Welcome to the MultiLanguage Invoice Extractor project! This Streamlit application utilizes advanced language models to analyze invoice images and answer questions about their content.
This application is designed to extract information from uploaded invoice images and provide detailed responses based on user prompts. It leverages the Google Gemini-1.5-flash model for generating content and analyzing the invoice data.
MultiLanguage.Invoice.Extractor.mp4
- Streamlit: For creating the web interface
- Pillow (PIL): For handling image files
- Google Generative AI: For using the Gemini-1.5-flash model
- python-dotenv: For loading environment variables
You can install the required libraries using the following command:
pip install -r requirements.txt
-
Clone the repository:
git clone https://github.com/muhammadadilnaeem/Multiple-Language-Invoice-Extracter-LLM-Project.git
-
Navigate to the project directory:
cd Multiple-Language-Invoice-Extracter-LLM-Project
-
Create a
.env
file in the project root directory and add your Google API key:GOOGLE_API_KEY=your_google_api_key_here
-
Install the required dependencies:
pip install -r requirements.txt
-
Run the Streamlit application:
streamlit run app.py
- Upload Invoice Image: Supports jpg, jpeg, png, and jfif formats.
- Input Prompt: Enter a question or details about the invoice.
- Generate Response: Click the button to analyze the invoice and get the response.
- Upload an Invoice Image: Click the "Choose an Image of Invoice" button to upload your invoice image.
- Enter a Prompt: Provide any details or questions you have regarding the invoice in the input field.
- Analyze the Invoice: Click "Tell me about Invoice" to get a detailed response based on the invoice content.
The application will notify you if no invoice image is uploaded when you try to submit the form.
The app features a custom style including colors and layout, optimized for both light and dark themes.