Update README.md

README.md

@@ -4,7 +4,7 @@ emoji: 🏢
 colorFrom: blue
 colorTo: purple
 sdk: gradio
-sdk_version: "4.0.0"
+sdk_version: "4.44.0"
 app_file: app.py
 pinned: false
 ---
@@ -30,12 +30,15 @@ A Hugging Face Gradio application that generates CLIP-ready visual descriptions
 2. Click "Create new Space"
 3. Choose "Gradio" as the SDK
 4. Upload `app.py`, `requirements.txt`, and `README.md`
-5. **Enable OAuth (Required)**:
-   - Go to your Space's Settings
-   - Scroll to "OAuth" section
-   - Enable "OAuth" toggle
-   - This allows the app to use your HF Pro account's API access
-6. Your app will be deployed automatically!
+5. **Add Your HF Token as a Secret (Required)**:
+   - Go to your Space's Settings (gear icon)
+   - Find the "Repository secrets" or "Secrets" section
+   - Click "Add a secret" or "New secret"
+   - Enter:
+     - **Name**: `HF_TOKEN`
+     - **Value**: Your Hugging Face token (get from https://huggingface.co/settings/tokens)
+   - Click "Save"
+6. Your app will be deployed and restart automatically!
 
 ### 2. Prepare Your CSV Files
 
@@ -51,16 +54,17 @@ Equipment,additional_data
 
 ### 3. Use the Application
 
-1. **Upload Files**: Upload one or more CSV files
-2. **Specify Column**: Enter the name of the column containing categories (default: "category")
-3. **Adjust Settings** (optional):
+1. **Login** (optional): Click the "Login" button in the sidebar to authenticate with your HF account
+2. **Upload Files**: Upload one or more CSV files
+3. **Specify Column**: Enter the name of the column containing categories (default: "category")
+4. **Adjust Settings** (optional):
    - Max Tokens: 64-512 (default: 256)
    - Temperature: 0.1-1.0 (default: 0.7)
    - Top-p: 0.1-1.0 (default: 0.9)
-4. **Process**: Click "Process Files" and wait for completion
-5. **Download**: Download the output CSV files with descriptions
+5. **Process**: Click "Process Files" and wait for completion
+6. **Download**: Download the output CSV files with descriptions
 
-*Note: Authentication is handled automatically through HF Spaces OAuth when enabled in settings.*
+*Note: Authentication works via the HF_TOKEN secret you added in Space settings.*
 
 ## Output Format
 
@@ -88,25 +92,27 @@ Car Rental For Self Driven,"a car available for self-drive rental, parked at a p
 ## Technical Details
 
 - **Model**: meta-llama/Llama-3.3-70B-Instruct
-- **Framework**: Gradio 4.0+
+- **Framework**: Gradio 4.44+
 - **Processing**: Categories are deduplicated automatically
 - **Output Files**: Named as `output_{original_name}_{timestamp}.csv`
 
 ## Troubleshooting
 
-### "Hugging Face token not found" error
-- Make sure OAuth is enabled in your Space settings
-- Go to Space Settings → OAuth → Enable OAuth toggle
-- Restart your Space after enabling OAuth
+### "Please login with your Hugging Face account" error
+- Make sure you've added `HF_TOKEN` as a Secret in your Space settings
+- Go to Space Settings → Secrets → Add a secret
+- Name: `HF_TOKEN`, Value: your token from https://huggingface.co/settings/tokens
+- Restart your Space after adding the secret
 
 ### "Column not found" error
 - Check that the column name matches exactly (case-sensitive)
 - View the error message to see available columns
 
 ### Authentication errors
-- Ensure you have a Hugging Face Pro account for API access
-- Check that OAuth is properly configured in Space settings
+- Ensure your HF token has proper permissions (Read access minimum)
+- For Pro features, make sure you have a Hugging Face Pro account
 - Verify that your account has access to the Llama 3.3 model
+- Check that the token hasn't expired
 
 ### Slow processing
 - The model processes each unique category individually
@@ -136,4 +142,5 @@ Get your token from: https://huggingface.co/settings/tokens
 
 ## License
 
-This project uses the Llama 3.3 model which requires agreement to Meta's license terms.
+This project uses the Llama 3.3 model which requires agreement to Meta's license terms.
+