Qdrant
A fast open-source vector database with rich filtering, built for production retrieval.
Qdrant is a purpose-built vector database written in Rust. It is fast, scales well, and its standout feature is filtered search: combining similarity with structured metadata conditions efficiently.
It runs self-hosted or as Qdrant Cloud, so a project can start on its own infrastructure and move to managed without changing the data model.
Where it fits
A strong pick when retrieval needs to combine similarity with metadata filtering, or has outgrown an in-database extension.
Where it does not fit
An extra system to operate that you may not need when data sits in Postgres and the workload is modest.
Alternatives to Qdrant
The closest options on the map, and where each fits instead.
-
Weaviate Dedicated vector database
A fit when you want hybrid search and the option to let the database handle vectorisation for you.
-
Milvus Dedicated vector database
A fit when vector search must operate at very large scale, into the billions of vectors.
-
pgvector Embedded vector search
The right call when your data already lives in Postgres and the vector workload is moderate: retrieval without a second database.
Unlike Qdrant No hosted API
-
Chroma Embedded vector database
The easiest on-ramp for a RAG prototype, and a fine production store for small to medium workloads.
Unlike Qdrant Maturity: growing
Pairs with
Commonly used alongside it.
