AI Parse

A skill for parsing PDF files using Large Language Models.

Capabilities

• Extract information from PDF files
• Return results in JSON or Markdown format
• Support both authenticated and trial modes
• Resume processing from existing task ID
• Save task ID information to JSON file for reference

Trial Mode (No Registration) Authenticated Mode (Registered Users)

Trial Mode Instructions

Trial Mode: No registration required. Perfect for testing and small PDF files.

Parameters

Parameter	Type	Required	Description
pdf_path	string	required	Path to the PDF file to process
result_path	string	required	Path to save the parsing result
format	string	required	Output format: "json" or "md"
task_id_path	string	required	Path to save task ID information (JSON format)
--task-id	string	optional	Existing task ID to resume processing

Usage Examples

Normal Upload Mode

python handler.py <pdf_path> <result_path> <format> <task_id_path>

Resume from Existing Task or Check Status

python handler.py --task-id <task_id> <result_path> <format>

Limitations: Trial mode has page limits. Visit https://api.pinocch.com/index to register for additional credits.

Authenticated Mode Instructions

Authenticated Mode: Get more credits and advanced features by registering.

Getting Started

To use this skill with authentication, you need to register and obtain your API token:

1. Register an account at https://api.pinocch.com/index
2. Navigate to the My Profile page
3. Generate your API token (see screenshot below)
4. Create a file named secret.txt in the skill directory with the following format:

username: <your username>
secret: <your token>

Token Generation Screenshot:

Parameters

Parameter	Type	Required	Description
username	string	required	Username for authentication
secret	string	required	Secret token for authentication
pdf_path	string	required	Path to the PDF file to process
result_path	string	required	Path to save the parsing result
format	string	required	Output format: "json" or "md"
task_id_path	string	required	Path to save task ID information (JSON format)
--task-id	string	optional	Existing task ID to resume processing

Usage Examples

Normal Upload Mode

python handler.py <username> <secret> <pdf_path> <result_path> <format> <task_id_path>

Resume from Existing Task or Check Status

python handler.py --task-id <task_id> <username> <secret> <result_path> <format>

Task ID File Format

When using normal upload mode, a task ID file will be created at task_id_path with the following JSON structure:

{
  "task_id": "AAFXKO",
  "pdf_path": "test.pdf",
  "submit_time": "2026-04-04 00:33:27"
}

This file can be used to:

• Track the submitted task
• Retrieve the task ID later for status checking
• Resume processing if interrupted

Implementation

Implemented by handler.py which:

• Uploads PDF files to the processing service
• Polls for processing completion
• Downloads and saves results in the requested format
• Supports resuming from existing task IDs
• Saves task ID information to JSON file

Environment Requirements

• Python 3.6+
• requests library

Return Value

The parsed result will be saved to the specified result_path in the requested format:

• JSON format: Structured JSON with task details and extracted content
• Markdown format: Formatted Markdown with page-by-page content

Notes

• For large PDF files, processing may take multiple minutes
• The --task-id parameter can be used to resume processing if interrupted
• Check the console output for processing progress and status updates
• The task ID file is created immediately after successful upload
• IMPORTANT FOR AGENTS: Before declaring a task as failed, always use the task ID to check the current status of the task. Use the --task-id parameter to resume or verify the task status. The task may still be processing or have completed successfully.