Update app.py

app.py

@@ -1,76 +1,74 @@
 import gradio as gr
 import requests
 import os
+MODELS = [
+    "Qwen/Qwen2.5-1.5B-Instruct",
+    "Qwen/Qwen2.5-0.5B-Instruct",
+    "microsoft/phi-2",
+    "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+]
 
 def generate_flutter_code(prompt, api_token=None):
-    """
-    Generate Flutter/Dart code using Hugging Face Inference API with Qwen 3 0.6B
-    """
     if not api_token:
         api_token = os.getenv("HF_TOKEN")
 
     if not api_token:
-        return "Error: Hugging Face API token is required. Please provide it in the input field or set HF_TOKEN environment variable."
-
-    # Qwen 3 0.6B model for code generation
-    model_id = "Qwen/Qwen-0.6B"
-
-    # Enhanced prompt for Flutter/Dart code generation
-    enhanced_prompt = f"""You are an expert Flutter/Dart developer. Generate high-quality, production-ready Flutter/Dart code based on the following description. Include proper error handling, state management, and follow Flutter best practices.
-
-Description: {prompt}
+        return "❌ Hugging Face API token is required."
+
+    enhanced_prompt = f"""
+You are an expert Flutter/Dart developer.
+
+Task:
+Generate clean, production-ready Flutter/Dart code.
+
+Requirements:
+- Proper widget structure
+- Clear state management
+- Comments for complex logic
+- Error handling
+- Best practices
+
+User request:
+{prompt}
+
+Return ONLY Dart code.
+"""
+
+    headers = {
+        "Authorization": f"Bearer {api_token}",
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "inputs": enhanced_prompt,
+        "parameters": {
+            "max_new_tokens": 1024,
+            "temperature": 0.2,
+            "top_p": 0.95,
+            "do_sample": True
+        }
+    }
 
-Please provide:
-1. Complete Dart code with all necessary imports
-2. Proper widget structure
-3. State management if needed
-4. Comments explaining complex parts
-5. Error handling where appropriate
+    for model_id in MODELS:
+        try:
+            api_url = f"https://api-inference.huggingface.co/models/{model_id}"
+            response = requests.post(api_url, headers=headers, json=payload, timeout=40)
 
-Generate the code:"""
+            if response.status_code == 200:
+                data = response.json()
+                if isinstance(data, list) and "generated_text" in data[0]:
+                    return data[0]["generated_text"].strip()
 
-    try:
-        # Hugging Face Inference API endpoint
-        api_url = f"https://router.huggingface.co/models/{model_id}"
+            elif response.status_code in (503, 504):
+                continue  # model loading → try next
 
-        headers = {
-            "Authorization": f"Bearer {api_token}",
-            "Content-Type": "application/json"
-        }
+            elif response.status_code == 429:
+                return "⚠️ Rate limit reached. Try again later."
 
-        payload = {
-            "inputs": enhanced_prompt,
-            "parameters": {
-                "max_new_tokens": 2048,
-                "temperature": 0.1,
-                "top_p": 0.95,
-                "do_sample": True,
-                "return_full_text": False
-            }
-        }
+        except requests.exceptions.RequestException:
+            continue
 
-        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 generated_text.strip()
-            else:
-                return "Error: Unexpected response format from API"
-        elif response.status_code == 503:
-            return "Error: Model is currently loading. Please try again in a few moments."
-        elif response.status_code == 429:
-            return "Error: Rate limit exceeded. Please try again later."
-        else:
-            return f"Error: API request failed with status code {response.status_code}. Response: {response.text}"
-
-    except requests.exceptions.Timeout:
-        return "Error: Request timed out. The model might be busy."
-    except requests.exceptions.RequestException as e:
-        return f"Error: Network request failed: {str(e)}"
-    except Exception as e:
-        return f"Error: Unexpected error occurred: {str(e)}"
+    return "❌ All models failed. Try again later."
 
 # Gradio interface
 def create_interface():