What problem does it solve? Building production RAG and semantic search systems requires a vector database that handles fast nearest neighbor search, metadata filtering, and horizontal scaling without sacrificing latency or data control. ## Core Features & Use Cases - Vector Search with Filtering: Perform nearest neighbor search combined with payload filters, geo queries, and full-text conditions using the qdrant-client Python library. - Hybrid and Multi-Vector Search: Combine dense and sparse vectors with Reciprocal Rank Fusion, and store multiple named vectors per point. - Production Scaling: Configure HNSW parameters, scalar/product/binary quantization, sharding, replication, and snapshots for large-scale deployments. - Use Case: Build a knowledge base RAG pipeline by encoding documents with sentence-transformers, upserting them into a Qdrant collection, and retrieving top-k context chunks filtered by source metadata. ## Quick Start Use the qdrant skill to create a collection, upsert embedded documents, and run a filtered similarity search against a local Qdrant instance.
