OCR tool for PDFs

Easily parse the text in your pdf -- even if it's images.

Provides output in 3 formats:

1. Structured
2. Raw
3. JSON

Set up

1. Clone the repository:

   git clone repo_link
   

2. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

3. Install the required packages:

   pip install -r requirements.txt
   

4. Setting up Poppler -- This is required.

   You need to have poppler installed on your machine and added in path (system environment variables)

   Go to this link: https://github.com/oschwartz10612/poppler-windows/releases/tag/v24.08.0-0

   Download the zip file, extract it, go to the bin folder isnide it, copy teh path and add it to your env variables.

5. Set your OPENAI_API_KEY

    export OPENAI_API_KEY=your_api_key_here     
   

   or

    set OPENAI_API_KEY=your_api_key_here
   

Usage

1. Start the Streamlit app:

   streamlit run app.py
   

2. Open your web browser and navigate to the URL provided by Streamlit (usually http://localhost:8501).

3. Upload your pdf document and see the result in 3 formats: Structured, Raw, and JSON.