# QMD - Quick Markdown Search

Use Bun instead of Node.js (`bun` not `node`, `bun install` not `npm install`).

## Commands

```sh
qmd add .              # Index markdown files in current directory
qmd status             # Show index status and collections
qmd update-all         # Re-index all collections
qmd embed              # Generate vector embeddings (requires Ollama)
qmd search <query>     # BM25 full-text search
qmd vsearch <query>    # Vector similarity search
qmd query <query>      # Hybrid search with reranking (best quality)
```

## Development

```sh
bun qmd.ts <command>   # Run from source
bun link               # Install globally as 'qmd'
```

## Architecture

- SQLite FTS5 for full-text search (BM25)
- sqlite-vec for vector similarity search
- Ollama for embeddings (embeddinggemma) and reranking (qwen3-reranker)
- Reciprocal Rank Fusion (RRF) for combining results

## Important: Do NOT run automatically

- Never run `qmd add`, `qmd add-context`, `qmd embed`, or `qmd update-all` automatically
- Never modify the SQLite database directly
- Write out example commands for the user to run manually
- Index is stored at `~/.cache/qmd/index.sqlite`

## Do NOT compile

- Never run `bun build --compile` - it overwrites the shell wrapper and breaks sqlite-vec
- The `qmd` file is a shell script that runs `bun qmd.ts` - do not replace it