All Stories

Introducing the SeekStorm MCP server

Introducing the SeekStorm MCP server

Connect AI applications to SeekStorm through the Model Context Protocol (MCP), with no separate seekstorm_server process required.

symspell_rs v7 - 3x faster lookup, 40% less memory consumption, 11x faster Damerau-Levenshtein edit distance

symspell_rs v7 - 3x faster lookup, 40% less memory consumption, 11x faster Damerau-Levenshtein edit distance

symspell_rs v7 introduces both significant implementation changes to SymSpell as well as algorithmic changes to the Damerau-Levenshtein calculation between v6.8.4 vs. v7.0.1. The resulting performance improvements are measured with the...

🔥SeekStorm 3.0 adds vector search & hybrid search

🔥SeekStorm 3.0 adds vector search & hybrid search

SeekStorm uses two separate, first-class, native index architectures, under one roof. Lexical search (sparse retrieval): sharded and leveled inverted index. Vector search (dense retrieval): sharded and leveled IVF index for...

Document iterator and search with empty query string

Document iterator and search with empty query string

SeekStorm introduces a new Document Iterator API and support search with empty query strings.

Typo-tolerant Query auto-completion (QAC) - derived from indexed documents

Typo-tolerant Query auto-completion (QAC) - derived from indexed documents

— work in progress, live reporting from the lab 😀 —