/Invoice-Extractor-LLM-APP

Primary LanguagePythonMIT LicenseMIT

Invoice-Extractor-LLM-APP

MultiLanguage Invoice Extractor

This project is a Streamlit web application that utilizes Google's Generative AI to extract information from invoice images based on user-provided prompts. It demonstrates the use of generative models for understanding and processing invoice data.

Features

  • Image Upload: Users can upload invoice images in JPG, PNG, or JPEG format.
  • Prompt Input: Users can provide prompts in text format to guide the extraction process.
  • Generative AI Integration: Utilizes Google's Generative AI to analyze images and generate responses.
  • Multi-Language Support: Capable of providing responses in multiple languages based on the input prompt.

Installation

To run this project locally, follow these steps:

  1. Clone the repository:

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

  2. Set up Python environment (recommended using Anaconda):

    conda create --name invoice python=3.8
conda activate invoice

  3. Install dependencies:

    pip install -r requirements.txt

  4. Set up Google API Key:

    • Obtain a Google API Key with access to Generative AI (Gemini).

    • Create a .env file in the project root directory.

    • Add your API key to the .env file:

      GOOGLE_API_KEY="your_api_key_here"

  5. Run the Streamlit application:

    streamlit run app.py

  6. Access the application in your browser at http://localhost:8501.

Usage

  • Upload an invoice image using the file uploader.
  • Enter a prompt that describes what information you want from the invoice.
  • Click the "Tell me about the invoice" button to generate and display the response.
  • The response will be shown below the image, indicating the extracted information.

Example Prompt

Here are some example prompts you can use:

You are an expert in understanding invoices.
You are provided with an image of an invoice and a prompt.
Extract the relevant information from the invoice image and generate a response that is relevant to the given prompt.

Contributing

Contributions are welcome! If you find any issues or have suggestions for improvements, please feel free to open an issue or create a pull request.

License

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