Back to directory

SeekStorm

A Rust search engine offering sub-millisecond native vector and lexical (BM25) search, usable as an in-process library or a multi-tenancy server, with a query planner that fuses both search modes.

SeekStorm

SeekStorm is a Rust search library and multi-tenancy server combining two first-class index architectures: an inverted index for lexical relevance and an ANN index for vector similarity. A query planner lets a query choose pure lexical, pure vector, or hybrid search, fusing results with Reciprocal Rank Fusion while shielding the caller from the underlying complexity.

It supports faceting, geo-proximity search, result sorting, sharded indexes for multi-core scaling, an n-gram index for fast phrase search, and typo-tolerant query autocompletion derived from indexed documents. REST clients are provided for Rust, Python, TypeScript, C# and Java, and an adapter can redirect an existing Algolia InstantSearch.js frontend to a SeekStorm backend without a UI rewrite.

Development began in 2015, has been in production since 2020, and the project was rewritten in Rust and open-sourced under the Apache License 2.0.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.