Update app.py

app.py

@@ -1,14 +1,11 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
 import os
 import cohere
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
 COHERE_API_KEY = os.getenv("COHERE_API_KEY")
-client_cohere = cohere.Client(COHERE_API_KEY)
+client = cohere.ClientV2(COHERE_API_KEY)
+
 COHERE_MODEL = "command-r-plus"
 
 
@@ -20,7 +17,7 @@ def respond(
     top_p,
 ):
 
-    system_message = ('''
+    system_message = '''
     You are a friendly chatbot who is also a video game recommendation expert. 
     Your task is to help parents and guardians to find appropriate video games for their children.   
     Extract the child's age, preferred genre and multiplayer preference.
@@ -48,7 +45,7 @@ def respond(
     If the requested genre is rare, explain why certain alternatives may be more suitable for the child's age.
 
     Only suggest video games that exist and are well-known. Do NOT make up game titles.
-    ''')
+    '''
     
     messages = [{"role": "system", "content": system_message}]
 
@@ -60,37 +57,21 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    cohere_response = client_cohere.chat(
+    response = client.chat(
             messages=messages,
             model=COHERE_MODEL,
             temperature=temperature,
             max_tokens=max_tokens
         )
-    response = cohere_response.text
     yield response
 
-    '''
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        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.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"),
@@ -102,6 +83,7 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    '''
 )