Turn local files into Perplexity context

Why local files needs preparation before Perplexity

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

Perplexity is best when your prepared source context should be paired with current web-grounded answers. 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 Perplexity.

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 Perplexity

Perplexity keeps uploaded material in a Space. Attach the bundle to a Space when the context should persist, or upload it directly in a thread when the question is one-off. It accepts text, Markdown, and PDF, so a Markdown or plain-text export from Riflet needs no further conversion.

Perplexity blends your file with live web results. Say explicitly when an answer should be grounded in the bundle only, or it may quote a public page over your own documentation and cite it as though both carry the same authority.

Because web results are always current and your bundle is not, the gap between them widens quietly. Re-export whenever the answer starts depending on which source Perplexity happened to prefer.

Token budget advice

Riflet lets you check the bundle against Sonar's 128,000-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 Perplexity. It creates the context file. When the source changes, re-export and upload the new bundle yourself.