Skip to content

Conversation

@omiya0555
Copy link

  • Document Parser: Parse documents to Markdown/HTML/Text
  • Information Extract: Extract structured data with JSON schema
  • Supports PDF, images, and office documents
  • Memory caching for performance optimization
  • Developer: omiya0555
  • Organization: Fusic

Plugin Submission Form

1. Metadata

2. Submission Type

  • New plugin submission
  • Version update for existing plugin

3. Description

This plugin provides advanced Document AI capabilities using Upstage API with two powerful tools:

  1. Document Parser
  • Parses PDFs, images, and office documents into text/HTML/Markdown format
  • Multi-format support: PDF, DOCX, XLSX, PPTX, JPEG, PNG, BMP, TIFF, HEIC
  • Advanced OCR with chart detection
  1. Information Extract
  • Extracts structured data from documents using custom JSON schemas
  • 90-95% accuracy on complex documents
  • Works with any document type without templates or training

Key Features:

  • Intelligent memory caching for improved performance
  • Comprehensive error handling and validation
  • Support for multiple output formats
  • High accuracy OCR and layout detection

4. Checklist

  • I have read and followed the Publish to Dify Marketplace guidelines
  • I have read and comply with the Plugin Developer Agreement
  • I confirm my plugin works properly on both Dify Community Edition and Cloud Version
  • I confirm my plugin has been thoroughly tested for completeness and functionality
  • My plugin brings new value to Dify

5. Documentation Checklist

Please confirm that your plugin README includes all necessary information:

  • Step-by-step setup instructions
  • Detailed usage instructions
  • All required APIs and credentials are clearly listed
  • Connection requirements and configuration details
  • Link to the repository for the plugin source code

6. Privacy Protection Information

Based on Dify Plugin Privacy Protection Guidelines:

Data Collection

Document files (PDFs, images, office documents), Upstage API keys, and processing parameters (JSON schemas, output format preferences).
All data is processed through Upstage API. No permanent storage by the plugin.

Privacy Policy

  • I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

  - Document Parser: Parse documents to Markdown/HTML/Text
  - Information Extract: Extract structured data with JSON schema
  - Supports PDF, images, and office documents
  - Memory caching for performance optimization
  - Developer: omiya0555
  - Organization: Fusic
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant