Update app.py

app.py

@@ -3,7 +3,7 @@ import requests
 
 # Function to send your prompt to NVIDIA LLaMA 4 Scout
 def talk_to_llama(prompt):
-    url = "https://api.nvcf.nvidia.com/v2/completions"
+    url = "https://api.nvcf.nvidia.com/v1/messages"  # ✅ Correct endpoint
     headers = {
         "Authorization": "Bearer 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",
         "Content-Type": "application/json"
@@ -12,10 +12,11 @@ def talk_to_llama(prompt):
         "messages": [{"role": "user", "content": prompt}]
     }
     response = requests.post(url, headers=headers, json=data)
+    
     try:
         return response.json()["choices"][0]["message"]["content"]
-    except:
-        return "Something went wrong. Here's what the server said: " + str(response.text)
+    except Exception as e:
+        return f"Something went wrong. Here's what the server said:\n{response.text}"
 
 # Build the chatbot interface
 chat = gr.Interface(