Conversation
Signed-off-by: Lukáš Janeček <xjacka@gmail.com>
Summary of ChangesHello @xjacka, 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 documentation example that illustrates the process of integrating a GPT-Researcher agent, developed using LangGraph, into the Agent Stack. The primary goal is to provide clear instructions for developers to connect external agents with the Agent Stack ecosystem, showcasing how to utilize the Highlights
🧠 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. Changelog
Activity
Using Gemini Code AssistThe 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
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 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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds a new documentation page with an example of integrating a GPT-Researcher agent with Agent Stack. The documentation is a good addition, but it has several issues that would prevent a user from successfully following the instructions. I've identified typos in commands and filenames, multiple issues in the Python code snippets (including missing imports, use of undefined functions, and incorrect indentation), and a misleading title for the document. My review provides specific feedback and suggestions to fix these problems and make the tutorial runnable and clear for users.
Signed-off-by: Lukáš Janeček <xjacka@gmail.com>
| with the following: | ||
|
|
||
| ```python | ||
| # type: ignore |
There was a problem hiding this comment.
are these # type: ignore needed for the tutorial?
There was a problem hiding this comment.
Yes, because the code is incomplete but it's being reviewed.
| @server.agent( | ||
| name="GPT Researcher", | ||
| ) | ||
| async def my_wrapped_agent( |
There was a problem hiding this comment.
my_agentstack_gpt_researcher
There was a problem hiding this comment.
We use human-readable names.
| server = Server() | ||
|
|
||
| @server.agent( | ||
| name="GPT Researcher", |
There was a problem hiding this comment.
- what about non-text inputs/outputs?
- what about adding some descriptions etc?
| os.environ["OPENAI_API_KEY"] = llm_config.api_key | ||
| os.environ["OPENAI_API_BASE"] = llm_config.api_base | ||
| os.environ["FAST_LLM"] = model | ||
| os.environ["SMART_LLM"] = model | ||
| os.environ["STRATEGIC_LLM"] = model |
There was a problem hiding this comment.
It would be better to leverage ENVs instead of LLM Fullfilment... not sure if this is even compatible with the GPT Researcher
There was a problem hiding this comment.
Is there any way to set the model class from LangChain directly?
2 participants
Summary
Linked Issues
Documentation
If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.