andre-z
Re:ANN v3: 200ms p99 query latency over 100B vectors
on Monday January 26, 2026 @03:04AM (#46763011)
What do I say? Happy to talk about "fakes". Here is my calendar. Feel free to book a slot. https://qdrant.to/andre-z
Re:Ask HN: Scaling local FAISS and LLM RAG system (356k chunks)archite...
on Tuesday November 25, 2025 @07:56AM (#46045345)
FAISS is not suitable for production. The dedicated vector search solutions solve all the issues you mentioned: you just store the metadata along with vectors in JSON format. At least, with Qdrant, it works like this: https://qdrant.tech/documentation/concepts/payload/
Re:
on Friday May 16, 2025 @11:01AM (#44006339)
miniCOIL is a contextualized per-word embedding model. It generates extremely small embeddings (8dim or even 4dim) while still preserving the word's context for each word in a sentence.
GitHub https://github.com/qdrant/miniCOIL HuggingFace https://huggingface.co/Qdrant/minicoil-v1
Re:Meilisearch – search engine API bringing AI-powered hybrid search
on Tuesday April 15, 2025 @04:51AM (#43690473)
"Slowness can arise from a misconfigured index or if filterable attributes aren't listed." ;)
Re:Ask HN: Alternatives to Vector DB?
on Tuesday March 18, 2025 @01:41PM (#43402306)
Qdrant runs on Linux/Mac/Windows and on x86/ARM processors
Re:Beating ColBERT: Experiment shows better retrieval with output toke...
on Tuesday August 20, 2024 @07:57AM (#41299169)
Any dense embedding model can become a late interaction model.
Optimize LLM resource usage with Semantic Cache [video]
Hardware is the new vendor lock-in
Re:Show HN: Chromem-go – Embeddable vector database for Go
on Friday April 05, 2024 @07:44AM (#39941193)
Qdrant lib project https://github.com/tyrchen/qdrant-lib, Qdrant SDK has also support for local mode, which means embeddable https://github.com/qdrant/qdrant-client
Or just use FAISS https://github.com/facebookresearch/faiss
The only other Repository is a fork of Qdrant.
Databases? Just use files instead
Re:Show HN: A fast HNSW implementation in Rust
on Friday March 15, 2024 @04:40AM (#39713390)
I can answer how it would be in Qdrant if interested. The index will take around 70GB RAM. New vectors are first placed in a non-indexed segment and are immediately available for search while the index is being built. The vectors and the index can be offloaded to disk. Search will take some milliseconds.
Re:Ask HN: Who is hiring? (March 2024)
on Thursday March 14, 2024 @11:43AM (#39705468)
Qdrant | Open Source Vector DB | Full-time | Remote/Berlin | https://qdrant.com
Hiring SRE, DevOps, Cloud Engineers, Rust Developers, and more.
RAG is dead Long live RAG
Re:Show HN: R2R – Open-source framework for production-grade RAG
on Monday February 26, 2024 @05:11PM (#39517339)
Thanks for your trust. :)
Re:We were not accepted into Google Summer of Code. So, we started our...
on Sunday February 25, 2024 @02:35AM (#39498483)
Yes. This makes sense. There is no criticism of Google at all. We just want to continue supporting contributors.
Re:We were not accepted into Google Summer of Code. So, we started our...
on Saturday February 24, 2024 @05:05PM (#39495545)
Sorry, my bad. Was partially copied from Linkedin, where I post most of the content. No idea behind. The emojis are from here https://qdrant.to/gsoc24
Re:We were not accepted into Google Summer of Code. So, we started our...
on Saturday February 24, 2024 @05:00PM (#39495502)
Did you look a bit deeper? Qdrant is written in Rust from scratch. The project is over three years old and started long before the "gold rush." :)
Run it wherever you want, in your data center, locally, with no limitations.
https://github.com/qdrant/qdrant-helm
Re:We were not accepted into Google Summer of Code. So, we started our...
on Saturday February 24, 2024 @04:55PM (#39495459)
This is not a reason. We participated successfully last year and even hired one of the guys afterward.
We were not accepted into Google Summer of Code. So, we started our own
Re:Ask HN: Who is hiring? (February 2024)
on Thursday February 01, 2024 @01:00PM (#39219015)
Qdrant | 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://cloud.qdrant.io
Re:Building a scalable and intelligent Transaction Categorization engine
on Friday January 26, 2024 @05:11AM (#39140857)
Welcome to add on our Discord to #built with qdrant channel.
Re:Qdrant, the Vector Search Database, raised $28M in a Series A round
on Tuesday January 23, 2024 @10:29AM (#39104671)
The open-source benchmarks show different results. Feel free to make a PR to improve. ;) https://qdrant.tech/benchmarks/
Re:Qdrant, the Vector Search Database, raised $28M in a Series A round
on Tuesday January 23, 2024 @08:45AM (#39103196)
Thanks. We will reveal our hiring strategy in more details soon.
Re:Qdrant, the Vector Search Database, raised $28M in a Series A round
on Tuesday January 23, 2024 @08:28AM (#39103025)
These are the major ones, correct.
Re:Qdrant, the Vector Search Database, raised $28M in a Series A round
on Tuesday January 23, 2024 @07:12AM (#39102364)
Does this count? https://testimonial.to/qdrant/all
Re:Qdrant, the Vector Search Database, raised $28M in a Series A round
on Tuesday January 23, 2024 @06:46AM (#39102159)
You should use whatever works best for you unless you face some limitations.
The issue is that vector databases are not databases but search engines. It is ACID vs BASE.
A few thoughts on this https://qdrant.tech/articles/dedicated-service/
Re:Qdrant, the Vector Search Database, raised $28M in a Series A round
on Tuesday January 23, 2024 @06:30AM (#39102036)
Re:Vector Databases: A Technical Primer [pdf]
on Saturday January 13, 2024 @03:19AM (#38978157)
Qdrant as a library project
https://github.com/tyrchen/qdrant-lib