Update app.py

app.py

@@ -1,29 +1,22 @@
-from huggingface_hub import InferenceClient
+from openai import InferenceClient
 import gradio as gr
 
-client = InferenceClient(
-    "google/gemma-7b-it"
-)
+client = InferenceClient("google/gemma-7b-it")
 
 def format_prompt(message, history):
     prompt = ""
     if history:
-        #<start_of_turn>userWhat is recession?<end_of_turn><start_of_turn>model
         for user_prompt, bot_response in history:
             prompt += f"<start_of_turn>user{user_prompt}<end_of_turn>"
             prompt += f"<start_of_turn>model{bot_response}"
     prompt += f"<start_of_turn>user{message}<end_of_turn><start_of_turn>model"
     return prompt
 
-def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
+def generate(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
     if not history:
         history = []
-        hist_len=0
     if history:
-        hist_len=len(history)
-        print(hist_len)
+        hist_len = len(history)
 
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -90,8 +83,7 @@ additional_inputs=[
 ]
 
 # Create a Chatbot object with the desired height
-chatbot = gr.Chatbot(height=450,
-                     layout="bubble")
+chatbot = gr.Chatbot(height=450, layout="bubble")
 
 with gr.Blocks() as demo:
     gr.HTML("<h1><center>🤖 Google-Gemma-7B-Chat 💬<h1><center>")
@@ -100,7 +92,6 @@ with gr.Blocks() as demo:
         chatbot=chatbot,  # Use the created Chatbot object
         additional_inputs=additional_inputs,
         examples=[["What is the meaning of life?"], ["Tell me something about Mt Fuji."]],
-
     )
 
-demo.queue().launch(debug=True)
+demo.queue().launch(debug=True)