An intelligent system for understanding and analyzing invoices using Google Generative AI.
The MultiLanguage Invoice Extractor is designed to leverage the power of Google Generative AI for analyzing invoices. Users can upload invoice images, provide input prompts, and receive detailed responses based on the content extracted from these images.
- Invoice Analysis: Analyze uploaded invoice images and provide insightful responses.
- Input Prompt: Users can input prompts to guide the analysis and receive targeted information.
- Google Generative AI Integration: Leverages Google's Generative AI for intelligent content generation.
- Python > 3.9
- API Key (Set in the .env file)
-
Clone the Repository:
git clone https://github.com/yourusername/multilanguage-invoice-extractor.git
-
Navigate to Project Directory:
cd multilanguage-invoice-extractor
-
Install Dependencies:
pip install -r requirements.txt
-
Set Up API Key:
-
Open the
.env
file and replaceyour_api_key
with your actual API key:GOOGLE_API_KEY=your_api_key
-
-
Run the Streamlit App:
streamlit run app.py
-
Access the Application:
- Open your web browser and go to http://localhost:8501.
-
Provide Input Prompt:
- Enter an input prompt describing the task or question related to the uploaded invoice image.
-
Upload Invoice Image:
- Use the file uploader to upload an invoice image (in formats like png, jpg, or jpeg).
-
Submit for Analysis:
- Click the "What is this?" button to trigger the analysis of the uploaded image based on the provided input prompt.
-
View Analysis Result:
- The system will process the image using Google's Generative AI model and display the result.
Additional configuration options or customization details.
Contributions are welcome! Follow the guidelines in CONTRIBUTING.md.
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.
- Streamlit
- Google Generative AI
- Other libraries/tools/resources used in the project.
This version now includes the major steps in your project in the "Usage" section of the README.md.