fix: rags of 5 metrics

[pekopoke]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @pekopoke, 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 configurability and code structure of the RAG (Retrieval Augmented Generation) metrics evaluation system. It introduces the ability to dynamically provide OpenAI API credentials for embedding models, making the system more adaptable. Additionally, it refactors several prompt-related methods into static methods for better code organization and clarifies JSON formatting within prompts. These changes collectively improve the maintainability and flexibility of the RAG evaluation components.

Highlights

• Configurable OpenAI API Credentials: The EmbeddingModel now supports dynamic configuration of OpenAI API keys and base URLs, moving away from hardcoded values and improving flexibility for different environments.
• Refactoring to Static Methods: Several prompt generation methods across various RAG metric modules (llm_rag_context_recall, llm_rag_context_relevancy, llm_rag_faithfulness) have been converted to static methods, indicating they do not rely on instance or class state.
• JSON Prompt Formatting Adjustment: JSON output formats within prompts in llm_rag_faithfulness.py were updated to use double curly braces ({{...}}), likely to ensure proper escaping and compatibility with templating engines.
• Comment Clarifications: Minor comment updates were made across multiple files to clarify the default threshold value for metric evaluation, changing '满分10分' (out of 10 points) to simply '默认阈值为5' (default threshold is 5).

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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. ↩

[gemini-code-assist]

Code Review

This pull request introduces several fixes and improvements across five RAG metric evaluation modules. Key changes include correctly handling API credentials for OpenAI embedding models by passing them as parameters instead of using hardcoded values, fixing f-string formatting issues in prompts by escaping curly braces, and marking helper methods as @staticmethod for better code structure. The changes are solid and enhance the code's robustness and maintainability. I have one suggestion in llm_rag_answer_relevancy.py to simplify a conditional block for improved readability.

[gemini-code-assist]

The if/elif/else structure for validating key and api_url is a bit complex. You can simplify this by using two separate if statements to check for each required parameter. This makes the validation logic more direct and easier to read.

            # 从配置中获取API密钥和base_url
            if not cls.dynamic_config.key:
                raise ValueError("key cannot be empty in llm config.")
            if not cls.dynamic_config.api_url:
                raise ValueError("api_url cannot be empty in llm config.")
            api_key = cls.dynamic_config.key
            base_url = cls.dynamic_config.api_url