Chabot

Abstract

Finding accurate and reliable answers can be a daunting task due to various challenges. These challenges include limited access to reading records, language barriers, and limited resources. However, Chabot’s can play a crucial role in addressing these challenges by providing a convenient and user-friendly platform for accessing and analysing data. Chabot can use Lang chain and Stream lit to create an interactive application for querying PDF documents and provide instant responses to user queries. Which can help increase engagement and awareness of their research work. Ultimately, the use of Chabot’s can help increase accessibility and accuracy of a researcher, which can contribute to a greater understanding of their work. The Project is also based on Chabot designed to provide users with information on their documents. The Chabot uses the Stream lit library to create a web application. This application allows users to upload PDF documents and interact with them in a conversational manner. The code uses the Lang Chain library to process the text from the PDFs, split it into chunks, and generate embedding’s for each chunk. These embedding’s are then stored in a vector store using the FAISS library. The application then uses a large language model to generate responses to user queries based on the content of the uploaded PDFs.