AI-Driven RAG Chatbot: Combining Information Retrieval with Generative AI

Generative AI technologies are emerging nowadays and they transform the way of user interaction with information, and allows the systems to deliver accurate responses to the user queries. This research focuses on creating a Retrieval Augmented Generation Chatbot as an e-learning assistant where it fetches the accurate data from the pdf document that is trained on and give accurate precise responses to the user query. This e-learning assistant is created specifically for the subject of “Artificial Intelligence” to deliver the user-queries related to Artificial Intelligence. The system uses Flask for the backend and React for the frontend. PDFs are loaded, split into smaller sections, and processed using LangChain. Embeddings are generated with Google’s AI models and stored in Chroma, a vector database. When a user submits a query, the system searches for similar content and uses Google Gemini-1.5-Pro to generate a response based on the retrieved data. This ensures high accuracy by relying on specific content rather than broad AI knowledge. This solution can easily scale and is perfect for education and knowledge-based fields. It helps students, teachers, and professionals by providing fast, reliable answers, making learning more efficient and effective.