[ Tech stack ]
Qdrant
The open source vector database in Rust for semantic search at scale.
Qdrant is an open source vector database written in Rust: it indexes embeddings and serves low-latency similarity search, even across millions of vectors. Payload filtering combines semantics and business criteria in one query, and hybrid search (dense + sparse) sharpens relevance. Managed cloud or self-hosted, it's our choice when a RAG pipeline has to handle real load or stay on your own infrastructure.
[ Why Qdrant at Dexon ]
What this technology does well, and why we use it.
Typical usage: Production RAG, semantic search, recommendation, deduplication.
- 01
Written in Rust: performance and low memory footprint at scale.
- 02
Payload filtering: semantics + business criteria in one query.
- 03
Hybrid dense + sparse search, quantization and multi-tenancy.
- 04
Managed cloud or self-hosted (Docker, Kubernetes): sovereignty possible.
[ Complementary technologies ]
The building blocks we often mobilise alongside.
A stack rarely exists alone. Here are the technologies Dexon most often pairs with this one, through pipeline habits, usage similarity or internal mastery. Click on a building block to see its scope.
[ Reassurance ]
- 0+
- custom projects delivered
- 30
- engineers, designers, project managers
- 80 %
- from top French schools
- 24 h
- average reply time
[ They trust us ]
More than 100 French and European companies trust us
[ Press ]
They talk about us.
Nationwide coverage by BFM Business, Le Figaro, Challenges, La Tribune and CNews. An outside reading of our work and our innovations.
