chore(ava): add llm validate for extract method in test case, support invoke tbox api with ci

[Yzing]

PR includes

• fixed #0
• add / modify test cases
• documents, demos

[gemini-code-assist]

Summary of Changes

Hello @Yzing, 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 significantly upgrades the data extraction and analysis capabilities by integrating Large Language Model (LLM) validation directly into the testing framework. It introduces a new mock for the extract method that can interact with an internal LLM API, enabling more sophisticated validation of data parsing and feature extraction. Concurrently, the underlying type analysis logic has been refined for improved accuracy and consistency across various data types, ensuring a more robust data understanding pipeline.

Highlights

• LLM Validation for Extract Method: Introduced a mechanism to validate the extract method using an LLM (Large Language Model) within test cases, enabling more sophisticated data parsing and feature extraction validation.
• CI Integration for LLM API: Configured the test environment to invoke an internal Tbox API (LLM service) during Continuous Integration, allowing for real-time LLM-powered testing.
• Refined Type Analysis Logic: Updated the analyzeField and analyzeType functions to improve type recommendation logic, especially for number and date types, and adjusted isOrdinal and isNominal checks for greater accuracy.
• Enhanced Test Suite and Setup: Modified existing test cases and added new setup for Jest, including environment variable loading via dotenv and increased test timeouts, to support the new LLM-based testing infrastructure.

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 refactors and expands the test suite for the extract functionality, notably by integrating LLM-based validation through a CI-invoked API. Key changes include unifying integer and float types into a more general number type, which is consistently applied across various tests. The setup is also improved by using dotenv for managing test environment variables and refining the Jest configuration.

My review highlights a few critical points. Firstly, some tests have been modified to align with what appears to be buggy behavior in utility functions, rather than asserting the correct logic. This is a significant concern as it undermines the reliability of the tests. Secondly, I've identified some leftover debugging code and a type inconsistency in a new mock file. Addressing these issues will improve code quality and ensure the tests accurately validate the intended functionality.