Turn Notion into local LLMs context

Why Notion needs preparation before local LLMs

Notion pages often hold product specs, client notes, meeting notes, and research, but AI chats cannot reliably see the whole workspace unless you prepare an export.

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

Connect your Notion workspace to Riflet with a connection token, or export the pages as Markdown and CSV and add the exported folder.

• Add Notion workspace exports as a Riflet source.
• Select project pages, PRDs, meeting notes, decision logs, client briefs, and exported databases that matter for the question.
• 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 project pages, PRDs, meeting notes, decision logs, client briefs, and exported databases that matter for the question. Add a short instruction file at the top if the AI needs naming conventions, project goals, or constraints.

This workflow does not connect live to Notion. You export from Notion first, then Riflet helps select, merge, and budget the exported files. Riflet can also connect directly to a Notion workspace with a connection token if you would rather skip the export.

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.