Projects / Computer Science / Computer Science project 46

College FAQ Chatbot Using Retrieval-Augmented Generation (RAG)

Approx. component budget: Rs. 0 - 2,000

Objective

Give correct, source-backed answers and say 'I do not know' when the documents do not contain the answer.

What you will build

A chatbot that answers student questions about rules, fees, timetables and forms using the college's own documents, and shows the source of each answer.

Results you can expect

• Answer accuracy on 50 test questions judged by humans
• Rate of wrong confident answers
• Retrieval hit rate
• Response time
• And a comparison with a chatbot that has no document access

What you will learn

Embeddings, vector search, chunking, prompt design, hallucination control, and evaluating AI answers.

Tools and notes

Python, LangChain or LlamaIndex, FAISS or Chroma, sentence-transformers, a free or open-source language model, Streamlit. Use only public college documents.

Resume points from this project

• Built and tested College FAQ Chatbot Using Retrieval-Augmented Generation (RAG); objective: give correct, source-backed answers and say 'I do not know' when the documents do not contain the answer.
• Measured and analysed answer accuracy on 50 test questions judged by humans and rate of wrong confident answers; wrote the report and presented the results in a viva. Add your own numbers: [x].

Replace [x] with your own measured results. Write only what you really did.

More computer science projects

Back to all projects