A Streamlit application to extract and understand information from invoice images using Google's Generative AI.

• Upload invoice images in JPG, JPEG, or PDF format.
• Extract and answer questions based on the uploaded invoice image using Gemini Pro Vision.

• Python 3.7+
• Streamlit
• python-dotenv
• Pillow (PIL)
• google-generativeai

1. Clone the repository:

   git clone https://github.com/yourusername/multilanguage-invoice-extractor.git
   cd multilanguage-invoice-extractor

2. Create and activate a virtual environment (optional but recommended):

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

3. Install the dependencies:

   pip install -r requirements.txt

4. Create a .env file in the project root directory and add your Google API key:

   GOOGLE_API_KEY=your_google_api_key

1. Run the Streamlit application:

   streamlit run app.py

2. Open your web browser and go to http://localhost:8501.

3. Upload an invoice image and input your prompt to get the response based on the uploaded invoice image.

├── app.py
├── requirements.txt
├── .env
└── README.md

• app.py: Main application file containing the Streamlit app code.
• requirements.txt: List of dependencies required for the project.
• .env: Environment file to store the Google API key.
• README.md: Project documentation.

• Streamlit
• Pillow
• google-generativeai