docs: add Langfuse integration documentation

[helloml0326]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @helloml0326, 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 new documentation that serves as a detailed tutorial for integrating OpenJudge with Langfuse. It aims to empower users to set up robust external evaluation pipelines for their LLM applications, offering enhanced flexibility and a wide array of grading dimensions. The guide covers the entire workflow from data retrieval to result submission, ensuring a seamless experience for automated quality assessment.

Highlights

• New Langfuse Integration Documentation: A comprehensive guide has been added detailing how to build external evaluation pipelines for Langfuse using OpenJudge, leveraging its 50+ built-in graders for LLM application quality evaluation.
• Step-by-Step Integration Workflow: The documentation outlines a clear three-step process: fetching traces from Langfuse, running evaluations with OpenJudge (including single grader and batch processing options), and sending the evaluation scores back to Langfuse.
• Prerequisites and Code Examples: The new document includes instructions for installing dependencies, configuring environment variables, initializing clients, and provides Python code snippets for creating test traces, fetching data, and executing evaluations.
• Navigation Update: The mkdocs.yml file has been updated to include a new 'Integrations' section in the navigation, under which the new Langfuse documentation is now accessible.

🧠 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 adds comprehensive documentation for integrating OpenJudge with Langfuse. The new documentation page is well-structured and provides detailed code examples for fetching traces, running evaluations, and sending scores back to Langfuse. I've identified a couple of issues in the code examples that would prevent them from running correctly or cause confusion, along with suggestions for fixes. Overall, this is a great addition to the documentation.

[gemini-code-assist]

The fetch_recent_traces function is missing the logic to extract the expected output from the trace metadata. This is inconsistent with the fetch_traces_for_evaluation function and might cause issues later in the batch_evaluate_traces example, which relies on the expected field. To improve consistency and ensure the example works as intended, I suggest adding this logic.

Suggested change

	for trace in response.data:
	if trace.input and trace.output:
	result.append({
	"id": trace.id,
	"input": trace.input,
	"output": trace.output,
	"metadata": trace.metadata or {},
	})
	for trace in response.data:
	if trace.input and trace.output:
	trace_dict = {
	"id": trace.id,
	"input": trace.input,
	"output": trace.output,
	"metadata": trace.metadata or {},
	}
	# Add expected output if available in metadata
	if trace.metadata and "expected" in trace.metadata:
	trace_dict["expected"] = trace.metadata["expected"]
	result.append(trace_dict)

[gemini-code-assist]

The SimilarityGrader is imported but not used in the batch_evaluate_traces example. To keep the code clean and avoid confusion, it's best to remove unused imports.