Website | Benchmark | Demo | Library Docs | Server Docs | Server Readme | Roadmap | Blog | Twitter
--- **SeekStorm**: **sub-millisecond**, native **vector** & **lexical search** - **in-process library** & **multi-tenancy server**, in **Rust**. Development started in 2015, in [production](https://seekstorm.com) since 2020, Rust port in 2023, open sourced in 2024, work in progress. SeekStorm is open source licensed under the [Apache License 2.0](https://github.com/SeekStorm/SeekStorm?tab=Apache-2.0-1-ov-file#readme) Blog Posts: - [SeekStorm is now Open Source](https://seekstorm.com/blog/sneak-peek-seekstorm-rust/) - [SeekStorm gets Faceted search, Geo proximity search, Result sorting](https://seekstorm.com/blog/faceted_search-geo-proximity-search/) - [SeekStorm sharded index architecture - using a multi-core processor like a miniature data center](https://seekstorm.com/blog/SeekStorm-sharded-index-architecture/) - [N-gram index for faster phrase search: latency vs. size](https://seekstorm.com/blog/n-gram-indexing-for-faster-phrase-search/) - [Typo-tolerant Query auto-completion - derived from indexed documents](https://seekstorm.com/blog/query-auto-completion-(QAC)/) - [SeekStorm 3.0 adds vector search & hybrid search](https://seekstorm.com/blog/seekstorm-adds-vector_search-hybrid-search/) ### SeekStorm high-performance search library #### Hybrid search * Internally, SeekStorm uses [**two separate, first-class, native index architectures**](ARCHITECTURE.md#architecture) for **vector search** and **keyword search**. Two native cores, not just a retrofit, add-on layer. * SeekStorm doesnβt try to make one index do everything. It runs two native search engines and lets the query planner decide how to combine them. * Two **native** index architectures under one roof: - **Lexical search**: an inverted index optimized for lexical relevance, - **Vector search**: an ANN index optimized for vector similarity. * Both are first-class engines, integrated at the query planner level. - Query planner with multiple QueryModes and FusionTypes - **Per query choice** of lexical search, **vector search**, or **hybrid search**. * Separate internal index, storage layouts, indexing, search, scoring, top-k candidates - unified query planner and result fusion (Reciprocal Rank Fusion - RRF). * But the user is fully shielded from the complexity, as if it was only a single index. * Enables pure lexical, pure vector or hybrid search (exhaustive, not only re-ranking of preliminary candidates). #### Architecture * *Fast* sharded indexing: 35K docs/sec = 3 billion docs/day on a laptop. * *Fast* sharded search: [7x faster query latency, 17x faster tail latency (P99)](#benchmarks) for lexical search. * Billion-scale index * Index either in RAM or memory mapped files * Cross-platform (Windows, Linux, MacOS) * SIMD (Single Instruction, Multiple Data) hardware acceleration support, both for x86-64 (AMD64 and Intel 64) and AArch64 (ARM, Apple Silicon). * Single-machine scalability: serving thousands of concurrent queries with low latency from a single commodity server without needing clusters or proprietary hardware accelerators. * 100% human π craftsmanship - No AI π€ was forced into vibe coding/AI slop. #### Vector Features * **Multi-Vector indexing**: both from multiple fields and from multiple chunks per field. * **Integrated inference**: Generate and index embeddings from any text document field, using [Model2Vec from MinishLab](https://gi ``` --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/tools/seekstorm-seekstorm`](/api/graphcanon/tools/seekstorm-seekstorm) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_