Create app.py

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import requests
+
+# Define the API settings
+API_TOKEN = "YOUR_HUGGING_FACE_API_TOKEN"  # Replace with your HF token
+MODEL_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-3.3-70B-Instruct"
+
+# Function to fetch a response from the model
+def chat_with_model(user_input):
+    headers = {
+        "Authorization": f"Bearer {API_TOKEN}",
+        "Content-Type": "application/json",
+    }
+    payload = {
+        "inputs": user_input,
+        "parameters": {
+            "max_length": 100,
+            "temperature": 0.7,
+            "top_k": 50,
+        },
+        "options": {"wait_for_model": True},
+    }
+
+    response = requests.post(MODEL_URL, headers=headers, json=payload)
+
+    if response.status_code == 200:
+        result = response.json()
+        if result and isinstance(result, list):
+            return result[0].get("generated_text", "No response received.")
+    else:
+        return f"Error {response.status_code}: {response.text}"
+
+    return "An error occurred while generating a response."
+
+# Gradio Interface
+def chatbot(user_message):
+    # Add a system message for context
+    system_message = "You are a helpful assistant using the Llama-3.3-70B model. Respond thoughtfully."
+    full_input = f"{system_message}\nUser: {user_message}\nAssistant:"
+    return chat_with_model(full_input)
+
+# Load your HTML UI
+with open("index.html", "r") as html_file:
+    custom_html = html_file.read()
+
+# Gradio App with Custom HTML
+app = gr.Interface(
+    fn=chatbot,
+    inputs="text",
+    outputs="text",
+    title="Chatbot with Llama-3.3-70B",
+)
+
+# Add the HTML to the app
+app.launch(
+    inline=True,  # Embed the app into the HTML
+    share=True,   # Make the app shareable
+    custom_html=custom_html,  # Use the custom HTML file
+)