Skip to main content
POST
Read any file into Markdown ready for a model (Word, PowerPoint, Excel, PDF, .doc/.ppt/.xls, TXT, Markdown)

Authorizations

Authorization
string
header
required

Authorization: Bearer ak_eu_…. The prefix is the project's region and must match the server (api.eu / api.us).

Body

file
required

A file uploaded with POST /files.

Pattern: ^file_
store
boolean
default:true

false: its content is deleted 15 minutes after it finishes.

Response

The text, as Markdown.

object
string
required
Allowed value: "extraction"
document_id
string
required
Pattern: ^doc_[0-9A-HJKMNP-TV-Z]{26}$
format
enum<string>
required
Available options:
docx,
pptx,
xlsx,
pdf,
doc,
ppt,
xls,
txt,
md,
png,
jpg,
gif,
webp
markdown
string
required

Headings, lists and tables kept; one section per slide or sheet; page markers in a PDF. Scanned pages and pictures are read with OCR.

chars
integer
required

Length of the whole text, before any cut.

Required range: -9007199254740991 <= x <= 9007199254740991
truncated
boolean
required

true when longer than 2 000 000 characters.

pages
integer | null
required

Pages (PDF), slides (PowerPoint) or sheets (Excel).

Required range: -9007199254740991 <= x <= 9007199254740991