AnyDoc Dify Plugin

Convert documents to GitHub-Flavored Markdown inside Dify using AnyDoc by Firecrawl. Conversion runs locally in the plugin runtime. No network connection, endpoint, host, or proxy is required, and document contents are not sent to an external API.

Marketplace namespace:
Source repository: https://github.com/erbanku/anydoc
Contact: [email protected]
License: MIT

Supported formats

Word: DOC, DOCX, DOCM
PowerPoint: PPT, PPS, POT, PPTX, PPTM, PPSX, PPSM
Excel: XLS, XLSX, XLSM, XLSB
OpenDocument: ODT, ODS, ODP
RTF, EPUB, CSV, and text-based PDF

Format detection prefers file content signatures. The uploaded filename is used as a fallback for signature-less formats such as CSV.

Tool output

returns:

Markdown text
A downloadable blob
JSON metadata with detected format, filenames, and output size

Requirements

Dify with plugin support (Python 3.12 runner)
Linux amd64 or arm64 plugin runtime
No API credentials, authentication, or network endpoint required

Setup

Install the plugin from the Dify Marketplace or upload a packaged .
Add the Convert to Markdown tool to a workflow or agent.
Provide a supported document file as input.

Local development

The deployment package uses and vendored Linux wheelhouses for offline installs. The source tree keeps for local validation.

Limitations

AnyDoc converts text-based PDFs but does not perform OCR. Use an OCR plugin for scanned or image-only PDFs. Encrypted documents are not supported. Embedded image bytes remain in AnyDoc's document model and are not exported by this Markdown-only tool.

Privacy

See PRIVACY.md. Document contents are processed locally and are not transmitted to third-party services.

Localization

Simplified Chinese README: readme/README_zh_Hans.md