TopK is a unified retrieval engine for hybrid search, vector search, multi-vector retrieval, keyword search (BM25) custom ranking, and managed inference in one API. Built on object storage for 10x lower cost and massive scale.
Retrieval Engine — Store and query dense vectors, sparse vectors, multi-vector embeddings, and metadata in a single collection. Filter by metadata, rank with custom expressions, and run managed inference — all in a single API.
Document Search — Ingest files, search across your private documents, and get source-backed answers. Connect your data to agents with the SDKs, CLI or MCP server.
Start with the documentation for quickstart guides, API reference, and product documentation.
- Python SDK - Python SDK for TopK API
- JavaScript SDK - Javascript SDK for TopK API with full Typescript support
- Rust SDK - Rust SDK for TopK API
- TopK CLI - CLI for TopK API
- TopK MCP - Connect TopK to MCP-compatible AI agents