Skip to content

Conversation

alcholiclg
Copy link
Collaborator

Change Summary

  1. Support the new EnrichDocPipeline to enable image classification in .docx and .pptx files.
  2. Support filtering out certain unnecessary images based on the classified image labels.

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.
  • Documentation reflects the changes where applicable

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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 enhances document processing capabilities by introducing image classification and filtering for Word (.docx) and PowerPoint (.pptx) files. It integrates a new enrichment pipeline that can classify images within these documents and subsequently filter out specific image types (like QR codes, logos, and icons) to improve content relevance and reduce noise. This feature aims to provide more refined document parsing and data extraction.

Highlights

  • Image Classification for DOCX and PPTX: This PR introduces the capability to classify images within .docx and .pptx files by integrating a new EnrichDocPipeline. This pipeline utilizes a specialized DocumentPictureClassifier to identify and label images.
  • Intelligent Image Filtering: Building upon the new image classification feature, this change adds functionality to automatically filter out specific types of images, such as QR codes, logos, and icons, based on their classified labels. This helps in refining the document content by removing unnecessary visual elements.
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 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.

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds support for image classification in DOCX and PPTX files by introducing a new EnrichDocPipeline. It also adds functionality to filter out images classified as QR codes, logos, or icons. The changes look good overall. I've provided a couple of suggestions to improve code maintainability by reducing duplication and using more appropriate data structures.

Comment on lines 62 to 86
word_pipeline_options = DocPipelineOptions()
word_pipeline_options.do_picture_classification = True
word_pipeline_options.do_code_enrichment = False
word_pipeline_options.do_formula_enrichment = False
word_pipeline_options.accelerator_options = accelerator_options # type: ignore

ppt_pipeline_options = DocPipelineOptions()
ppt_pipeline_options.do_picture_classification = True
ppt_pipeline_options.do_code_enrichment = False
ppt_pipeline_options.do_formula_enrichment = False
ppt_pipeline_options.accelerator_options = accelerator_options # type: ignore

self._converter = DocumentConverter(
format_options={
InputFormat.PDF:
PdfFormatOption(pipeline_options=pdf_pipeline_options)
PdfFormatOption(pipeline_options=pdf_pipeline_options),
InputFormat.DOCX:
WordFormatOption(
pipeline_cls=EnrichDocPipeline,
pipeline_options=word_pipeline_options),
InputFormat.PPTX:
PowerpointFormatOption(
pipeline_cls=EnrichDocPipeline,
pipeline_options=ppt_pipeline_options)
})

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The initialization of word_pipeline_options and ppt_pipeline_options is duplicated. You can create a single doc_pipeline_options object and reuse it for both DOCX and PPTX formats to improve maintainability and reduce code duplication.

        doc_pipeline_options = DocPipelineOptions()
        doc_pipeline_options.do_picture_classification = True
        doc_pipeline_options.do_code_enrichment = False
        doc_pipeline_options.do_formula_enrichment = False
        doc_pipeline_options.accelerator_options = accelerator_options  # type: ignore

        self._converter = DocumentConverter(
            format_options={
                InputFormat.PDF:
                PdfFormatOption(pipeline_options=pdf_pipeline_options),
                InputFormat.DOCX:
                WordFormatOption(
                    pipeline_cls=EnrichDocPipeline,
                    pipeline_options=doc_pipeline_options),
                InputFormat.PPTX:
                PowerpointFormatOption(
                    pipeline_cls=EnrichDocPipeline,
                    pipeline_options=doc_pipeline_options)
            })

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

Comment on lines 30 to 32
if pic_class is not None and pic_class.lower() in [
'qr_code', 'logo', 'icon'
]:

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Using a set for membership testing is more efficient than a list. Also, these magic strings should be defined as a constant at the class level for better maintainability, e.g., FILTERED_IMAGE_LABELS = {'qr_code', 'logo', 'icon'}.

                if pic_class is not None and pic_class.lower() in {'qr_code', 'logo', 'icon'}:

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

@alcholiclg alcholiclg changed the title Feat/image filter [WIP]Feat/image filter Sep 22, 2025
@alcholiclg alcholiclg changed the title [WIP]Feat/image filter [WIP]feature: image filter Sep 22, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant