feat: remove unnecessary stuff

README.md

@@ -11,12 +11,12 @@ pinned: false
 
 # Business Card Data Extractor 💼
 
-An AI-powered tool that extracts structured data from business card images using Google's Gemini AI. Upload business card images and get organized data exported to Excel files with automatic Google Drive storage.
+An AI-powered tool that extracts structured data from business card images using advanced AI models. Upload business card images and get organized data exported to Excel files with automatic Google Drive storage.
 
 ## Features
 
 - **Batch Processing**: Process multiple business cards at once (up to 5 per batch)
-- **AI Model Selection**: Choose between Gemini 2.5 Flash (fast) or Gemini 2.5 Pro (accuracy)
+- **AI Model Selection**: Choose between Speed-Optimized AI (fast) or Accuracy-Optimized AI (high accuracy)
 - **Google Drive Storage**: Automatic upload to organized Drive folders
 - **Excel Export**: Get data in two formats:
   - Current session results
@@ -28,7 +28,7 @@ An AI-powered tool that extracts structured data from business card images using
 
 1. **Setup**: Complete the setup process below (one-time)
 2. **Upload Images**: Select up to 5 business card images
-3. **Choose Model**: Select Gemini model (Flash for speed, Pro for accuracy)
+3. **Choose Model**: Select AI model (Speed-Optimized for fast processing, Accuracy-Optimized for best results)
 4. **Process**: Click "Extract Business Card Data"
 5. **Access Files**: Download temporary copies or access permanent files via Google Drive links
 
@@ -45,7 +45,7 @@ An AI-powered tool that extracts structured data from business card images using
 
 ## Setup Instructions
 
-### 1. Google Gemini API
+### 1. AI API Key
 - Get your API key from: https://aistudio.google.com/
 - Set as environment variable: `Gemini_API`
 
@@ -93,7 +93,7 @@ An AI-powered tool that extracts structured data from business card images using
 
 2. **Set Environment Variables** in your deployment platform:
    ```bash
-   Gemini_API=your_gemini_api_key
+   Gemini_API=your_ai_api_key
    GOOGLE_CLIENT_ID=your_google_client_id
    GOOGLE_CLIENT_SECRET=your_google_client_secret
    GOOGLE_TOKEN_BASE64=your_base64_encoded_token
@@ -109,4 +109,4 @@ An AI-powered tool that extracts structured data from business card images using
 - **Maximum File Size**: 10MB per image
 - **Batch Processing**: Up to 5 cards per API call
 - **Storage**: Automatic upload to Google Drive
-- **Models**: Gemini 2.5 Flash (fast) / Pro (accurate)
+- **Models**: Speed-Optimized AI (fast processing) / Accuracy-Optimized AI (best accuracy)

app.py

@@ -34,16 +34,16 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
-# Configure Gemini API
-logger.info("Configuring Gemini API")
+# Configure AI API
+logger.info("Configuring AI API")
 gemini_api_key = os.getenv("Gemini_API")
 if not gemini_api_key:
     logger.error("Gemini_API environment variable not found!")
-    logger.error("Please set the Gemini_API environment variable with your Google Gemini API key")
+    logger.error("Please set the Gemini_API environment variable with your AI API key")
     raise ValueError("❌ Gemini_API environment variable is required. Please set it in your environment.")
 
 genai.configure(api_key=gemini_api_key)
-logger.info("Gemini API configured successfully")
+logger.info("AI API configured successfully")
 
 # Initialize Google Drive service
 logger.info("Initializing Google Drive service")
@@ -119,7 +119,7 @@ def extract_business_card_data_batch(images, filenames, model_name="gemini-2.5-f
         raise
     
     # Configure model
-    logger.debug(f"Configuring Gemini model: {model_name}")
+    logger.debug(f"Configuring AI model: {model_name}")
     generation_config = {
         "temperature": 0.1,
         "response_mime_type": "application/json"
@@ -131,9 +131,9 @@ def extract_business_card_data_batch(images, filenames, model_name="gemini-2.5-f
             generation_config=generation_config,
             system_instruction=system_prompt
         )
-        logger.debug("Gemini model configured successfully")
+        logger.debug("AI model configured successfully")
     except Exception as e:
-        logger.error(f"Failed to configure Gemini model: {e}")
+        logger.error(f"Failed to configure AI model: {e}")
         raise
     
     # Prepare multiple images for the model
@@ -578,7 +578,8 @@ def process_business_cards(images, model_name="gemini-2.5-flash", save_images=Tr
     logger.info("Creating summary message")
     num_batches = len(image_batches) if 'image_batches' in locals() else 1
     summary = f"Successfully processed {len(all_data)} business card(s) in {num_batches} batch(es) of up to 5 cards.\n"
-    summary += f"🤖 AI Model used: {model_name}\n"
+    model_display = "Speed-Optimized AI" if "flash" in model_name else "Accuracy-Optimized AI"
+    summary += f"🤖 AI Model used: {model_display}\n"
     summary += f"⚡ API calls made: {num_batches} (instead of {len(all_data)})\n"
     
     if save_images:
@@ -667,7 +668,7 @@ with gr.Blocks(title="Business Card Data Extractor") as demo:
             )
             
             model_selector = gr.Dropdown(
-                choices=["gemini-2.5-pro", "gemini-2.5-flash"],
+                choices=[("Accuracy-Optimized AI", "gemini-2.5-pro"), ("Speed-Optimized AI", "gemini-2.5-flash")],
                 value="gemini-2.5-pro",
                 label="AI Model Selection"
             )
@@ -708,7 +709,7 @@ with gr.Blocks(title="Business Card Data Extractor") as demo:
     gr.Markdown(
         """
         ## Features:
-        - 🤖 **Model Selection**: Choose between Gemini 2.5 Flash (fast) or Pro (accurate)
+        - 🤖 **Model Selection**: Choose between Speed-Optimized AI (fast) or Accuracy-Optimized AI (accurate)
         - ⚡ **Batch Processing**: Processes 5 cards per API call for efficiency
         - 📄 **Data Extraction**: Names, emails, phone numbers, addresses, and more
         - 📞 **Smart Combination**: Multiple emails/phones combined with commas

env.example

@@ -1,10 +1,10 @@
 # Environment Variables for Business Card Data Extractor
 # Copy this file to .env and replace with your actual values
 
-# Google Gemini API Key (Required)
+# AI API Key (Required)
 # Get your key from: https://aistudio.google.com/
 # For deployment: Add this as an environment variable named "Gemini_API"
-Gemini_API=your_gemini_api_key_here
+Gemini_API=your_ai_api_key_here
 
 # Google Drive API Credentials (Required - for file storage)
 # Get these from Google Cloud Console:

setup_hf_space.md

@@ -30,9 +30,9 @@ business_cards/.gitkeep
 3. Click **Add a new secret**
 4. Set:
    - **Name**: `Gemini_API`
-   - **Value**: Your Google Gemini API key
+   - **Value**: Your AI API key
 
-### 4. Get Your Gemini API Key
+### 4. Get Your AI API Key
 1. Go to [Google AI Studio](https://aistudio.google.com/)
 2. Click "Get API key"
 3. Create a new API key
@@ -51,7 +51,7 @@ business_cards/.gitkeep
 ✅ **Batch processing**: Efficient 5-cards-per-API-call processing  
 
 ## Environment Variables Required
-- `Gemini_API`: Your Google Gemini API key (required)
+- `Gemini_API`: Your AI API key (required)
 
 ## Notes
 - The space will create necessary directories automatically