/QueryPDF

QueryPDF form the Hackathon Nextgen-GPT-AI (https://lablab.ai/event/nextgen-gpt-ai-hackathon/neural-nomads/querypdf)

Primary LanguageJupyter Notebook

QueryPDF with GPT-4

Welcome to QueryPDF, an innovative solution that leverages GPT-4, vector search, and document embeddings to enhance your PDF document exploration experience.

Overview

QueryPDF allows users to upload PDF documents and interactively query their content. Behind the scenes, the system utilizes advanced vector database technology to store document embeddings, enabling efficient vector searches for relevant content. The integration with GPT-4 ensures natural language understanding and generation, providing accurate and contextually rich responses.

Features

  • Upload and Query: Easily upload PDFs and pose queries to extract information from the documents.

  • Vector Database: Utilizes a powerful vector database to store document embeddings, facilitating fast and accurate searches.

  • GPT-4 Integration: Leverages GPT-4 for natural language understanding and generation of responses, enhancing the user experience.

Getting Started

  1. Clone the Repository:

    git clone https://github.com/ViditDhull/Nextgen-GPT-AI-Hackathon.git
cd QueryPDF

  2. Install Dependencies:

    pip install -r requirements.txt

  3. Run the Application:

    python app.py

  4. Access the Application: Open your web browser and navigate to http://localhost:5000 to interact with QueryPDF.

Usage

  1. Upload PDF:

    • Click on the "Upload" button to upload your PDF document.

  2. Pose Queries:

    • Enter your queries in the provided input box and submit.

  3. View Responses:

    • Explore the natural language responses generated by GPT-4.