LLM文档转换 icon

LLM文档转换

LLM文档处理节点,将文档转换为大模型友好的格式

Overview

This node, named "LLM文档转换" (LLM Document Conversion), is designed to convert various document formats into Markdown text using a large language model (LLM) friendly format. Specifically, the "Excel转Markdown" operation under the "文件转Markdown" resource converts Excel files (.xlsx) into Markdown format. This is useful for scenarios where users want to extract and present spreadsheet data in a clean, readable Markdown format for documentation, reports, or publishing on platforms that support Markdown.

Practical examples include:

  • Converting financial reports or data tables from Excel into Markdown for inclusion in GitHub README files.
  • Transforming Excel-based project plans or schedules into Markdown for easy sharing in team chats or wikis.
  • Automating the generation of Markdown documentation from Excel data exports.

Properties

Name Meaning
文件字段名 The name of the input file field containing the document to convert. Supports formats like pdf, doc, docx, ppt, pptx, xlsx, html, csv, etc. For this operation, it should be an Excel file (xlsx).
返回Markdown文本 Boolean option indicating whether to return the converted Markdown text content (true) or only return the URL of the converted document (false).

Output

The node outputs JSON data containing the conversion results. If the "返回Markdown文本" property is enabled, the output JSON will include the Markdown text extracted from the Excel file. Otherwise, it returns a URL pointing to the converted document.

If binary data is involved (e.g., the original Excel file), it is handled internally but not explicitly exposed in the output JSON.

Dependencies

  • Requires an API key credential for accessing the LLM document conversion service.
  • The node communicates with an external API endpoint specified by the base URL configured in the credentials.
  • Supported document formats depend on the backend service capabilities.

Troubleshooting

  • Common issues:

    • Uploading unsupported file formats may cause conversion failures.
    • Missing or invalid API credentials will prevent the node from authenticating with the conversion service.
    • Large Excel files might lead to timeouts or incomplete conversions.
  • Error messages:

    • Authentication errors indicate problems with the provided API key; verify and update credentials.
    • File format errors suggest the input file is not supported or corrupted; ensure the file is a valid Excel document.
    • Network or timeout errors require checking connectivity and possibly increasing timeout settings.

Links and References

  • No direct links are embedded in the source code. Users should refer to the documentation of the external LLM document conversion API used by this node for detailed usage and limitations.

Discussion