Turn Obsidian into local LLMs context

Why Obsidian needs preparation before local LLMs

An Obsidian vault can be a deep knowledge base, but pasting one note at a time loses links, folder context, and the supporting notes around an idea.

Local models are useful for private workflows, but they usually need tighter bundles because context limits vary by runtime. The result depends heavily on how cleanly your source material is grouped, labeled, and filtered before it reaches the model.

Step-by-step workflow

Point Riflet at your vault folder and select the notes, MOCs, and project folders that should shape the answer.

• Add Obsidian vaults as a Riflet source.
• Select MOCs, project notes, evergreen notes, research summaries, source notes, and short instruction files that explain naming conventions.
• Use filters to remove stale exports, generated files, and unrelated background material.
• Export one Markdown or text bundle and use it in local LLMs.

What to include

For this workflow, prioritize MOCs, project notes, evergreen notes, research summaries, source notes, and short instruction files that explain naming conventions. Add a short instruction file at the top if the AI needs naming conventions, project goals, or constraints.

A full-vault dump is rarely the best context. Curate topical folders, current notes, and project maps so the model does not spend tokens on unrelated daily notes.

Getting the bundle into local LLMs

local LLMs keeps uploaded material in the prompt itself. Paste the bundle into the prompt, or load it through the front-end you run, such as LM Studio, Ollama, or a text-generation web UI. It accepts plain text and Markdown, so a Markdown or plain-text export from Riflet needs no further conversion.

The usable context limit is often far below the number on the model card, because quantisation and available VRAM cap what you can actually load. Check the limit your runtime reports, not the headline figure, before sizing the bundle.

Nothing persists between runs, so the bundle is re-sent every session. That makes bundle size a recurring cost rather than a one-time one, and it is the strongest argument for trimming hard.

Token budget advice

Riflet lets you check the bundle against Local LLM's 32,768-token context window before export. Keep room for your actual question and for the model's answer.

If the bundle is too large, remove files that merely repeat what another file already explains. Context quality usually beats context volume.

Honest limitation

Riflet does not push live updates into local LLMs. It creates the context file. When the source changes, re-export and upload the new bundle yourself.