Update app.py

app.py

@@ -17,6 +17,16 @@ TRAINING_DATASET = "Sahil5112/ContinuumGPT"  # Main training dataset for Continu
 CONVERSATION_BUFFER = []
 MAX_BUFFER_SIZE = 10  # Save to HF after 10 training examples
 
+# Model mapping for HuggingFace Inference API
+MODEL_MAPPING = {
+    "puter:gpt-5-nano": "meta-llama/Llama-3.2-3B-Instruct",
+    "puter:claude-sonnet-4": "meta-llama/Llama-3.2-3B-Instruct",
+    "puter:google/gemini-2.5-flash": "meta-llama/Llama-3.2-3B-Instruct",
+    "puter:meta-llama/llama-4-scout": "meta-llama/Llama-3.2-3B-Instruct",
+    "puter:deepseek-chat": "meta-llama/Llama-3.2-3B-Instruct",
+    "puter:liquid/lfm-7b": "meta-llama/Llama-3.2-3B-Instruct"
+}
+
 def load_training_dataset():
     """Load existing training data from HuggingFace"""
     try:
@@ -54,10 +64,95 @@ def save_to_training_dataset(training_examples):
         print(f"❌ Error saving to dataset: {e}")
         return False
 
+def call_huggingface_model(model_name, prompt):
+    """Call HuggingFace Inference API - Returns dict with success/error info"""
+    if not HF_TOKEN:
+        return {
+            "success": False,
+            "error": "HF_TOKEN not set. Please add your HuggingFace token to enable AI model training.",
+            "response": None
+        }
+    
+    hf_model = MODEL_MAPPING.get(model_name, "meta-llama/Llama-3.2-3B-Instruct")
+    
+    try:
+        headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+        api_url = f"https://api-inference.huggingface.co/models/{hf_model}"
+        
+        payload = {
+            "inputs": prompt,
+            "parameters": {
+                "max_new_tokens": 512,
+                "temperature": 0.7,
+                "top_p": 0.95,
+                "return_full_text": False
+            }
+        }
+        
+        response = requests.post(api_url, headers=headers, json=payload, timeout=30)
+        
+        if response.status_code == 200:
+            result = response.json()
+            if isinstance(result, list) and len(result) > 0:
+                generated_text = result[0].get("generated_text", "")
+                return {
+                    "success": True,
+                    "error": None,
+                    "response": generated_text
+                }
+            return {
+                "success": False,
+                "error": f"Unexpected response format: {str(result)}",
+                "response": None
+            }
+        elif response.status_code == 503:
+            return {
+                "success": False,
+                "error": f"Model {hf_model} is loading. Please try again in a few seconds.",
+                "response": None
+            }
+        else:
+            return {
+                "success": False,
+                "error": f"API Error: {response.status_code} - {response.text[:200]}",
+                "response": None
+            }
+    except Exception as e:
+        return {
+            "success": False,
+            "error": f"Error calling model: {str(e)}",
+            "response": None
+        }
+
 @app.route("/")
 def index():
     return send_from_directory(".", "index.html")
 
+@app.route("/api/generate", methods=["POST"])
+def generate_response():
+    """Generate AI response using HuggingFace models"""
+    data = request.get_json()
+    prompt = data.get("prompt", "").strip()
+    model = data.get("model", "puter:gpt-5-nano")
+    
+    if not prompt:
+        return jsonify({"success": False, "error": "Missing prompt"}), 400
+    
+    result = call_huggingface_model(model, prompt)
+    
+    if result["success"]:
+        return jsonify({
+            "success": True,
+            "response": result["response"],
+            "model": model
+        })
+    else:
+        return jsonify({
+            "success": False,
+            "error": result["error"],
+            "model": model
+        })
+
 @app.route("/api/train", methods=["POST"])
 def train_model():
     """Process AI model response and save as training data"""
@@ -149,14 +244,14 @@ def flush_buffer():
         return jsonify({"error": "Failed to flush buffer"}), 500
 
 if __name__ == "__main__":
-    port = int(os.getenv("PORT", 7860))
+    port = int(os.getenv("PORT", 5000))
     
     print("🚀 Starting ContinuumLearner Training Server...")
     print(f"📊 Training Dataset: {TRAINING_DATASET}")
     print(f"🎓 Dataset URL: https://huggingface.co/datasets/{TRAINING_DATASET}")
     print("")
     print("🤖 Training Mode: Model Copy Learning")
-    print("   - AI models respond to prompts")
+    print("   - AI models respond to prompts via HuggingFace API")
     print("   - Responses are saved as training data")
     print("   - ContinuumGPT learns from these patterns")
     print("   - NO user data is stored")
@@ -168,5 +263,7 @@ if __name__ == "__main__":
         print(f"📚 Current dataset size: {len(training_data)} training examples")
     else:
         print("⚠️ HuggingFace Integration Disabled - Add HF_TOKEN to enable")
+        print("   - You can still use the app, but responses will show warnings")
+        print("   - Training data won't be saved to HuggingFace")
     
     app.run(host="0.0.0.0", port=port, debug=False, threaded=True)