Update app.py

app.py

@@ -46,7 +46,7 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 import os
 
-hf_token = os.getenv("HF_TOKEN")
+#hf_token = os.getenv("HF_TOKEN")
 
 client = InferenceClient("google/gemma-2-2b-it")
 
@@ -54,13 +54,14 @@ def respond(
     message,
     history: list[tuple[str, str]],
     #system_message,
-    user_message,
+    ##user_message,
     max_tokens,
     temperature,
     top_p,
 ):
     #messages = [{"role": "system", "content": system_message}]
-    messages = [{"role": "user", "content": user_message}]
+    ##messages = [{"role": "user", "content": user_message}]
+    messages = []
 
     for val in history:
         if val[0]:
@@ -75,32 +76,22 @@ def respond(
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
         token = message.choices[0].delta.content
 
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        #gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )