chore: update example with new apis.

[k82cn]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @k82cn, 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 modernizing and enhancing several example applications within the repository. Key changes include updating API definitions to leverage Python's dataclasses for improved clarity and reduced boilerplate, streamlining the handling of flamepy task outputs by removing manual deserialization steps, and significantly improving the Langchain and OpenAI agent examples. The OpenAI agent now showcases advanced tool-use capabilities, while the Langchain agent demonstrates a more flexible approach to system prompt integration. These changes aim to make the examples more robust, easier to understand, and aligned with current best practices for interacting with the flamepy framework and external LLM agents.

Highlights

• API Definition Refactor: API request and response classes across various examples (Langchain, Crawler) have been modernized to utilize Python's dataclasses for clearer and more concise definitions, replacing the previous inheritance from flamepy.Request and flamepy.Response.
• Automated Output Deserialization: The examples now benefit from simplified result handling as explicit from_json calls for flamepy task outputs have been removed, indicating that the framework now handles deserialization automatically or returns objects directly.
• Langchain Agent Context Handling: The Langchain agent example (agent.py) has been updated to dynamically incorporate system prompts retrieved from the flamepy context directly into the agent's message history, enhancing flexibility in agent configuration.
• OpenAI Agent Tool Integration: The OpenAI agent example has been significantly enhanced to demonstrate tool-use capabilities, introducing a fetch_weather tool and updating the client's system prompt to guide the agent in leveraging this new functionality.
• Crawler API File Renamed: The api.py file within the crawler example has been renamed to apis.py to better align with the new dataclass-based API definitions and improve consistency.

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 updates the example applications to use new flamepy APIs. The changes primarily involve replacing flamepy.Request and flamepy.Response with standard Python dataclasses, which simplifies the data model definitions. The client code is updated accordingly to handle direct object outputs instead of JSON deserialization. Additionally, the langchain agent example is updated to reflect a new way of handling context, and the OpenAI agent example is enhanced with a function tool. The changes are consistent and improve the examples. I've found one minor issue in the client logic for displaying session history.