Perception
Parse
nace parse https://example.com/report.pdf -p 1-3 --format markdown,blocks > report.md
nace parse ./locked.pdf --password - # asks for the password, or reads it from a pipe| Flag | What it does |
|---|---|
--format FORMATS | A comma list of markdown, text and blocks, sent as output.formats. Default: the API's markdown,blocks. |
--table-format {html,markdown} | How tables are written inside the Markdown and text, sent as output.table_format. Default html. |
--chunk {none,page,section} | Split the document into pieces for retrieval, sent as chunking.strategy. Default none. |
--figures {omit,include,describe} | Drop figures, keep them, or keep them and caption them, sent as figures.mode. Default include. |
--sheets NAMES | A workbook's sheets to parse, as a comma list of names, sent as spreadsheet.sheets. Default: every sheet. |
--password VALUE | An encrypted PDF's password: the text, @FILE, or - for stdin, without one trailing newline. At a terminal, - asks at a prompt that doesn't echo it. Not with a job: source. Debug logs mask it. |
Each of these flags wins over the same field from --option or --options, and keeps the other fields of its block. With -o auto, stdout gets the Markdown, or the text when you asked only for text, except for a large document's full content (below). Ask for blocks alone and you get the result JSON. See Parse.
Large documents and workbooks
For a very large document, document.markdown is only a preview, and document.content_url links the full Markdown. See Very large results. With -o auto or md, nace parse and nace job fetch the full content instead, to stdout or --save, and say so on stderr. They wait up to --wait-timeout while it's being prepared. If the fetch fails, they print the preview, name the nace file <job> <content_url> command that fetches the rest on stderr, and exit 1. After --format text, the full content can be Markdown, since that can be the only form the service keeps; stderr says so.
For a workbook whose sheets each have a content_url, they print the preview and list one nace file <job> <content_url> per sheet on stderr. nace rows reads a sheet's rows.