qdrant-vector-search

SKILL.md

Rust-powered vector database for production RAG with hybrid search and distributed scaling.

Supports dense, sparse, and multi-vector storage per point with four distance metrics (COSINE, EUCLID, DOT, MANHATTAN) and HNSW indexing for fast nearest-neighbor search

Rich filtering during search across any payload field, with optional payload indexing for performance and support for complex boolean queries

Quantization options (scalar, product, binary) and on-disk storage for memory efficiency in large-scale deployments

Integrates with sentence-transformers, LangChain, and LlamaIndex for RAG pipelines; includes batch search, REST and gRPC APIs, and distributed deployment with sharding and replication

Qdrant - Vector Similarity Search Engine

High-performance vector database written in Rust for production RAG and semantic search.

When to use Qdrant

Use Qdrant when:

Building production RAG systems requiring low latency

Need hybrid search (vectors + metadata filtering)

Require horizontal scaling with sharding/replication

Want on-premise deployment with full data control

Need multi-vector storage per record (dense + sparse)

Building real-time recommendation systems