Integrate Language Model for chat functionality#2
Conversation
CodeRifle
commented
Jun 22, 2025
CodeRifle
commented
- Modified script.js to use LanguageModel.create() and session.prompt() for chat responses.
- Removed hardcoded responses.
- Added a mock LanguageModel object in index.html for testing purposes, to be replaced with the actual SDK.
- Implemented basic error handling for LLM session initialization and prompting.
- Modified script.js to use LanguageModel.create() and session.prompt() for chat responses. - Removed hardcoded responses. - Added a mock LanguageModel object in index.html for testing purposes, to be replaced with the actual SDK. - Implemented basic error handling for LLM session initialization and prompting.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @CodeRifle, 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 significantly upgrades the chat functionality by transitioning from static, hardcoded responses to dynamic, AI-generated replies using a Language Model. It sets up the necessary asynchronous communication with the LLM, includes a convenient in-browser mock for development, and incorporates error handling to ensure a more robust user experience.
Highlights
- Language Model Integration: The chat functionality now uses an external Language Model (LLM) via
LanguageModel.create()andsession.prompt()for generating responses, replacing previous static replies. - Hardcoded Response Removal: The
responsesobject containing predefined answers has been removed fromscript.js, making the chat dynamic. - Mock LLM for Development: A mock
LanguageModelobject has been added directly intoindex.html. This allows for local development and testing of the LLM integration without requiring the actual SDK to be present. - Robust Error Handling: Basic error handling has been implemented for both the initialization of the LLM session and during the prompting process, providing user feedback in case of issues.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| 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 issue 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 is currently in preview and 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 to provide feedback.
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
-
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. ↩
There was a problem hiding this comment.
Code Review
The pull request integrates a language model for chat functionality, replacing hardcoded responses. A mock object is used for local development. The review suggests separating the mock implementation, removing dead code, refining error handling, and reordering operations to improve code quality and user experience.
| <script type="module"> | ||
| // This is a placeholder. The actual LanguageModel library (e.g., from a CDN) | ||
| // would make `LanguageModel` available globally or as a module. | ||
| // For demonstration, we'll mock a simple version if it's not already defined. | ||
| if (typeof window.LanguageModel === 'undefined') { | ||
| console.log("Mocking LanguageModel for development purposes."); | ||
| window.LanguageModel = { | ||
| create: async () => { | ||
| console.log("Mock LanguageModel.create() called"); | ||
| return { | ||
| prompt: async (message) => { | ||
| console.log(`Mock session.prompt() called with: "${message}"`); | ||
| await new Promise(resolve => setTimeout(resolve, 1000)); // Simulate network delay | ||
| if (message.toLowerCase().includes("error test")) { | ||
| throw new Error("Simulated LLM error."); | ||
| } | ||
| return `Mock response to: "${message}"`; | ||
| } | ||
| }; | ||
| } | ||
| }; | ||
| } | ||
| </script> |
There was a problem hiding this comment.
Consider moving the mock LanguageModel implementation to a separate file (e.g., mock-llm.js) and including it only during development. This prevents shipping development-only code to production.
| // const responses = { | ||
| // 'who is rishabh gupta?': `Rishabh Gupta is an accomplished AI Engineer with expertise in developing and implementing cutting-edge artificial intelligence solutions. He has a strong background in machine learning, deep learning, and natural language processing, with a proven track record of delivering innovative AI-powered applications.`, | ||
| // | ||
| // 'what are his skills?': `Rishabh's technical skills include: | ||
| // • Deep Learning & Machine Learning (PyTorch, TensorFlow) | ||
| // • Natural Language Processing | ||
| // • Computer Vision | ||
| // • Large Language Models (LLMs) | ||
| // • Python, JavaScript, and various AI/ML frameworks | ||
| // • Cloud platforms (AWS, GCP)`, | ||
| // | ||
| // 'show me his projects': `Here are some of Rishabh's notable projects: | ||
| // 1. Developed an advanced NLP system for automated customer support | ||
| // 2. Created a computer vision solution for real-time object detection | ||
| // 3. Implemented a recommendation engine using deep learning | ||
| // 4. Built scalable ML pipelines for production environments`, | ||
| // | ||
| // 'default': `I'm not sure about that specific query, but I'd be happy to tell you about Rishabh's experience, skills, or projects. Feel free to ask about those topics!` | ||
| // }; |
There was a problem hiding this comment.
Remove the commented-out responses object to improve code clarity. Version control can be used to retrieve old code if needed.
| async function initializeSession() { | ||
| try { | ||
| // Assuming LanguageModel is available globally e.g. via a <script> tag | ||
| if (window.LanguageModel && typeof window.LanguageModel.create === 'function') { | ||
| modelSession = await window.LanguageModel.create(); | ||
| console.log("LanguageModel session initialized."); | ||
| } else { | ||
| console.error("LanguageModel library not found or 'create' method is missing."); | ||
| addMessage("Error: Chat functionality is currently unavailable. LanguageModel library not found.", false); | ||
| typingIndicator.style.display = 'none'; | ||
| } | ||
| } catch (error) { | ||
| console.error("Error initializing LanguageModel session:", error); | ||
| addMessage("Error: Could not initialize the chat assistant. Please try again later.", false); | ||
| typingIndicator.style.display = 'none'; | ||
| } | ||
| } |
There was a problem hiding this comment.
Simplify error handling in initializeSession by throwing an error when LanguageModel is not found. This consolidates error handling and ensures a consistent user experience.
async function initializeSession() {
try {
if (!window.LanguageModel || typeof window.LanguageModel.create !== 'function') {
throw new Error("LanguageModel library not found or 'create' method is missing.");
}
modelSession = await window.LanguageModel.create();
console.log("LanguageModel session initialized.");
} catch (error) {
console.error("Error initializing LanguageModel session:", error);
addMessage("Error: Could not initialize the chat assistant. Please try again later.", false);
typingIndicator.style.display = 'none';
}
}| // async function getResponse(message) { | ||
| // const normalizedMessage = message.toLowerCase().trim(); | ||
| // await simulateTyping(); | ||
| // typingIndicator.style.display = 'none'; | ||
| // return responses[normalizedMessage] || responses['default']; | ||
| // } |
There was a problem hiding this comment.
Remove the commented-out getResponse function as it's no longer used.
| async function sendMessage() { | ||
| const message = userInput.value.trim(); | ||
| if (!message) return; | ||
|
|
||
| addMessage(message, true); | ||
| userInput.value = ''; | ||
| simulateTyping(); // Show typing indicator | ||
|
|
||
| const response = await getResponse(message); | ||
| addMessage(response); | ||
| if (!modelSession) { | ||
| addMessage("Chat assistant is not available. Session not initialized.", false); | ||
| typingIndicator.style.display = 'none'; | ||
| return; | ||
| } | ||
|
|
||
| try { | ||
| const result = await modelSession.prompt(message); | ||
| addMessage(result); | ||
| } catch (error) { | ||
| console.error("Error getting response from LanguageModel:", error); | ||
| addMessage("Sorry, I encountered an error trying to respond. Please try again.", false); | ||
| } finally { | ||
| typingIndicator.style.display = 'none'; // Hide typing indicator | ||
| } | ||
| } |
There was a problem hiding this comment.
Check for modelSession availability before showing the typing indicator in sendMessage to prevent UI flicker if the session hasn't initialized.
async function sendMessage() {
const message = userInput.value.trim();
if (!message) return;
addMessage(message, true);
userInput.value = '';
if (!modelSession) {
addMessage("Chat assistant is currently unavailable. Please try again later.", false);
typingIndicator.style.display = 'none';
return;
}
simulateTyping();
try {
const result = await modelSession.prompt(message);
addMessage(result);
} catch (error) {
console.error("Error getting response from LanguageModel:", error);
addMessage("Sorry, I encountered an error trying to respond. Please try again.", false);
} finally {
typingIndicator.style.display = 'none';
}
}1 participant
