feat(integration): add LangSmith integration cookbook and documentation

[ployts]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @ployts, 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 introduces a new integration with LangSmith, a platform for LLM application development and monitoring. It provides both a practical cookbook with code examples and detailed documentation to guide users on how to leverage OpenJudge's grading capabilities within the LangSmith evaluation ecosystem. This enhancement allows for seamless evaluation of LLM applications, supporting both individual graders and batch processing via the GradingRunner, thereby streamlining the assessment of model performance.

Highlights

• LangSmith Integration Cookbook: A new cookbook file cookbooks/integrations/langsmith.py has been added, demonstrating how to integrate OpenJudge with LangSmith. It covers both individual grader integration and batch evaluation using the GradingRunner.
• LangSmith Integration Documentation: Comprehensive documentation docs/integrations/langsmith.md has been added, guiding users through setting up, defining applications, creating datasets, and implementing OpenJudge graders as LangSmith evaluators.
• Extensibility for Compute Functions: Several compute_ functions within openjudge/graders/text/_utils/compute.py have been updated to accept **kwargs: Any. This change enhances the flexibility and future extensibility of these text metric computation functions.
• Import Path Correction: An import path in cookbooks/grader_validation/accuracy.py was corrected, changing tutorials.grader_validation.base to cookbooks.grader_validation.base to reflect the correct module location.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 a valuable cookbook and documentation for LangSmith integration. The overall structure is good, but I've identified several issues that need attention. The Python cookbook script contains a critical bug related to creating LangSmith examples that will cause a runtime error, along with incorrect docstrings and some code duplication. The accompanying markdown documentation has a few errors in its code snippets and a broken link. I've provided specific comments and code suggestions to address these points and improve the quality and correctness of the new integration guide.