Skip to main content

Manage and delete files

Open File management from the menu. Here you manage uploads and files created by the AI. Selecting a file to manage is different from adding it as a source to a chat; see Chat with documents.

Uploading files​

Drag files into the Drop files here box or click Choose files. While uploading, you can see the progress there; you can add more files using the upload button in the toolbar.

Deleting multiple files at once​

  1. Find the files with the filter at the top and, if needed, choose files or images.
  2. Use the table view for an overview with checkboxes. You can also tick files in the grid view.
  3. Tick the files you want to delete. In the table, the checkbox above the column selects the rows on the current page; this does not automatically select all pages.
  4. Check the number of selected files. A selection may include files you previously ticked. Use Clear selection in the table if you want to start over.
  5. Click the trash can at the top. It appears as soon as you have selected something.
  6. Check the number in the confirmation and confirm only if the selection is correct.
  7. Wait for the notification and the refreshed overview. In the event of a partial error, the notification states how many files were and were not deleted. Check the remaining files before trying again.

Deleting removes the selected files from File management. First save your own copy if you may need it later. Disabling an attachment in chat does not delete the saved file.

Downloading and saving​

Select one file to download it directly. With Download as ZIP you can download a selection together. If you have set up a Drive connection, you can also send supported files to the linked folder. You set up these connections under Preferences → Drive connections.

Checking processing​

An upload is only usable once processing is complete. Documents may be up to 150 MB per file; separate limits apply to audio, video, and images. An accepted upload does not mean that every format or type of content can be processed.

If an error occurs, first read the error message. You can have a supported document processed again via the action menu, or by selecting one document and choosing Reprocess. If necessary, resubmit a damaged or protected document as a readable file. Reprocessing replaces the previous text extraction.

For failed audio and the option to delete the source recording after transcription, see Audio and transcription. In that case, the transcript text may be retained; this differs from deleting the entire file in File management.

Checking which sources have been read​

Below an answer, Sources can show which content the model used: Full text, Selection, Summary, Incomplete processing, or Not read. An attached file is therefore not automatically read in full. Check this information before using an answer that must cover all parts of a file.

With a selection or shortened result, you can more specifically ask for a chapter or the remaining parts. In case of incomplete processing, first check the file status. An assistant administrator can choose Complete source text required under Source text: then summaries are not used as a replacement for the text. Large sources may be read in parts and consume more usage. Even then, checking the sources notice remains necessary.

With Automatic, the assistant includes small files (up to 5 files with a combined total of about 30,000 words) in full with every question. This gives faster answers. In larger files, the assistant looks up the relevant parts.

Protected PDFs and missing text​

A protected PDF that opens without a password and contains a text layer can be processed. The text layer is read; OCR of protected scanned pages is not supported. A PDF that asks for a password or contains only scanned pages must be submitted again as a readable, unprotected file.

After uploading, check the processing status. A file that has not yet been processed or does not yield usable text is not silently treated as read. Below the answer, Sources can indicate that processing is incomplete, with the reason. Only ask the AI for conclusions about the full content after processing has succeeded.

On this page