added more comments

app.py

@@ -5,7 +5,7 @@ import random
 from huggingface_hub import InferenceClient
 
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-# name of llm chatbot accessed ^^
+# name of llm chatbot accessed ^^ or can use ' microsoft/phi-4 that's connected to the microsoft phi gen model
 
 def respond(message,history):
 
@@ -18,6 +18,7 @@ def respond(message,history):
     messages.append({'role': 'user','content': message})
 
     response = client.chat_completion(messages, max_tokens = 100)
+    #max tokens is a parameter to determine how long the message should be
 
     return response['choices'][0]['message']['content'].strip()