sync

app.py

@@ -4,7 +4,7 @@ import requests
 import sseclient
 import gradio as gr
 
-API_URL = "http://localhost:8000/v1/chat/completions"
+API_URL = "http://localhost:8000/v1/completions"
 
 
 def stream_completion(message, history, max_tokens, temperature, top_p, beta):
@@ -52,18 +52,19 @@ def stream_completion(message, history, max_tokens, temperature, top_p, beta):
 
 
 # ----------------------- UI ---------------------------------------------
-with gr.Blocks(title="🧪 Mixture of Inputs (MoI) Demo") as demo:
+with gr.Blocks(title="🎨 Mixture of Inputs (MoI) Demo") as demo:
     gr.Markdown(
-        "## 🧪 Mixture of Inputs (MoI) Demo  \n"
-        "Streaming local vLLM demo with dynamic **beta** adjustment."
+        "## 🎨 Mixture of Inputs (MoI) Demo  \n"
+        "Streaming vLLM demo with dynamic **beta** adjustment in MoI, higher beta means less blending."
     )
 
     # sliders first – all on one row
     with gr.Row():
-        max_tokens = gr.Slider(1, 2048, value=512, step=1, label="Max new tokens")
+        beta = gr.Slider(0.0, 10.0, value=1.0, step=0.1, label="MoI Beta")
         temperature = gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature")
         top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
-        beta = gr.Slider(0.0, 10.0, value=1.0, step=0.1, label="MoI Beta")
+        max_tokens = gr.Slider(1, 2048, value=512, step=1, label="Max new tokens")
+
 
     chatbot = gr.Chatbot(height=450)
     user_box = gr.Textbox(placeholder="Type a message and press Enter…", show_label=False)