Adding support for image and table annotation for DocAI #13329
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
There was a problem hiding this comment.
Hello @bibliofilo, 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!
Summary of Changes
This pull request adds support for image and table annotation to the DocAI Layout Parser. The changes include modifications to documentai/snippets/handle_response_sample.py to include example code for enabling image and table annotation, updates to documentai/snippets/handle_response_sample.py to add parameters for enabling image and table annotation, and updates to documentai/snippets/handle_response_sample_test.py to enable image and table annotation in the test case.
Highlights
- Feature: Adds support for image annotation in DocAI Layout Parser.
- Feature: Adds support for table annotation in DocAI Layout Parser.
- Documentation: Updates documentation and code to match and support the new offering.
Changelog
- documentai/snippets/handle_response_sample.py
- Added example code for enabling image and table annotation (lines 35-36).
- Added parameters
enable_image_annotationandenable_table_annotationto theprocess_document_layout_samplefunction (lines 467-468). - Modified
process_document_layout_sampleto includeenable_image_annotationandenable_table_annotationinProcessOptions(lines 476-477).
- documentai/snippets/handle_response_sample_test.py
- Enabled image and table annotation in the
test_process_document_layouttest case (lines 232-233).
- Enabled image and table annotation in the
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.
A parser's task, to dissect,
Layouts complex, to inspect.
Images and tables,
Now part of the fables,
Annotations, we now expect.
Footnotes
-
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. ↩
There was a problem hiding this comment.
Code Review
The pull request introduces support for image and table annotation in DocAI Layout Parser. The changes include updating documentation and code to support this feature. Overall, the changes seem reasonable, but there are a few areas that could be improved for clarity and consistency.
Summary of Findings
- Inconsistent use of boolean values: The code uses string literals for boolean values in the comments but uses actual boolean values in the function definition. This inconsistency can be confusing.
- Missing documentation for new parameters: The new parameters
enable_image_annotationandenable_table_annotationin theprocess_document_layout_samplefunction lack docstrings, which should be added to improve readability and maintainability.
Merge Readiness
The pull request is almost ready for merging. However, the inconsistencies in boolean value usage and the missing documentation for the new parameters should be addressed before merging. Once these issues are resolved, the code should be good to go. I am unable to directly approve the pull request, and users should have others review and approve this code before merging.
Co-authored-by: Holt Skinner <13262395+holtskinner@users.noreply.github.com>
Co-authored-by: Holt Skinner <13262395+holtskinner@users.noreply.github.com>
Co-authored-by: Holt Skinner <13262395+holtskinner@users.noreply.github.com>
Co-authored-by: Holt Skinner <13262395+holtskinner@users.noreply.github.com>
Description
Image Annotation is GA in DocAI Layout Parser, these changes were requested internally to update documentation and available code to match and support the offering.
Bugs: b/413675713
Fixes #
Note: Before submitting a pull request, please open an issue for discussion if you are not associated with Google.
Checklist
nox -s py-3.9(see Test Environment Setup)nox -s lint(see Test Environment Setup)