Spaces:
Sleeping
Sleeping
# Quick Start Guide | |
## 1. Install Dependencies | |
```bash | |
pip install -r requirements.txt | |
``` | |
## 2. Run the Application | |
```bash | |
python app.py | |
``` | |
## 3. Use the Web Interface | |
1. Open your browser to http://localhost:7860 | |
2. Click "Upload Business Cards" and select one or more business card images | |
3. Choose your AI model: Flash (faster) or Pro (more accurate) | |
4. Choose whether to save images (enabled by default) | |
5. Click "Process Business Cards" | |
6. Download both generated Excel files: | |
- π **Current Run**: Just the cards you processed | |
- π **Total Database**: All cards ever processed | |
## What Gets Extracted? | |
- **Names**: Full name, first name, last name | |
- **Contact Info**: Multiple emails and phone numbers | |
- **Professional Info**: Job title, company, department | |
- **Location**: Full address, street, city, state, zip, country | |
- **Online**: Website, LinkedIn profile | |
- **Other**: Any additional information on the card | |
## Output Format | |
- Each business card = 1 row in Excel | |
- Two files: Current run + Cumulative database | |
- Multiple emails/phones are combined with commas | |
- Phone types (mobile/landline) are combined into one column | |
- Street and address are combined into one field | |
- Filename, processing date, and image path included for reference | |
- Images optionally saved to business_cards folder with timestamps | |
- Excel files are auto-formatted with proper column widths | |
## Tips | |
- Upload multiple cards at once (processed in batches of 5 for efficiency) | |
- Supported formats: JPG, PNG, JPEG | |
- Higher quality images = better extraction | |
- Batch processing reduces API calls and costs | |
- Enable image saving to keep a visual record of processed cards | |
- Check the preview table before downloading |