[Feat] Add timeout and strip image html tags for PaddleOCR plugin

[Bobholamovic]

This PR contains Changes to Non-LLM Models Plugin

• I have Run Comprehensive Tests Relevant to My Changes

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

• I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Dify Plugin SDK Version

• I have Ensured dify_plugin>=0.3.0,<0.6.0 is in requirements.txt (SDK docs)

[gemini-code-assist]

Summary of Changes

Hello @Bobholamovic, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the PaddleOCR plugin by improving its reliability and the quality of its output. It introduces request timeouts for all external API calls, coupled with robust error handling, to prevent the plugin from hanging and to provide more informative feedback on failures. Furthermore, it refines the markdown output from document parsing by stripping out extraneous HTML image tags, resulting in a cleaner and more focused textual representation.

Highlights

• Version Update: The PaddleOCR plugin version has been incremented from 0.1.2 to 0.1.3 in the manifest file.
• API Request Timeout: A timeout mechanism has been implemented for all external API calls made by the PaddleOCR plugin to prevent indefinite waiting and improve robustness.
• Timeout Error Handling: Specific exception handling for API request timeouts has been added, providing clearer error messages when the PaddleOCR API request times out.
• Image Tag Stripping from Markdown: A new utility function was introduced to automatically remove HTML image tags from markdown output generated by the document parsing tools, ensuring cleaner text.
• Authorization Header Correction: The authorization header format in document_parsing_vl.py was corrected from 'Bearer' to 'token' for consistency and correctness.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces several valuable improvements to the PaddleOCR plugin. It enhances robustness by adding a request timeout to API calls and properly handling timeout exceptions. It also cleans up the output of document parsing tools by stripping HTML image tags. The version bump and the fix for the authorization header are also correctly implemented. My main feedback is about a minor code duplication issue with the REQUEST_TIMEOUT constant, which is defined in three different files. I've suggested centralizing it in the new tools/utils.py module to improve maintainability. Overall, this is a good set of changes.