Skip to content

Upload Files in Chat

Drop a file into a Pinchy chat and the agent receives its content directly — no copy-pasting, no separate upload step.

Text and documents

Any text-based file — Markdown, CSV, JSON, YAML, plain text, source code, and similar formats — is fully readable by the agent. You can drop a .csv or a .md just like a PDF and the agent will read the whole thing.

  • PDF (with text extraction and vision analysis)
  • Microsoft Word (.docx)

Code and text

  • .txt, .md, .csv, .json, .xml, .html, .css, plus common source-file extensions

Images

  • JPEG, PNG, WebP, GIF, HEIC/HEIF

15 MB per file.

Two things happen when you attach a file:

  1. The file is saved to the agent’s workspace at uploads/<filename>. The agent reads it on demand from there.
  2. Images are also sent inline to the LLM when the model supports vision, so the agent can “see” an image without a separate read step.

For PDFs, Pinchy automatically picks the best vision-capable model available in your provider configuration. Anthropic Claude and Google Gemini handle PDFs natively; other vision-capable models fall back to a text-and-image extraction step.

For Microsoft Word .docx files, Pinchy extracts the document’s text — paragraphs, headings, and tables — at upload time and ships it directly to the agent as text. No vision model required. Embedded images in .docx are not yet processed.

Workspaces are isolated per agent: file-reading tools only see files in that agent’s own workspace, never another agent’s files or the host system. See Agent Workspaces for the full picture.

Files uploaded to a shared agent are visible to all users with access to that agent — they live in a workspace that everyone with access to the agent shares. Pinchy shows a reminder of this in the upload UI. If you’re uploading sensitive content, use a personal agent instead. See Agent Workspaces for the privacy implications.

Pinchy renders an inline preview next to your chat message:

  • PDFs show a small first-page thumbnail. Click to open the browser’s PDF viewer in a modal — zoom, page-nav and download all work as you’d expect.
  • Images render as a thumbnail. Click to enlarge.

Both previews survive page reloads — the file lives in the agent workspace, not in browser memory, so it’s still there hours or days later.

Pinchy validates every uploaded file against its actual content, not just the browser-reported MIME type. A file renamed to .pdf that contains executable code will be rejected. Filenames are also sanitized before being written to disk.