Advanced · 03

Obsidian as an LLM knowledge base

An Obsidian vault has quietly become the best personal infrastructure for LLM work: a folder of plain Markdown, linked into a graph, fully local. Every AI integration that reads vaults — and every copy-paste into a chat — inherits whatever quality your notes have. Which makes the conversion question concrete: when a PDF, notebook or report enters your vault, what should it become?

1 · Why the vault shape fits LLMs

2 · What the Obsidian preset emits

ElementOutput
Document metadataYAML front matter (title, source file, date) — Dataview-queryable
Overview / summary sections> [!abstract] callouts
Method-like sections> [!info] / > [!warning] callouts by role (limitations get warnings)
Figures![[figures/chart_1.png]] embeds — drop the .zip's figures folder into the vault and they render
Notebook cellsKept as plain sections (cell headers stay addressable, not callout-wrapped)

The callout mapping is heuristic and says so — it styles the note for scanning; the underlying text is untouched.

report.md > [!info] from report.pdf …see ![[figure_3.png]] …method in [[spec-v2]]
Callouts carry provenance, wikilinks feed the graph — converted documents become first-class vault citizens.

3 · Three vault workflows this unlocks

  1. The reading inbox. Saved articles (.html) convert to notes with the chrome already stripped — your highlights-and-links pass starts from clean text.
  2. The analysis archive. Notebooks convert with cell addresses, so a note can cite Cell [12] and a future chat about that note can too.
  3. The AI-readable reference shelf. Specs, reports and transcripts (.srt meeting captions included) become vault citizens that any assistant-with-vault -access can retrieve properly — the same chunking logic as hosted workspaces, but on your disk.

4 · Vault hygiene that pays off with models

Convert something with the Obsidian preset and drop it straight into your vault — front matter, callouts, figure embeds.