Supported file types
Curator reads text and metadata from common text, PDF, and image files. That extracted content is what makes a file searchable and lets chat cite it.
Any file can still be browsed by name in All Files even when Curator cannot read its content. It just will not show up in content or meaning-based search until its text can be extracted.
Read for content
Section titled “Read for content”These are the files Curator reads all the way through, so their contents become searchable.
| Category | Extensions | How it is read |
|---|---|---|
| Text and code | .txt, .md, .csv, .json, .xml, .html, .yaml, .toml, .ini, .log, plus common code files (.py, .js, .ts, .rs, .go, .java, .c, .cpp, .css, .sh, .sql, and more) | Read directly as text. |
| PDFs | .pdf | Text PDFs are read directly. Scanned or image-only PDFs are read page by page with OCR, up to 50 pages. |
| Images | .jpg, .jpeg, .png, .gif, .bmp, .webp, .tiff, .heic, .heif, .svg, .ico | A vision model looks at the image and describes what it contains. |
Browsed by name only
Section titled “Browsed by name only”Curator indexes these files so you can find them by name, but it does not read inside them. It records a best guess from the filename instead, so they will not turn up in content search.
| Category | Extensions | Notes |
|---|---|---|
| Office documents | .doc, .docx, .ppt, .pptx, .rtf, .odt, .pages, .keynote | Not read for content yet. |
| Spreadsheets | .xls, .xlsx, .ods, .numbers | Not read for content yet. |
| Archives and apps | .zip, .tar, .gz, .7z, .rar, .dmg, .pkg, .exe, and similar | Skipped entirely. |
| Audio and video | Common audio and video files | Skipped entirely. |
For how this content is turned into search, see How processing works.