Qdrant Vector Search in Rust | Arnaud Gourlay @ Rust Meetup Linz

Qdrant is a vector database and vector similarity search engine. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and more.
In this session, Arnaud Gourlay explains how Qdrant is used and peeks under the hood to explain what is inside. In particular - to see why Rust is a good fit for the job.
This presentation by Arnaud Gourlay was recorded at the Rust Linz meetup on March 2nd, 2023 (www.meetup.com...)

[@hritikakolkar]

I actually learned rust because of qdrant, but now I think I should also learn Go

[@gabrielsegatti8017]

Learned lots of things, great presentation!

[@peek2much3]

Awesome and well explained even for someone like me who’s coming from DevOps and are truly interested in learning this truly cutting edge tech. What resources do you recommend as I want to remain vendor agnostic with something like qdrant that is OSS? Thanks

[@zeroows]

Thank you for the excellent presentation. In most use cases, the new std::Mutex is faster than `parking_lot`.

[@chandra_ramdhan]

Awesome

[@SunilSamson]

Why isn't there an option to query the collection?

[@meetthereqs]

whats is the benefit of using qdrant vector search versus a firebase solution?

[@zyansheep]

25:42 I wonder why they call it vertical and horizontal simd, why not just call it what it is: map and reduce?

[@ArnaudQdrant]

Good point, I have not thought about it. I would guess that the SIMD terminology predates the democratization of the terms map and reduce. In any case I assume people would understand you when as well.