qmdlisted

# QMD — Local Knowledge Base Search QMD is the local vector+keyword search engine over the user's workspaces. Use it **before** answering questions that may already be documented — especially for context about people, projects, decisions, and past work. ## Workflow The workflow is always: 1. **Search** for candidate documents. 2. **Retrieve** the full source with `qmd get` or `qmd multi-get`. 3. **Answer** from retrieved text, citing paths or docids. **Do not answer from snippets alone** when the user needs facts, decisions, quotes, or nuance. Snippets are only leads. When reporting what you retrieved, a compact note is enough; do not paste whole files unless needed: ```text Retrieved: #abc123 wiki/projects/GenAICategorizer.md, #def432 memory/2026-05-26.md ``` ## Pick the right search mode | Mode | Command | When to use | |---|---|---| | BM25 keyword | `qmd search` | Exact words, titles, names, code symbols, rare phrases | | Hybrid + rerank | `qmd query` | Indirect wording, conceptual recall, best quality | | Structured | `qmd query` with `lex:/vec:/hyde:` fields | Hard searches needing exact anchors + semantic recall | **Simple lookup:** ```bash qmd search "challenger crew project status" -n 10 qmd search '"GenAI Categorizer"' -c wiki-main -n 5 ``` **Semantic concept lookup:** ```bash qmd query "decision quality depends on surfacing assumptions and context" -n 10 ``` **Structured query (hard searches):** ```bash qmd query $'intent: Find the concept note about met