API
detailed description of the API endpoints, including their functionality and how to use them via curl requests.
Documents
Parse Any Document
Endpoint: /parse_document
Method: POST
Parses PDF, PowerPoint, or Word documents.
Curl command:
Parse PDF
Endpoint: /parse_document/pdf
Method: POST
Parses PDF documents.
Curl command:
Parse PowerPoint
Endpoint: /parse_document/ppt
Method: POST
Parses PowerPoint presentations.
Curl command:
Parse Word Document
Endpoint: /parse_document/docs
Method: POST
Parses Word documents.
Curl command:
Image
Parse Image
Endpoint: /parse_media/image
Method: POST
Parses image files (PNG, JPEG, JPG, TIFF, WEBP).
Curl command:
Process Image
Endpoint: /parse_media/process_image
Method: POST
Processes an image with a specific task.
Possible task inputs: OCR | OCR with Region | Caption | Detailed Caption | More Detailed Caption | Object Detection | Dense Region Caption | Region Proposal
Curl command:
Arguments:
image
: The image filetask
: The processing task (e.g., Caption, Object Detection)prompt
: Optional prompt for certain tasks
Media
Parse Video
Endpoint: /parse_media/video
Method: POST
Parses video files (MP4, AVI, MOV, MKV).
Curl command:
Parse Audio
Endpoint: /parse_media/audio
Method: POST
Parses audio files (MP3, WAV, FLAC).
Curl command:
Website
Parse Website
Endpoint: /parse_website
Method: POST
Parses a website given its URL.
Curl command:
Arguments:
url
: The URL of the website to parse
Last updated