#search

Wiki 7

  • Agentic Search Search an agent decides when and how to run, across many context sources each with its own native search tool
  • Agentic Search for Context Engineering Leonie Monigatti's case that context engineering is ~80% agentic search, with three demos on what each search tool can and can't do
  • Fast Levenshtein Distance Using a Trie How to find dictionary words within N edits of a query 300× faster by sharing Levenshtein table rows across trie prefixes
  • Full Text Search with IndexedDB Building full-text search on IndexedDB with multiEntry indexes and rarest-term probing
  • Hybrid Search Combining BM25 keyword search with embedding similarity for better retrieval
  • Inverted Index Data structure mapping terms to documents, the foundation of all full-text search systems
  • Terminal Search Clients ddgr, googler and two Kagi CLIs compared on auth cost, output format, upkeep and agent use

Toolbox 2

  • msgvault Offline email archive with SQLite full-text, DuckDB analytics and an MCP server over it
  • qmd Local-first search over markdown notes combining BM25, vector search and LLM re-ranking