Extroactor pdf 2 image

[ic-xu]

Summary

Many friends chat with the large model by uploading PDFs. The current approach is to extract the text content from the PDF and input it into the model. We found that this method might lose some important information in the PDF, such as layout, tables, and even the relationships between elements. I hope to input as much information as possible into the model, so I created a feature to convert PDFs to images for input.

Tip

Close issue syntax: Fixes #<issue number> or Resolves #<issue number>, see documentation for more details.

Screenshots

Before	After
...

Checklist

Important

Please review the checklist below before submitting your pull request.

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[laipz8200]

Adding a special case for PDF - Image in the Document Extractor might confuse users. I think this feature should be implemented as a Tool.

Additionally, models that excel at image recognition, such as Gemini and Claude, also support direct PDF input.