DataEntryAI

An intelligent data processing pipeline for extracting structured information from documents (PDFs and images) using AI models.

Features

• PDF and image file processing (In the future)
• Automated schema extraction
• AI-powered data extraction
• Multi-format output generation
• Configurable processing pipelines

Installation

1. Clone the repository

git clone https://github.com/drLacheheb/DataEntryAI.git
cd DataEntryAI

2. Set up virtual environment (recommended)

python -m venv venv
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

Usage

Basic Processing

python src/main.py

Supported Input Formats

• PDF (Not yet implemented)
• JPEG (.jpg, .jpeg)
• PNG (.png)

Project Structure

├── src/                 - Main source code
│   ├── ai/             - AI model integration
│   ├── processing/     - Data processing modules
│   └── utils/          - Common utilities
├── data/               - Data assets
│   ├── input/          - Input documents
│   └── output/         - Processing results
└── requirements.txt    - Dependency list

---

Note: Before running the application, ensure your input files are placed in the data/input/ directory and selected in the src/main.py (cli tool can be implemented...) ,appropriate AI model weights are configured.