Qmd

QMD - Query Markdown Documents

How search works

QMD searches local markdown collections: notes, docs, wikis, transcripts, and project knowledge bases. Use it before web search when the answer may already be in indexed local files.

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.

Typical loop:

qmd search "merchant reality support interviews" -n 5
# leads: #abc123 concepts/customer-proximity.md; #def432 sources/merchant-call.md
qmd multi-get "#abc123,#def432" --format md

Default to structured qmd query with intent:, lex:, vec:, and hyde: fields that you write yourself. You are a better query expander than the built-in model: you know the user's actual goal, the domain vocabulary, and the nearby-but-wrong concepts to avoid. Do not just paste the user's words into qmd query "..." and hope the expansion model guesses right — supply the intent: and craft the lexical and semantic terms deliberately (see Pick the right search mode).

When reporting what you retrieved, a compact note is enough; do not paste whole files unless needed:

Retrieved:
- #abc123 concepts/customer-proximity.md
- #def432 sources/merchant-call.md

Pick the right search mode

Use BM25 lexical search when you know exact words, titles, names, code symbols, or rare phrases:

qmd search "cockpit OKR Goodhart" -n 10
qmd search '"AI Before Headcount"' -c concepts -n 5

Use qmd query with structured fields when the user describes an idea indirectly, uses different wording than the source, or needs conceptual recall. This is the default mode — write the fields yourself rather than leaning on query expansion. Combine exact anchors with semantic recall:

qmd query $'intent: Find the concept note about metrics as instruments without letting OKRs replace judgment.\nlex: cockpit instruments OKR Goodhart metrics judgment\nvec: data informed not metric driven product judgment\nhyde: A concept note says metrics are useful like cockpit instruments, but leaders should remain data-informed rather than metric-driven because OKRs and dashboards can Goodhart product judgment.'

Structured query fields (you author each one — do not delegate this to the expansion model):

• intent: states what you are trying to find and what to avoid. Always supply this. It steers ranking away from nearby-but-wrong concepts.
• lex: exact terms, aliases, titles, code symbols, and rare words you expect in the source. This is your own keyword expansion.
• vec: paraphrases the idea in natural language, in source-like wording.
• hyde: describes the document or answer that would satisfy the request.

You do not need all four every time, but you should almost always write at least intent: plus one of lex:/vec:. A bare qmd query "the user's sentence" throws away the context only you have and relies on the built-in expander to reconstruct it — prefer the structured form.

If you genuinely have nothing to expand (a single rare token, a verbatim phrase), that is a job for qmd search, not bare qmd query:

qmd query --format json --explain $'intent: ...\nlex: ...\nvec: ...'  # inspect ranking

If qmd query is slow or model/GPU setup fails, fall back to qmd search with better lexical terms.

Retrieve sources

Search results include docids like #abc123 and qmd://... paths. Fetch them:

qmd get "#abc123"
qmd get qmd://concepts/ai-before-headcount.md
qmd multi-get "#abc123,#def432" --format md
qmd multi-get 'concepts/{ai-before-headcount.md,data-informed-not-metric-driven.md}' --format md
qmd multi-get 'sources/podcast-2025-*.md' -l 80

Use multi-get when comparing several hits or gathering context across pages.

Output is line-numbered and carries the docid — cite both

get and multi-get are line-numbered by default and always print the document's #docid and qmd:// path. So get output looks like:

qmd://concepts/note.md  #abc123
---

1: # Metrics as instruments
2:
3: Treat dashboards like cockpit instruments...

Cite the docid and exact line numbers in your answer, and use the numbers to ask for the next slice. Pass --no-line-numbers only when you need raw content to copy verbatim (e.g. reproducing a code block).

When you need to open or edit the underlying file (e.g. hand a path to Read, Edit, or an editor), add --full-path. It replaces the qmd:// URL + docid header with the document's on-disk path, falling back to the canonical header if the file no longer exists on disk:

$ qmd get "#abc123" --full-path
/Users/you/notes/concepts/note.md
---

1: # Metrics as instruments

--full-path works the same way on qmd search and qmd query: result paths become the file's on-disk path — ./-prefixed relative path when the file is inside $PWD, absolute realpath otherwise — and the per-result #docid is dropped because the path is the identifier. The leading ./ is intentional so the output is unambiguously a filesystem path and cannot be mistaken for a bare collection-relative string. Default search/query output still uses qmd:// URIs; only opt into --full-path when you specifically need a path you can hand to a non-QMD tool.