feat: add documentation for deploying and testing LLM models with Ope… - #70
Conversation
…nAI API integration.
Summary of ChangesHello @KUASWoodyLIN, 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 for deploying and testing Large Language Models (LLMs) with OpenAI API integration. A key part of this update involves adjusting an example's API endpoint to align with the correct method for interacting with the OpenAI service, ensuring the provided code examples are accurate and functional for users. Highlights
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
|
There was a problem hiding this comment.
Pull request overview
This pull request corrects the API endpoint in the LLM model deployment documentation to align with the OpenAI completions API format. The documentation describes deploying and testing LLM models in an OtterScale cluster using Python.
Changes:
- Updated the API endpoint from
/v1/chatto/v1/completionsto match the payload structure that usespromptinstead ofmessages
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![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 updates the documentation for deploying and testing LLM models by correcting an API endpoint in the Python example code. The change from /v1/chat to /v1/completions is correct and aligns the example with the expected payload. My review includes a suggestion to further improve the robustness of the example code by adding a request timeout and ensuring proper URL construction, which will help users who copy and paste this code avoid potential issues.
| response = requests.post( | ||
| f"{SERVICE_URL}/v1/chat", | ||
| f"{SERVICE_URL}/v1/completions", | ||
| headers=headers, | ||
| json=payload | ||
| ) |
There was a problem hiding this comment.
The requests.post call can be made more robust. It's missing a timeout, which can cause the script to hang indefinitely if the remote server is unresponsive. Additionally, concatenating URL parts with an f-string can be fragile if SERVICE_URL contains a trailing slash, leading to double slashes in the URL.
I'd recommend adding a timeout and also stripping any trailing slash from the service URL to make the code more resilient.
response = requests.post(
f"{SERVICE_URL.rstrip('/')}/v1/completions",
headers=headers,
json=payload,
timeout=60 # Add a timeout to prevent requests from hanging
)
…nAI API integration.