Scribd
Upload
6 views1 page

Abstract

This paper presents a Retrieval-Augmented Generation (RAG) based intelligent chatbot aimed at improving information retrieval from digital documents in educational institutions. The system utilizes document embeddings, vector-based semantic search, and large language models to provide accurate and context-aware responses, allowing users to interact with various institutional documents. Experimental results indicate that the system significantly enhances response accuracy and reduces hallucinations compared to traditional chatbots.

Uploaded by

imgrootkcots
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
6 views1 page

Abstract

This paper presents a Retrieval-Augmented Generation (RAG) based intelligent chatbot aimed at improving information retrieval from digital documents in educational institutions. The system utilizes document embeddings, vector-based semantic search, and large language models to provide accurate and context-aware responses, allowing users to interact with various institutional documents. Experimental results indicate that the system significantly enhances response accuracy and reduces hallucinations compared to traditional chatbots.

Uploaded by

imgrootkcots
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

ABSTRACT:

With the rapid growth of digital documents in educational


institutions, retrieving accurate information efficiently has
become a significant challenge. Traditional chatbots and
keyword-based search systems often fail to provide context-
aware and precise responses, especially when dealing with
large volumes of unstructured data. To address this issue, this
paper proposes a Retrieval-Augmented Generation (RAG)
based intelligent chatbot designed specifically for college
document querying.
The proposed system integrates document embeddings,
vector-based semantic search, and large language models to
generate accurate, context-aware responses grounded in
institutional documents. Users can upload documents such as
syllabi, notices, and academic regulations, and interact with
the system through a conversational interface. The backend is
developed using FastAPI, with MongoDB for data storage,
while the frontend is implemented using React.
Experimental results demonstrate that the proposed system
significantly reduces hallucinations compared to traditional
LLM-based chatbots and improves response accuracy. The
system is scalable, secure, and suitable for real-world
academic environments.

You might also like