app.py: refactored and fixed warning

app.py

@@ -1,13 +1,8 @@
+import dotenv
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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")
-
-
-def respond(
+def respond_chat_completion(
     message,
     history: list[tuple[str, str]],
     system_message,
@@ -15,36 +10,57 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    messages_in = [
+        {
+            "role": "system",
+            "content": system_message
+        }
+        ]
 
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": val[0]})
+            messages_in.append(
+                {
+                    "role": "user",
+                    "content": val[0]
+                }
+                )
         if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+            messages_in.append(
+                {
+                    "role": "assistant",
+                    "content": val[1]
+                }
+                )
 
-    messages.append({"role": "user", "content": message})
+    messages_in.append(
+        {
+            "role": "user",
+            "content": message
+        }
+        )
 
-    response = ""
+    dotenv.load_dotenv(dotenv.find_dotenv())  # Load env. variable HF_TOKEN
+    client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-    for message in client.chat_completion(
-        messages,
+    messages_out = client.chat_completion(
+        messages_in,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        top_p=top_p
+        )
 
+    response = ""
+    for message in messages_out:
+        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,
+chatbot = gr.ChatInterface(
+    respond_chat_completion,
+    type='messages',
     additional_inputs=[
         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"),
@@ -61,4 +77,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    chatbot.launch()