Returns the parsed full text of the source's PDF as markdown: title, abstract, and body. Includes a nullable download object with downloadUrl, expiresAt, filename, and contentType for the original PDF. The URL expires after 30 minutes; call again for a fresh URL. Fetch download.downloadUrl with curl -L --fail --output paper.pdf '<downloadUrl>', without an Authorization header. If a download URL is temporarily unavailable, download is null and the parsed text is still returned. Before parsing finishes, use get_library_source to get the original PDF download details.

A 404 has one of three codes. full_text_pending: the PDF search or parse is in progress; retry later. full_text_unavailable: no PDF was found. not_found: the source is not visible to you.

Example

curl https://elicit.com/api/v2/library/sources/{sourceId}/full-text \
  -H "Authorization: Bearer elk_live_your_key_here"