendor lock-in. I can’t imagine sinking millions into a massive project and getting stuck with a huge bill. Then, to migrate away you need all sorts of devops folks and the ability to deal with incompatibilities. Uncertainty about pricing and the hardware bottleneck is a real problem for our users. I just raised this point in our blog today. https://qdrant.tech/blog/are-you-vendor-locked/
Comment linking /blog/are-you-vendor-locked/
on “Alternative clouds are booming as companies seek cheaper access to GPUs”Submitted On a roll: Qdrant brings sparse vectors, discovery search and custom sharding as a story · 16 points
HN discussionI understand the sentiment. We are starting to open source some tools, mostly around embedding model evaluation (i.e. https://github.com/voyage-ai/voyage-evaluation-public ), with other stuff coming up. FWIW, there are other deployment options besides the API as well: AWS ( https://docs.voyageai.com/docs/aws-marketplace-model-package ), Azure ( https://docs.voyageai.com/docs/azure-marketplace-managed-app... ), Snowf…
Comment linking /documentation/embeddings/voyage/
on “All-in-one embedding model for interleaved text, images, and screenshots”Submitted BM42 – a new baseline for hybrid search as a story · 14 points
HN discussionHas anyone had experience with qdrant ( https://qdrant.tech/ ) as a vector store data and can speak to how txtai compares?
Comment linking /
on “Txtai: Open-source vector search and RAG for minimalists”Submitted Which vector search engine is the fastest? as a story · 13 points
HN discussionhttps://qdrant.tech/documentation/concepts/payload/ Perhaps it’s not that different than other solutions have but my impression was their payload system was more flexible and extensible than competing options, especially with the speed that Qdrant delivers, so for example pg_vector can leverage all of postgres capabilities but I don’t believe it can compete with Qdrant on vector specific problems.
Comment linking /documentation/concepts/payload/
on “Show HN: R2R – Open-source framework for production-grade RAG”Submitted Qdrant Scalar Quantization: up to 2x faster, 4x less memory as a story · 12 points
HN discussionThanks for writing this up! > Filtering with vector search may be harder than you expect. I've only ever used it for a small proof of concept, but Qdrant is great at categorical filtering with HNSW. https://qdrant.tech/articles/filtrable-hnsw/
Comment linking /articles/filtrable-hnsw/
on “Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed”Submitted Semantic Search-as-You-Type as a story · 11 points
HN discussionI'm currently looking to implement RAG locally, using QDrant [1] for instance. Just playing around for now, but it makes sense to have a runnable example for our users too :) [2]. [1]. https://qdrant.tech/ [2] https://aimeetingbot.com
Comment linking /
on “Ask HN: Has Anyone Trained a personal LLM using their personal notes?”Submitted New Insights on Vector Database Performance: Updated Qdrant Benchmarks as a story · 10 points
HN discussionHere is a video on how it can be used with a vector search database like Qdrant to retrieve real-time data. https://youtu.be/fQUGuHEYeog HowTo: https://qdrant.tech/articles/chatgpt-plugin/ Disclaimer: I'm a part of Qdrant team.
Comment linking /articles/chatgpt-plugin/
on “ChatGPT Plugins”Submitted 40x Faster Vector Search with Binary Quantization as a story · 10 points
HN discussionThat's a game-changer! It seems like factuality issues with ChatGPT might be fixed. We wrote a blog post on how to get started with a custom plugin: https://qdrant.tech/articles/chatgpt-plugin/
Comment linking /articles/chatgpt-plugin/
on “ChatGPT Plugins”Submitted Product Quantization in Vector Search as a story · 10 points
HN discussionWith regards to competitors picking similar things up, we've this article explaining why a dedicated vector search service is a good idea: https://qdrant.tech/articles/dedicated-service/
Comment linking /articles/dedicated-service/
on “Qdrant, the Vector Search Database, raised $28M in a Series A round”Submitted Beating ColBERT: Experiment shows better retrieval with output token embeddings as a story · 9 points
HN discussion> For example, it can automatically map ‘frontend engineer’ to ‘web developer’ Small revolution indeed. Ref: https://qdrant.tech/use-cases/
Comment linking /use-cases/
on “Qdrant, the Vector Search Database, raised $28M in a Series A round”Submitted HNSW indexing for vector dbs is now GPU vendor agnostic as a story · 8 points
HN discussion
