LLMs & AI Infra Vector DB stable

Qdrant

High-performance vector similarity search engine

22.0K stars 150 contributors Since 2021
Website → GitHub

Vector database built in Rust for fast similarity search with filtering, payload storage, and distributed deployment.

License
Apache-2.0
Min RAM
2 GB
Min CPUs
2 cores
Scaling
horizontal
Complexity
intermediate
Performance
enterprise grade
Self-hostable
K8s native
Offline
Pricing
fully free
Docs quality
good
Vendor lock-in
none

Use cases

  • RAG retrieval backend for LLM applications
  • Product recommendation via embedding similarity
  • Semantic document search across knowledge base
  • Image similarity search for e-commerce

Anti-patterns / when NOT to use

  • Not a general-purpose database
  • No SQL support
  • Needs separate storage for non-vector data

Replaces / alternatives to

  • Pinecone
  • proprietary vector search

Technical specs

Language
Rust
API type
RESTgRPC
Protocols
HTTP
Data model
vector
Deployment
dockerbinary
SDKs
pythonjavascriptgorust

Community

GitHub stars 22.0K
Contributors 150
Commit frequency daily
Plugin ecosystem none
Backing Qdrant
Funding vc_backed

Release

Latest version
Last release
Since 2021

Best fit

Team size
solosmallmediumenterprise
Industries
saase-commercehealthcarelegaleducation

Tags

  • vector-database
  • similarity-search
  • embeddings
  • semantic-search
  • rag
  • ai-infrastructure