Centralized manage prompt

[qinantong]

Hello, I have recently been using your project and making some modifications as required by the company. I noticed that there are sometimes large blocks of prompts in the code, which may affect code readability. Therefore, I am submitting this MR. In this MR, I have extracted the large blocks of prompts from the backend and placed them in the prompts.py file for centralized management.

[gemini-code-assist]

Summary of Changes

Hello @qinantong, 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!

The primary goal of this pull request is to improve code readability and maintainability by centralizing the management of large prompt blocks. I've extracted various prompt definitions from existing backend files and consolidated them into a new dedicated api/prompts.py file. This change ensures that all prompt templates are managed in one location, making them easier to find, update, and review.

Highlights

• Prompt Centralization: I've created a new file, api/prompts.py, to store all large prompt strings previously embedded directly within other backend files.
• Refactoring api/rag.py: The system_prompt and RAG_TEMPLATE definitions have been removed from api/rag.py and are now imported from the new api/prompts.py module.
• Refactoring api/simple_chat.py: All DEEP_RESEARCH and SIMPLE_CHAT related prompt strings have been moved out of api/simple_chat.py and are now imported from api/prompts.py, replacing the inline string definitions with references to the centralized variables.

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 or fill out our survey 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 does a good job of centralizing prompts into a dedicated api/prompts.py file, which improves code organization and readability. The changes in api/rag.py and api/simple_chat.py correctly adopt these new constants. However, I've found a critical issue in api/prompts.py where the placeholder syntax for several prompts is incorrect for their usage with str.format(), which will cause issues at runtime. I've also included a few medium-severity suggestions to improve code style and maintainability, such as fixing a misplaced import and adhering to file formatting standards.