Create README.md

README.md

@@ -1,13 +1,112 @@
 ---
-title: Ibi Voice Backend
-emoji: 📚
-colorFrom: purple
-colorTo: red
-sdk: gradio
-sdk_version: 5.35.0
-app_file: app.py
-pinned: false
 license: mit
+title: Ibi-Voice Translation Backend
+sdk: gradio
+emoji: 🌍
+colorFrom: blue
+colorTo: pink
+short_description: JR Digital Insights - Professional English to Ibibio transla
+---
+# 🎯 Ibi-Voice Translation Backend
+
+**JR Digital Insights** - AI-powered Ibibio translation service on Hugging Face Spaces
+
+## 🚀 Quick Setup
+
+### 1. Get Your API Keys
+
+#### Groq API Key (Free)
+1. Go to [console.groq.com](https://console.groq.com)
+2. Sign up/login
+3. Navigate to "API Keys"
+4. Create new key
+5. Copy the key (starts with `gsk_...`)
+
+#### Tavily Search API Key (Free Tier)
+1. Go to [tavily.com](https://tavily.com)
+2. Sign up for free account
+3. Get your API key from dashboard
+4. Copy the key (starts with `tvly-...`)
+
+### 2. Configure Hugging Face Space
+
+1. In your HF Space, click **"Settings"** tab
+2. Scroll to **"Repository secrets"**
+3. Add these secrets:
+   ```
+   Name: GROQ_API_KEY
+   Value: your_groq_key_here
+   
+   Name: TAVILY_API_KEY  
+   Value: your_tavily_key_here
+   ```
+4. Click **"Add secret"** for each
+
+### 3. Upload Files
+
+Upload these files to your HF Space:
+- `app.py` (main backend code)
+- `requirements.txt` (dependencies)
+- `README.md` (this file)
+
+## 🌐 API Usage
+
+### Frontend Integration
+
+```javascript
+// Connect your Ibi-Voice frontend to this backend
+async function translateOnline(query) {
+    const response = await fetch('https://your-username-ibi-voice-backend.hf.space/api/predict', {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({
+            data: [query],
+            fn_index: 0  // First function in Gradio interface
+        })
+    });
+    
+    const result = await response.json();
+    return result.data[0];
+}
+
+// Usage example
+translateOnline("What is 'God is good' in Ibibio?")
+    .then(translation => console.log(translation));
+```
+
+### Direct API Call
+
+```bash
+curl -X POST "https://your-username-ibi-voice-backend.hf.space/api/predict" \
+     -H "Content-Type: application/json" \
+     -d '{
+       "data": ["What is God is good in Ibibio?"],
+       "fn_index": 0
+     }'
+```
+
+## 🔧 Features
+
+- **🧠 AI Reasoning**: Uses Groq LLaMA3-8B for intelligent translation analysis
+- **🔍 Web Search**: Real-time lookup via Tavily API for current information
+- **📚 Local Dictionary**: Built-in fallback for common Ibibio phrases
+- **🎯 Smart Combining**: Merges all sources for best possible translation
+
+## 📋 Testing Queries
+
+Try these example queries:
+- "What is 'God is good' in Ibibio?"
+- "How do you say 'thank you' in Ibibio?"
+- "Translate 'good morning' to Ibibio"
+- "What does 'sosongo' mean in English?"
+
+## 🎯 Next Steps
+
+1. Deploy this backend to HF Spaces
+2. Test the API endpoints
+3. Integrate with your Ibi-Voice React frontend
+4. Add more local dictionary entries as needed
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+**Built for JR Digital Insights** | Ibibio Language Preservation Project