Update app.py

app.py

@@ -1,46 +1,44 @@
+import os
 import requests
-import json
-
-# Replace with your actual API endpoint and API key
-API_URL = "https://api.nvidia.com/llama-3.1-nemotron-ultra-253b-v1"
-API_KEY = "your_api_key_here"
-
-# Your cinematic scene prompt
-cinematic_prompt = """
-INT. ANCIENT MARATHA FORT - NIGHT
-
-The rain lashes against the stone walls as SAMBHAJI MAHARAJ, regal and fierce, stands silhouetted by lightning atop the ramparts. His eyes burn with defiance. Thunder cracks. Below, a vast Mughal army advances. The drums of war echo in the mist. SAMBHAJI slowly unsheathes his sword — engraved with ancient Maratha inscriptions.
-
-CAMERA: Low-angle, slow dolly-in as wind catches his cape.
-LIGHTING: Moonlit with flickering torches, rain reflections.
-SFX: Thunder, horses in distance, war drums.
-
-[Generate scene narration in immersive cinematic prose.]
-"""
-
-# Payload for the API
-payload = {
-    "model": "llama-3.1-nemotron-ultra-253b-v1",
-    "prompt": cinematic_prompt,
-    "temperature": 0.7,
-    "top_p": 0.9,
-    "max_tokens": 1024,
-    "stop": ["\n\n", "[END]"]
-}
-
-# Headers
-headers = {
-    "Content-Type": "application/json",
-    "Authorization": f"Bearer {API_KEY}"
-}
-
-# Safe API Call
-try:
-    response = requests.post(API_URL, json=payload, headers=headers)
-    response.raise_for_status()  # Raise error for non-2xx responses
-    data = response.json()
-    print("Generated Output:\n", data.get("text", data))  # Adjust based on actual response format
-except requests.exceptions.RequestException as e:
-    print("API Request failed:", str(e))
-except json.JSONDecodeError as e:
-    print("JSON Decode Error:", str(e))
+import gradio as gr
+
+# Retrieve the NVIDIA API key from Hugging Face Space secrets
+NVIDIA_API_KEY = os.getenv("NVIDIA_API_KEY")
+if not NVIDIA_API_KEY:
+    raise ValueError("NVIDIA_API_KEY not found in environment variables")
+
+# Function to generate a response using the NVIDIA API
+def generate_response(input_text):
+    # Placeholder NVIDIA API endpoint (replace with the actual endpoint)
+    url = "https://api.nvidia.com/v1/models/llama-3.1-nemotron-ultra-253b-v1/generate"
+    headers = {
+        "Authorization": f"Bearer {NVIDIA_API_KEY}",
+        "Content-Type": "application/json",
+    }
+    data = {
+        "prompt": input_text,
+        "max_tokens": 100,  # Adjust as needed
+        "temperature": 0.7,  # Adjust for creativity/control
+        # Add other parameters as required by the NVIDIA API
+    }
+    try:
+        response = requests.post(url, headers=headers, json=data)
+        response.raise_for_status()  # Raise an exception for HTTP errors
+        output = response.json()
+        # Adjust the key based on the actual API response format
+        return output["generated_text"]
+    except requests.exceptions.RequestException as e:
+        return f"Error: {str(e)}"
+
+# Set up the Gradio interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(label="Input your query"),
+    outputs=gr.Textbox(label="Response"),
+    title="Llama 3.1 Nemotron Ultra 253B v1",
+    description="Ask a question and get a response from the AI model."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()