Update doc research readme #710
Conversation
wangxingjun778
had a problem deploying
to
testci
GitHub Actions
Failure
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @wangxingjun778, 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 focuses on enhancing the clarity and detail of the documentation for the doc_research project. The updates provide more specific information about the types of input files supported and improve the readability of the quick start instructions. Additionally, the Chinese version of the README includes a clarification regarding deployment options.
Highlights
- Enhanced Feature Descriptions: The documentation now explicitly lists supported file formats (PDF, TXT, PPT, DOCX) for the "Multiple Input Types" feature, providing clearer expectations for users.
- Improved Quick Start Clarity: The quick start instructions in both English and Chinese READMEs have been updated with more descriptive comments, making it easier for users to understand how to run the application via command line or Python script.
- Deployment Option Clarification: The Chinese README now includes a clarification regarding CPU-Only support for ModelScope Studio within the "Flexible Deployment" section.
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
-
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
This pull request updates the README files for the doc research project, adding more details about supported file types and clarifying the instructions for running the application. The changes are generally improvements to the documentation.
My review focuses on ensuring the accuracy and consistency of the information added. I've pointed out a potential discrepancy in the listed supported file formats compared to the implementation, and an inconsistency between the English and Chinese READMEs regarding CPU/GPU support in ModelScope Studio. Please review these points to ensure the documentation is clear and correct for users.
|
|
||
| - 🔍 **Deep Document Research** - Support deep analysis and summarization of documents | ||
| - 📝 **Multiple Input Types** - Support multi-file uploads and URL inputs | ||
| - 📝 **Multiple Input Types** - Support multi-file uploads and URL inputs, including PDF, TXT, PPT, DOCX, etc. |
There was a problem hiding this comment.
This change adds PPT and DOCX to the list of supported input types. However, the code in ms_agent/tools/docling/doc_loader.py suggests that only PDF, HTML, and TXT files are currently supported. For instance, a TODO comment in that file says: currently only supports PDF and HTML formats.
To ensure the documentation is accurate, could you please confirm whether PPT and DOCX files are fully supported? If not, it would be best to remove them from this list to avoid user confusion.
|
|
||
| - 🔍 **文档深度研究** - 支持文档的深度分析和总结 | ||
| - 📝 **多种输入类型** - 支持多文件上传和URLs输入 | ||
| - 📝 **多种输入类型** - 支持多文件上传和URLs输入（文件格式包含PDF、TXT、PPT、DOCX等） |
There was a problem hiding this comment.
Similar to the English README.md, this change adds support for PPT and DOCX files. As mentioned in the other comment, the codebase (ms_agent/tools/docling/doc_loader.py) suggests these formats might not be supported yet. Please verify and ensure this list is accurate.
| - 📊 **多模态报告** - 支持Markdown格式的图文报告输出 | ||
| - 🚀 **精准高效** - 利用强大的LLM进行快速准确的研究，采用关键信息抽取技术进一步优化了token使用 | ||
| - ⚙️ **灵活部署** - 支持本地运行和魔搭创空间运行模式，兼容CPU和GPU环境 | ||
| - ⚙️ **灵活部署** - 支持本地运行和魔搭创空间运行模式（CPU-Only），同时也兼容GPU环境 |
There was a problem hiding this comment.
This line now specifies that ModelScope Studio runs in CPU-Only mode. However, the corresponding line in the English README.md (line 28) states it supports both CPU and GPU environments. These two files are now inconsistent.
Please verify which statement is correct and update the other README file accordingly to ensure consistency.
1 participant
No description provided.