AI product
Qdrant is an open-source vector search engine written in Rust for storing vectors with JSON payloads and querying them through an API. It performs vector similarity search using HNSW traversal, applies metadata filters during retrieval, and supports dense, sparse, hybrid, and multivector search, along with reranking methods such as ColBERT and maximum marginal relevance. Qdrant can run on-premises, in hybrid or private deployments, at the edge through Qdrant Edge, or as the fully managed Qdrant Cloud service. The project is used for AI retrieval and supports synchronization between local or edge deployments and cloud-based memory.
1 use taken from transcripts — each links to the moment in the video.
A vector search engine used to embed directly into an application, store embeddings with payloads, and query them offline in sub-millisecond time. The talk also describes its cloud equivalent and synchronization capabilities.
1 in the library.