• Rucha Bhalchandra Nikumbh
• Prof. Dr. Bhagwan D. Phulpagar

In the era of rapidly expanding digital content, efficiently extracting and interacting with information from documents has become increasingly vital. This paper presents the design and implementation of a Generative AI-driven chatbot that leverages Natural Language Processing (NLP) and Deep Learning to provide adaptive summarization and interactive question answering based on user-uploaded PDF documents. The proposed system aims to enhance the document reading experience by enabling users to receive concise summaries of complex content and engage in personalized, context-aware dialogues with the chatbot. The core of the system is built upon a fine-tuned transformer-based NLP model that understands and processes textual information extracted from the PDF. A deep learning framework enables the system to maintain contextual continuity and semantic relevance in both summaries and user interactions. The chatbot is capable of dynamically generating human-like responses to user queries by referring directly to the content of the uploaded document, allowing for a more interactive and intuitive way of consuming knowledge. Additionally, the platform supports intelligent suggestions and allows users to download chat transcripts, further enriching usability. This research highlights the practical integration of advanced NLP techniques with deep learning architectures in a real-world application. The paper also discusses the challenges encountered during the development process, such as handling large document sizes, managing session-based interactions, and balancing performance with accuracy. The implemented system avoids relying solely on traditional static retrieval or keyword-based matching techniques, instead providing a more fluid and adaptive conversational experience. Our evaluation demonstrates that this hybrid approach significantly improves the relevance and coherence of generated answers while offering an efficient summarization capability. The chatbot serves as a step forward in transforming passive document reading into an active, intelligent dialogue system. This research contributes to the growing field of conversational AI by presenting a scalable and user-centric solution for automated document understanding and interaction.

Generative AI, NLP, Deep Learning, Chatbot, Document Summarization, Interactive Question Answering, PDF Analysis, Conversational AI, Transformer Models, BERT

"A Comparative Review of NLP Models for Enhancing Conversational AI Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.k504-k512, April-2025, Available :http://www.jetir.org/papers/JETIR2504A66.pdf

"A Comparative Review of NLP Models for Enhancing Conversational AI Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppk504-k512, April-2025, Available at : http://www.jetir.org/papers/JETIR2504A66.pdf