/File-Based-Chatbot

This project is designed to extract text from both PDF and docx files within a specified folder path and generate responses to user-input questions using natural language processing (NLP) techniques.

Primary LanguagePython

File-Based Chatbot: Answering Questions from Documents

This is a file-based chatbot application that utilizes the Gemini model for generating responses to user queries based on text extracted from documents (PDF, DOC, DOCX).

Overview

This File-Based Chatbot is a Python application leveraging various libraries, including PySimpleGUI, pdfplumber, google-generativeai, and python-docx. The chatbot analyzes text data extracted from PDFs and Word documents in a specified folder and responds to user queries.

Features

  • Extracts text data from PDF and Word documents.
  • Utilizes the Gemini model for generating responses.
  • Simple and user-friendly interface using PySimpleGUI.
  • Supports a wide range of document formats.

Gemini Model

The chatbot uses the Gemini model, powered by Google's GenerativeAI platform, to generate responses based on the extracted text and user queries. The Gemini model is a powerful language model capable of understanding and generating natural language responses

License

This project is licensed under the MIT License - see the LICENSE file for details.