Qdrant

Vector similarity search is provided by Qdrant, an open-source search engine written in Rust.

qdrant.tech
Qdrant homepage screenshot

About Qdrant

Qdrant is a vector search engine written in Rust for AI retrieval. It stores vectors with JSON metadata and supports filtering by nested fields, text, geo, and vector presence, plus hybrid queries that combine dense and sparse vectors.

It provides real-time indexing without rebuilding the whole index, scalar, binary and asymmetric quantization options, and reranking with score boosting, ColBERT and MMR. Deployment options listed are managed cloud on AWS, GCP or Azure, hybrid with own Kubernetes, private air-gapped setups, and edge, which is in beta.

Key features

  • JSON metadata storage with nested, text and geo filtering
  • Hybrid search combining dense and sparse vectors
  • Support for BM25, SPLADE++ and miniCOIL retrieval
  • Multiple vectors per stored object
  • Filtering applied during HNSW traversal
  • Reranking with score boosting, ColBERT and MMR
Best for: Developers building AI search and retrieval that use vector, keyword and filtered queries.
Good for
  • Built in Rust with SIMD and custom Gridstore storage engine
  • Runs on managed cloud, hybrid Kubernetes, private air-gapped and edge environments
  • Combines dense, sparse and multivector search with filtering and reranking
Watch out for
  • Edge deployment is listed as beta

Qdrant at a glance

Type
Online tool
Pricing
Not confirmed. Check the site
Platforms
Web
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

Qdrant alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 12 alternatives

Popular in APIs & Databases

Well-known listings from the same topic.

All 93

Qdrant FAQ

Where can Qdrant be deployed?
It lists Qdrant Cloud on AWS, GCP or Azure, Hybrid Cloud with your own Kubernetes, Private Cloud for air-gapped setups, and Qdrant Edge in beta.
What methods does hybrid search support?
Dense or sparse vectors, including BM25, SPLADE++ and miniCOIL in one query.
How is filtering handled?
Filters are applied during HNSW traversal, without separate pre- or post-filtering.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing