Create app.py

app.py

@@ -0,0 +1,38 @@
+import os
+import requests
+import gradio as gr
+
+def run_llama_v2(prompt):
+    api_token = os.environ.get('REPLICATE_API_TOKEN')
+    if not api_token:
+        raise ValueError("REPLICATE_API_TOKEN environment variable not set.")
+
+    headers = {
+        'Authorization': f'Bearer {api_token}',
+    }
+
+    url = 'https://api.replicate.ai/v1/runs/replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1'
+    payload = {
+        'input': {
+            'prompt': prompt,
+        }
+    }
+
+    response = requests.post(url, headers=headers, json=payload)
+
+    if response.status_code == 200:
+        return response.json()
+    else:
+        raise Exception(f"Error running the model: {response.status_code} - {response.text}")
+
+iface = gr.Interface(
+    fn=run_llama_v2,
+    inputs=gr.inputs.Textbox(prompt="Type here..."),
+    outputs=gr.outputs.JSON(),
+    live=True,
+    title="Hugging Face Chatbot",
+    description="Interact with the Hugging Face Llama v2 chatbot model.",
+)
+
+if __name__ == "__main__":
+    iface.launch()