Mineru icon

Mineru

Use Mineru API to parse PDF, documents, and images, automatically create tasks and wait for results

Mineru

AI-generated

Overview

This node integrates with the Mineru API to parse documents and images from a provided URL. It supports various formats including PDF, DOC, DOCX, PPT, PPTX, PNG, JPG, and JPEG. The node creates a parsing task on Mineru, optionally enabling OCR, formula recognition, and table recognition. It waits for the task to complete by polling the API at specified intervals and downloads the resulting parsed data as a ZIP file. This node is useful for automating document data extraction workflows, such as extracting text, tables, and formulas from business documents or scanned images.

Use Case Examples

  1. Extract text and tables from a PDF invoice URL to automate data entry.
  2. Parse scanned images with OCR enabled to convert them into searchable text.
  3. Download parsed document data in multiple formats including markdown, JSON, and DOCX for further processing.

Properties

Name Meaning
Document URL The URL of the document to be parsed, supporting multiple file formats.
Enable OCR Whether to enable OCR functionality to recognize text in images.
Enable Formula Recognition Whether to enable formula recognition functionality.
Enable Table Recognition Whether to enable table recognition functionality.
Document Language Specify the language of the document for parsing.
Data ID Optional identifier for the business data to help identify the document.
Page Range Specify the page ranges to parse, e.g., '1-10,15,20-25'.
Extra Export Format Additional export formats besides the default markdown and JSON, such as DOCX, HTML, or LaTeX.
Model Version Select Mineru model version to use for parsing.
Polling Interval (Seconds) Interval in seconds to check the parsing task status.
Maximum Waiting Time (Minutes) Maximum time in minutes to wait for the parsing task to complete.

Output

Binary

Outputs the parsed document data as a ZIP file containing the extracted content in requested formats.

JSON

  • fileName - The name of the downloaded ZIP file containing parsed data.
  • fileSize - The size of the downloaded ZIP file in bytes.
  • error - Error message if the parsing or download failed.

Dependencies

  • Mineru API with an API token credential

Troubleshooting

  • Ensure the Document URL is valid and accessible; empty or invalid URLs cause errors.
  • API token must be valid and authorized; invalid tokens cause authentication failures.
  • Parsing task may fail if the document format is unsupported or corrupted.
  • Task timeout error occurs if parsing takes longer than the specified maximum waiting time.
  • File download errors may occur due to network issues or invalid download links.

Links

Discussion