Finding information inside organizational documents is harder than it should be. You open a PDF, scroll through pages, maybe open another file, and still not find what you need. Traditional search methods take time. Rule-based chatbots do not help much either they only respond to what they were programmed for. This research is about creating an AI-powered chatbot that actually understands questions and finds answers from real documents. It runs completely on AWS serverless, so no infrastructure headaches. Amazon Lex handles the conversations. It figures out what the user is asking. Amazon Bedrock, specifically the Claude model, generates the actual responses. But here is the key part Retrieval Augmented Generation. That is a fancy way of saying the chatbot first pulls relevant info from documents stored in S3, then uses that to form its answer. So the response is grounded in actual content, not just AI guesswork. The frontend is built with Vue.js and JavaScript. It looks clean. Works on mobile. Supports voice too. You can talk to it, it talks back. There is silence detection, interruption handling all the stuff that makes voice feel natural. Security comes from Amazon Cognito, so only authorized users get in. And the whole setup is automated using CloudFormation. That means I can deploy everything with a template, consistent every time. You can run the chatbot as a full page. Or embed it as a widget using iframe. It remembers conversation history. It uses response cards for interactive options. Little details that make it actually usable. The goal was simple stop making people dig through documents. Let the AI do the digging. Faster responses, less dependency on human agents, and something that scales when more users show up. This system can work for customer support, education, enterprise knowledge bases anywhere people need answers fast.
Conversational Chatbot, AWS, Amazon Lex, Amazon Bedrock, Retrieval Augmented Generation, Generative AI, Serverless.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.