feat(langchain4j): add UsageMetadata extraction from TokenCountEstimator or TokenUsage

[rhuan080]

In this commit, I added support for LlmResponse.usageMetadata to retrieve token usage either from a provided TokenCountEstimator or from LangChain4j’s built-in tokenUsage.

This enables usage like:

AnthropicChatModel anthropicModel = AnthropicChatModel.builder()
                        .apiKey(apiKey)
                        .modelName(model)
                        .build();

TokenCountEstimator tokenCountEstimator = AnthropicTokenCountEstimator.builder()
                        .modelName(model)
                        .apiKey(apiKey)
                        .build();
BaseLlm llm = LangChain4j(anthropicModel, tokenCountEstimator);

If no TokenCountEstimator is provided, chatResponse.tokenUsage() becomes the fallback source for usage metadata.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Summary of Changes

Hello @rhuan080, 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 significant enhancement to the LangChain4j integration by enabling the extraction and reporting of token usage metadata. This feature provides greater transparency into the cost and resource consumption of LLM interactions, allowing developers to better monitor and optimize their applications. The implementation prioritizes user-provided token estimators for accuracy, while gracefully falling back to available model-provided usage data.

Highlights

• Enhanced Token Usage Metadata: Implemented support for extracting UsageMetadata from LlmResponse to provide detailed token consumption information.
• Flexible Token Counting: Allows users to provide a custom TokenCountEstimator for precise token counting, or automatically falls back to LangChain4j's built-in TokenUsage if available.
• Constructor Overloads: Added new constructors to the LangChain4j class to facilitate the injection of a TokenCountEstimator.
• Robust Testing: Included comprehensive unit tests to ensure the correct behavior of token usage estimation, including fallback and priority scenarios.

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 support for extracting token usage metadata, prioritizing a provided TokenCountEstimator and falling back to LangChain4j's built-in TokenUsage. The implementation is logical and is accompanied by a good set of unit tests covering the new functionality.

My review includes two main points for improvement:

1. Refactoring Constructors: The number of constructors has doubled, leading to boilerplate. I've suggested considering a builder pattern for better maintainability.
2. Exception Handling: There's a try-catch block that silently swallows exceptions during token estimation. I've recommended adding logging to aid in debugging potential issues.

Overall, this is a valuable feature addition. Addressing the feedback will improve the robustness and maintainability of the code.