Update app.py

app.py

@@ -1,30 +1,36 @@
 import gradio as gr
 import requests
 
-# Function to send your prompt to NVIDIA LLaMA 4 Maverick
 def talk_to_llama(prompt):
-    url = "https://integrate.api.nvidia.com/v1/meta/llama-4-maverick-17b-128e-instruct"
+    url = "https://integrate.api.nvidia.com/v1/chat/completions"
     headers = {
-        "Authorization": "Bearer YOUR_API_KEY_HERE",  # Replace with your actual API key
+        "Authorization": "Bearer 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",  # Replace if you regenerate key
         "Content-Type": "application/json"
     }
     data = {
-        "messages": [{"role": "user", "content": prompt}]
+        "model": "meta/llama-4-maverick-17b-128e-instruct",
+        "messages": [
+            {"role": "user", "content": prompt}
+        ],
+        "max_tokens": 512,
+        "temperature": 1.0,
+        "top_p": 1.0,
+        "stream": False
     }
+
     response = requests.post(url, headers=headers, json=data)
-    
+
     try:
         return response.json()["choices"][0]["message"]["content"]
-    except Exception as e:
-        return f"Something went wrong. Here's what the server said:\n{response.text}"
+    except Exception:
+        return f"Error:\n{response.text}"
 
-# Build the chatbot interface
 chat = gr.Interface(
     fn=talk_to_llama,
     inputs="text",
     outputs="text",
     title="Chat with LLaMA 4 Maverick",
-    description="Ask anything! This chatbot uses NVIDIA’s LLaMA 4 Maverick 17B 128E Instruct model."
+    description="Ask anything! This chatbot uses NVIDIA’s 3.5M token LLaMA 4 Maverick 17B model."
 )
 
 chat.launch()