Update app.py

app.py

@@ -1,45 +1,66 @@
 # app.py
-from transformers import AutoTokenizer, AutoModelForCausalLM
 import requests
 import gradio as gr
-import torch
 
-# Load the CodeParrot model and tokenizer (only once)
-model_name = "codeparrot/codeparrot-small"  # CodeParrot model
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+# Hugging Face Inference API configuration
+HF_API_KEY = "your_huggingface_api_key"  # Replace with your Hugging Face API key
+HF_API_URL = f"https://api-inference.huggingface.co/models/codeparrot/codeparrot-small"
 
 # Groq API configuration
 GROQ_API_KEY = "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"
 GROQ_API_URL = "https://api.groq.com/v1/completions"
 
+# Function to query Hugging Face Inference API
+def query_huggingface(prompt):
+    try:
+        headers = {
+            "Authorization": f"Bearer {HF_API_KEY}",
+            "Content-Type": "application/json"
+        }
+        data = {
+            "inputs": prompt,
+            "parameters": {
+                "max_length": 150  # Limit the length of the generated text
+            }
+        }
+        response = requests.post(HF_API_URL, headers=headers, json=data, timeout=30)  # Add timeout
+        response.raise_for_status()  # Raise an error for bad responses (4xx, 5xx)
+        return response.json()[0]["generated_text"]
+    except Exception as e:
+        return f"Error querying Hugging Face API: {str(e)}"
+
 # Function to query Groq API
 def query_groq(prompt):
-    headers = {
-        "Authorization": f"Bearer {GROQ_API_KEY}",
-        "Content-Type": "application/json"
-    }
-    data = {
-        "prompt": prompt,
-        "max_tokens": 150
-    }
-    response = requests.post(GROQ_API_URL, headers=headers, json=data)
-    return response.json()["choices"][0]["text"]
+    try:
+        headers = {
+            "Authorization": f"Bearer {GROQ_API_KEY}",
+            "Content-Type": "application/json"
+        }
+        data = {
+            "prompt": prompt,
+            "max_tokens": 150
+        }
+        response = requests.post(GROQ_API_URL, headers=headers, json=data, timeout=10)  # Add timeout
+        response.raise_for_status()  # Raise an error for bad responses (4xx, 5xx)
+        return response.json()["choices"][0]["text"]
+    except Exception as e:
+        return f"Error querying Groq API: {str(e)}"
 
 # Function to generate smart contract code
 def generate_smart_contract(language, requirements):
-    # Create a prompt for the model
-    prompt = f"Generate a {language} smart contract with the following requirements: {requirements}"
-    
-    # Use the CodeParrot model to generate code
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
-    outputs = model.generate(**inputs, max_length=300)  # Increased max_length for better results
-    generated_code = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    # Enhance the code using Groq API
-    enhanced_code = query_groq(generated_code)
-    
-    return enhanced_code
+    try:
+        # Create a prompt for the model
+        prompt = f"Generate a {language} smart contract with the following requirements: {requirements}"
+        
+        # Use Hugging Face Inference API to generate code
+        generated_code = query_huggingface(prompt)
+        
+        # Enhance the code using Groq API
+        enhanced_code = query_groq(generated_code)
+        
+        return enhanced_code
+    except Exception as e:
+        return f"Error generating smart contract: {str(e)}"
 
 # Custom CSS for a 3D CGI Figma-like feel
 custom_css = """