fix bug: return type mismatch

[alcholiclg]

Change Summary

1. Fix mismatch between return type and received variable in calling load_image_from_uri_to_pil(), which will further interrupt the loading process of doc_loader.
2. Remove unused ext variable.
3. Abandon download.py due to the support of downloading model from modelscope.

Related issue number

Checklist

• The pull request title is a good summary of the changes - it will be used in the changelog
• Unit tests for the changes exist
• Run pre-commit install and pre-commit run --all-files before git commit, and passed lint check.
• Some cases need DASHSCOPE_TOKEN_API to pass the Unit Tests, I have at least pass the Unit tests on local
• Documentation reflects the changes where applicable
• My PR is ready to review, please add a comment including the phrase "please review" to assign reviewers

[gemini-code-assist]

Summary of Changes

Hello @alcholiclg, 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 primarily addresses a critical bug related to image loading within the doc_loader by fixing a return type mismatch in a utility function. It also includes important code cleanup by removing an unused variable and an entire script that is no longer necessary due to updated model downloading capabilities.

Highlights

• Bug Fix: Image Loading: Corrected a return type mismatch when calling load_image_from_uri_to_pil() within the doc_loader, which previously interrupted the image loading process. The function now consistently returns only the PIL Image object.
• Code Cleanup: Unused Variable Removal: Eliminated the unused ext variable and its associated extraction logic from the load_image_from_uri_to_pil function, simplifying the code.
• Obsolete File Removal: Removed the ms_agent/utils/download.py script, as its model downloading functionality is now superseded by direct support for downloading models from ModelScope.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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 effectively resolves a bug related to a return type mismatch in load_image_from_uri_to_pil, and the associated changes are correct. The removal of the obsolete download.py script is also a good cleanup. I've added one suggestion to improve error handling by adopting Python's standard logging module instead of using print statements, which will enhance maintainability.

[gemini-code-assist]

While the clarification in the error message is helpful, using print() for logging errors is generally discouraged in application code. It's a better practice to use Python's logging module, which offers more flexibility and control (e.g., log levels, different handlers, formatting).

I recommend replacing all print calls within the except blocks of this function with logging.error(). This would require import logging at the module level.

Suggested change

	print(f'Error opening image with PIL: {e}')
	logging.error(f'Error opening image with PIL: {e}')