Skip to main content

​
Overview

The AI Chatbot endpoint provides students with a personalized learning companion powered by Groq AI. The assistant leverages the student’s course enrollment, progress data, and quiz performance to provide contextual guidance and study recommendations.

​
POST /api/user/ai-chat

Send a message to the AI assistant and receive a personalized response based on your learning context.

​
Authentication

Requires JWT authentication token in the Authorization header.

​
Request Body

​
content
string
required
The user’s message to the AI assistant. Must be a non-empty string.
​
sessionId
string
Optional session ID to continue an existing conversation. If not provided, a new session will be created.

​
Request Example

{
  "content": "What should I focus on studying next?",
  "sessionId": "a3f2c1b0-4e5d-6f7g-8h9i-0j1k2l3m4n5o"
}

​
Response

​
success
boolean
Indicates whether the request was successful.
​
activeSessionId
string
The session ID for this conversation. Use this to continue the conversation in subsequent requests.
​
response
string
The AI assistant’s response to the user’s message.
​
conversationHistory
array
Complete conversation history including all user and assistant messages.

​
Response Example

{
  "success": true,
  "activeSessionId": "a3f2c1b0-4e5d-6f7g-8h9i-0j1k2l3m4n5o",
  "response": "Based on your recent quiz results, I recommend focusing on the authentication module in your Web Development course. You scored 60% on that chapter, which indicates it needs review. Specifically, work on understanding JWT tokens and OAuth flows.",
  "conversationHistory": [
    {
      "role": "user",
      "content": "What should I focus on studying next?"
    },
    {
      "role": "assistant",
      "content": "Based on your recent quiz results, I recommend focusing on the authentication module in your Web Development course. You scored 60% on that chapter, which indicates it needs review. Specifically, work on understanding JWT tokens and OAuth flows."
    }
  ]
}

​
Error Responses

{
  "success": false,
  "message": "Missing message"
}

​
How It Works

​
Personalized Context

The AI assistant builds a comprehensive learning context for each user that includes:
  • Student Profile: Name and enrolled courses
  • Course Progress: Completion percentage and lecture tracking for each course
  • Quiz Performance: Recent quiz results with scores, performance levels (Needs Review, On Track, Mastered), and AI-generated study recommendations
  • Learning Patterns: Analysis of strengths and areas needing improvement

​
System Prompt

The assistant is configured with the following capabilities:
  • Help with course content and technical learning questions
  • Provide study guidance based on progress data
  • Offer personalized recommendations using quiz performance
  • Proactively suggest review for topics marked “Needs Review”
  • Maintain a concise, encouraging, and educational tone

​
Groq AI Integration

The chatbot uses Groq’s high-performance AI inference with the following configuration:
  • Model: openai/gpt-oss-120b - A 120B parameter open-source model
  • Temperature: 0.7 - Balanced between creativity and consistency
  • Max Tokens: 5000 - Supports detailed explanations
  • Top P: 1.0 - Full probability mass for response generation
  • Streaming: Disabled - Returns complete responses

​
Context Management

  • Conversation history is limited to the last 20 messages for optimal performance
  • System prompt is regenerated on each request to ensure context freshness
  • User data is fetched in real-time to reflect current progress
  • Session IDs are auto-generated using UUID v4

​
Data Sources

The assistant pulls data from:
  • User model: Name, enrolled courses
  • CourseProgress model: Lecture completion tracking
  • QuizResult model: Recent quiz scores and AI recommendations
  • Course model: Course titles, chapters, and content structure

​
Implementation Details

​
Request Validation

Requests are validated using Zod schema: 
const AiChatBodySchema = z.object({
  content: z.string().trim().min(1),
  sessionId: z.string().optional(),
})

​
Session Management

  • Sessions are stored in MongoDB using the ChatSession model
  • Each session is tied to a specific user (userId ensures ownership)
  • New sessions are created automatically with UUID v4 identifiers
  • Existing sessions are retrieved using both sessionId and userId for security

​
Context Building

The buildUserContext() function aggregates:
  1. User’s enrolled courses with populated course details
  2. Progress records for all enrolled courses
  3. Recent quiz results (limited to last 20)
  4. Calculated completion percentages
  5. Chapter and lecture information
  6. Latest AI study recommendations from quiz results

​
Best Practices

  1. Session Continuity: Always include the activeSessionId from previous responses to maintain conversation context
  2. Specific Questions: The AI performs best with specific questions about courses, topics, or study strategies
  3. Learning Context: The assistant’s recommendations improve as students complete more quizzes and courses
  4. Fresh Data: User context is rebuilt on every request to ensure recommendations reflect current progress

​
Rate Limiting

Consider implementing rate limiting on the client side to prevent excessive API calls to Groq’s service.