Chatbot Logic

Overview

A specialized RAG (Retrieval Augmented Generation) chatbot that helps users learn from the textbook content.

Backend

• Route: app/api/chat/route.ts
• Logic:
  1. Receives query and history.
  2. Embeds query using Gemini or OpenAI embedding model.
  3. Searches Qdrant (vector DB) for relevant textbook chunks.
  4. Constructs context from matches.
  5. Generates response using Gemini Flash/Pro.

Vector Search (Qdrant)

We use Qdrant for storing embeddings of the textbook.

• Collection: textbook_chunks (or similar).
• Fields: text, source, chunk_id.