atzamis / askpdf

This repository includes a LLM and a streamlit application for asking questions to a PDF.

Interactive PDF Q&A: A Retrieval-Augmented Generation Approach

Overview

This application leverages Retrieval-Augmented Generation (RAG) to enable users to interact with their PDF documents by asking questions and receiving relevant answers. The system integrates several technologies to load, process, and query documents efficiently.

Key Components

• Langchain: Framework for orchestrating Large Language Models (LLMs).
• PyPDF: Library for loading and processing PDF documents.
• FAISS: Library for efficient similarity search and clustering of dense vectors.
• Streamlit: Framework for building the interactive web application.

Prerequisites

Ensure you have Docker installed on your machine.

## How to Run the Application

1. Clone the Repository.

git clone https://github.com/NachoCP/AskPDF.git
cd AskPDF

2. Build the Docker Image.

docker build . -t chat-app

3. Run the Docker Container.

docker run -d -p 8000:8000 --name chat-app chat-app

4. Access the Application. Open your web browser and navigate to http://localhost:8000 to start interacting with your PDFs.

## Usage

1. Upload your PDF documents via the web interface.
2. Enter your OpenAI API key when prompted.
3. Ask questions about the content of the uploaded PDFs.
4. Receive responses generated by the LLM based on the content of your documents.