Update app.py

app.py

@@ -1,43 +0,0 @@
-import gradio as gr
-import requests
-import json
-
-# Set the base URL of your vLLM server
-BASE_URL = "https://q7i66ina1u82p8-8000.proxy.runpod.net/v1"
-
-# Pre-configured model details
-MODEL = "NousResearch/Meta-Llama-3-8B-Instruct"
-
-def chat_with_model(user_message):
-    # Prepare the chat messages in JSON format
-    payload = {
-        "model": MODEL,
-        "messages": [
-            {"role": "system", "content": "You are a knowledgeable assistant."},
-            {"role": "user", "content": user_message}
-        ]
-    }
-
-    # Headers to specify that the data sent is JSON
-    headers = {'Content-Type': 'application/json'}
-
-    # Make a POST request to the server
-    response = requests.post(f"{BASE_URL}/chat/completions", headers=headers, data=json.dumps(payload))
-    
-    # Check if the request was successful
-    if response.status_code == 200:
-        return response.json()['choices'][0]['message']['content']
-    else:
-        return "Failed to retrieve response from the model: " + str(response.status_code)
-
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=chat_with_model,
-    inputs=gr.Textbox(placeholder="Enter your message here..."),
-    outputs="text",
-    title="Chat with AI Model",
-    description="Send a message and get a response from a pre-configured AI model without knowing its details."
-)
-
-# Launch the application
-iface.launch()