Update README.md

README.md

@@ -8,7 +8,70 @@ sdk_version: 5.12.0
 app_file: app.py
 pinned: false
 license: apache-2.0
-short_description: 'This Hugging Face Space provides a receipt OCR service that '
+short_description: 'This Hugging Face Space provides restaurant receipts OCR.'
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Features
+
+- **Multi-Language Support**: Process receipts in multiple languages including English, Chinese, French, German, Korean, Japanese, and more
+- **LLM Integration**: Use Groq or OpenAI for structured JSON formatting
+- **Flexible Output**: Get raw OCR text or formatted JSON based on your needs
+- **Secure API Key Handling**: Safely input your API keys for LLM processing
+
+## How to Use
+
+1. **Upload Receipt**: Upload a clear image of your receipt
+2. **Select Language**: Choose the primary language of your receipt
+3. **LLM Processing** (Optional):
+   - Select your preferred LLM provider (Groq or OpenAI)
+   - Enter your API key
+4. **Process**: Click "Process Receipt" to get results
+
+## Output Format
+
+The app provides JSON output with the following structure:
+```json
+{
+  "restaurant_name": string,
+  "date": string,
+  "time": string,
+  "table_number": string or number,
+  "server_name": string,
+  "payment_method": string,
+  "items": [
+    {
+      "name": string,
+      "quantity": number,
+      "price": number
+    }
+  ],
+  "subtotal": number,
+  "tax": number,
+  "tip": number,
+  "total": number,
+  "receipt_number": string
+}
+```
+
+## Supported Languages
+
+- English
+- Chinese Simplified
+- French
+- German
+- Korean
+- Japanese
+- Italian
+- Spanish
+- Portuguese
+- Russian
+- Arabic
+- Hindi
+- Vietnamese
+- Thai
+
+## Notes
+
+- Image quality affects OCR accuracy
+- For best results, ensure receipt is well-lit and clearly visible
+- LLM processing requires valid API keys from Groq or OpenAI