FAQ
The questions we hear most.
If yours is not here, mail us and short answers come back fast.
- What is a digest?
- A single Markdown file containing the full text of all your sources, with source headers, metadata, and structure preserved. Drop it into any LLM.
- Why not just paste my PDFs in?
- Pasting drops headings, mangles tables, breaks code blocks, and burns tokens on noise. FileDigest preserves structure and tags sources so the model can reason across them.
- Is my data trained on?
- No. Files are processed in ephemeral sandboxes. Source files are deleted from storage right after a successful job unless you opt to retain them, and you can delete saved digests at any time.
- Do you support OCR?
- Yes, on Pro and Business. Docling handles scanned PDFs with layout-aware parsing.
- What does FileDigest actually do?
- It takes one or more files, such as PDFs, DOCXs, slides, or folders, and produces one ordered Markdown document with section headers, tables, code blocks, and source-file metadata preserved. You paste that document into any LLM. We do not run the LLM for you; we hand you a clean input.
- How long does processing take?
- A typical 4.5MB cold-start run finishes in about 62 seconds. The same file warm comes back in roughly 17 seconds. Larger jobs scale roughly linearly with token count.
- What file formats do you support?
- PDF and DOCX are the primary formats. PPTX, XLSX, HTML, Markdown, plain text, common image formats, ZIP batches, and folder picks are supported where the parser can read them.
- Do you keep my files?
- Source files are deleted from object storage immediately after a successful job unless you explicitly opt to retain them. Processed digests stay in your account until you delete them or delete your account. Full details in our privacy policy.
- How is pricing measured?
- In LLM tokens - the same units the model sees, roughly 1,000 tokens per 1.5 pages of typical PDF. Free is 3M tokens / month. Pro and Business scale up. See the breakdown on /pricing.
- Where do I report a bug or ask for a feature?
- Email hello@filedigest.app. We read everything. Bug reports with the job id and a brief description are most useful.