• Aditya Kalbhor
• Dr. Snehal Rathi
• Prasad Chate
• Sanwara Chandak
• Om Deore

For practitioners, students, and researchers, the amount of material available in various formats—especially in portable document format (PDF)—in the digital age presents both advantages and barriers. Using traditional methods to extract insights important from these documents can be time consuming and ineffective. This study describes a new conversational service using Lang chains, a framework for smooth communication and speech modelling, and Google Gemini, a state-of-the-art AI model for generating. The use of this product enables users to efficiently retrieve content and perspectives relevant to them. It allows for multiple PDF files to be uploaded and discussions to be held. The software processes the text within the PDF files into an easily retrievable format using vector embedding technology considerably improving the usability of the system and the degree of accessibility of information across the board. The methodologies that were adopted during application development processes and such like information extraction, chunking and embedding are discussed in this paper. It further assesses the implications of such inclusion from the perspective of acknowledgement of more advanced capabilities of engagement with academic sources. This study aims to develop a unique chat application that is designed for use with PDF files. The user is allowed to upload PDF documents, which are then converted into vector representations by, vector methods inspired by Facebook for easy content retrieval. With the inclusion of LangChain, the application provides deep reading of PDF contents and allows query answering over the contents, to the extent that the user can ask questions and receives relevant and correct answers within context. The system provides room for data management options as it allows both offline and online vectorized data management systems. Detailed and explanatory guidelines are provided to present no difficulties in execution as, making this endeavor an essential core focusing on improving usability of PDFs.

Google Gemini, PDF, Lang chain, vector embeddings, chat application.

"Question and Answer Chatbot using LLM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.e250-e258, November-2024, Available :http://www.jetir.org/papers/JETIR2411429.pdf

"Question and Answer Chatbot using LLM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. ppe250-e258, November-2024, Available at : http://www.jetir.org/papers/JETIR2411429.pdf