Update app.py

app.py

@@ -1,3 +1,45 @@
 import gradio as gr
+import gradio as gr
+import os
+from huggingface_hub import InferenceClient
+
+# Read API key from environment variable
+hf_token = os.getenv("hf_token")
+
+# Initialize InferenceClient with the token from the environment
+client = InferenceClient(api_key=hf_token)
+
+# Function to get responses from the model
+def get_response(user_input):
+    messages = [
+        { "role": "system", "content": "you are xylaria 1.4 senoa, developed by sk md saad amin" },
+        { "role": "user", "content": user_input }
+    ]
+    
+    stream = client.chat.completions.create(
+        model="Qwen/QwQ-32B-Preview", 
+        messages=messages, 
+        temperature=0.5,
+        max_tokens=10240,
+        top_p=0.7,
+        stream=True
+    )
+    
+    response = ""
+    for chunk in stream:
+        response += chunk.choices[0].delta.content
+    return response
+
+# Set up the Gradio interface
+iface = gr.Interface(
+    fn=get_response, 
+    inputs=gr.Textbox(label="Your message", placeholder="Type your message here..."), 
+    outputs=gr.Textbox(label="Response", interactive=False),
+    title="Xylaria 1.4 Senoa Chatbot",
+    description="A chatbot powered by Xylaria 1.4 Senoa, developed by Sk Md Saad Amin."
+)
+
+# Launch the interface
+iface.launch()
 
 gr.load("models/Qwen/QwQ-32B-Preview").launch()