Turn local files into Gemini context

Why local files needs preparation before Gemini

Real project context often lives in a messy local folder with PDFs, Word docs, spreadsheets, notes, and screenshots next to each other.

Gemini is useful when you want a large working context and need to combine notes, docs, and technical material in one pass. The result depends heavily on how cleanly your source material is grouped, labeled, and filtered before it reaches the model.

Step-by-step workflow

Add the folder that contains your project documents, then use the file tree to keep only the files that support the task.

• Add local folders as a Riflet source.
• Select PDFs, DOCX files, spreadsheets, Markdown notes, plain text files, briefs, and source documents.
• Use filters to remove stale exports, generated files, and unrelated background material.
• Export one Markdown or text bundle and use it in Gemini Gems.

What to include

For this workflow, prioritize PDFs, DOCX files, spreadsheets, Markdown notes, plain text files, briefs, and source documents. Add a short instruction file at the top if the AI needs naming conventions, project goals, or constraints.

Binary media should be described or converted before it becomes useful LLM context. Text-heavy documents usually carry the most value.

Getting the bundle into Gemini Gems

Gemini Gems keeps uploaded material in Gem knowledge. Create or edit a Gem and attach the bundle as knowledge, sitting alongside the instructions that define how the Gem should behave. It accepts text, Markdown, PDF, and Google Docs, so a Markdown or plain-text export from Riflet needs no further conversion.

A large context window tempts you to attach everything. The binding constraint is usually attention, not capacity: a focused bundle beats a full dump even when both comfortably fit, because every irrelevant page competes with the relevant ones.

A Gem's knowledge is edited in the Gem itself, so the update is a deliberate step. That is an advantage when you want the Gem's answers to stay pinned to a known version of the source material.

Token budget advice

Riflet lets you check the bundle against Gemini 3.7 Flash's 1,048,576-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 Gemini. It creates the context file. When the source changes, re-export and upload the new bundle yourself.