BhushanP-01/InvoiceExtractor
1
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
Multilanguage Invoice Extractor
This project aims to extract specific information from uploaded invoice images using machine learning models and various Python libraries. It's designed to provide a simple interface for users to interact with and extract necessary details from invoices. It is build using "Gemini pro vision model".
Features
- _Image Upload_: Users can upload images of invoices in formats like JPG, JPEG, or PNG.
- _Information Extraction_: Extracts requested information from uploaded invoice images.
- _Multi-Language Support_: Utilizes language processing capabilities for extraction in multiple languages.
Libraries and Dependencies
- Streamlit
- google-generativeai
- python-dotenv
- langchain
- PyPDF2
- chromadb
Usage
Setup
- Install the necessary dependencies using pip install -r requirements.txt.
- Set up environment variables following the .env.example file.
Running the App
Run the application using the following command: streamlit run app.py
Interface
- _Input Prompt_: Enter the desired information to extract from the invoice.
- _Image Upload_: Choose an invoice image (JPG, JPEG, or PNG) to process.
- _Extraction_: Click the "Tell me about the invoice" button to extract information.
How It Works
- _Initialization_: Loads required environment variables and configures the GenerativeAI model.
- _Gemini Pro Vision Model_: Uses the GenerativeAI model 'gemini-pro-vision' for content generation.
- _Extraction Function_: Processes the uploaded image and input prompt to extract requested information.
Contribution
Contributions are welcome! If you'd like to contribute to this project, please follow these steps:
- Fork the repository.
- Create a new branch (
git checkout -b feature/improvement). - Make modifications and commit changes (
git commit -am 'Add feature'). - Push the changes to your branch (
git push origin feature/improvement). - Create a Pull Request.
Acknowledgments
- Streamlit for the interactive web app framework.
- GenerativeAI for the Gemini Pro Vision model.
- Other libraries and tools used in this project.
