Update app.py

app.py

@@ -1,11 +1,14 @@
 import os
 import gradio as gr
 import openai
-from gtts import gTTS
-
+from gtts import gTTS # Google Text To Speech
 
+# load the api key
 openai.api_key = os.environ["OPEN_AI_KEY"]
 
+# takes an audio file from the microphone
+# submits the raw audio to OpenAI for 
+# Speech to Text Translation
 def transcribe(audio): 
  audio_file = open(audio, "rb") 
  # Call the transcribe method with the file-like object
@@ -15,20 +18,33 @@ def transcribe(audio):
 
 
 
- 
+# Create a Gradio App using Blocks 
 with gr.Blocks() as demo:
+ # First message as instructions to OpenAI
+ # Establishes a State object to create a
+ # unique state for each user and on reload
  messages = gr.State(value=[{"role": "system", "content": "You are a therapist. Respond in less than 5 sentences."}])
 
+ # Takes the users transcribed audio as a string
+ # Takes the messages list as a reference
+ # Sends the ongoing chat log to OpenAI
  def botResponse(user_input, messages):
+ # adds the user input to the ongoing chat log
+ # and submits the log to OpenAI
  messages.append({"role": "user", "content": user_input})
  response = openai.ChatCompletion.create(
  model="gpt-3.5-turbo-0301",
  messages=messages
  )
- 
+
+ # Parse the response from OpenAI and store
+ # it in the chat log
  system_message = response["choices"][0]["message"]["content"]
  messages.append({"role": "assistant", "content": system_message})
- 
+
+ # Process the messages list to get the
+ # chat log into a string. Exclude the
+ # System responses from the string
  chat_transcript = ""
  for message in messages:
  if (message["role"] != "system"):
@@ -36,6 +52,11 @@ with gr.Blocks() as demo:
  
  return chat_transcript
 
+ # Gets the last message in the 
+ # chat log and uses GTTS to
+ # convert the last response into
+ # an audio file. Returns a path to
+ # the converted text as an mp3 file
  def giveVoice(messages):
  bot_message=messages[-1]
  
@@ -47,6 +68,10 @@ with gr.Blocks() as demo:
  
  return new_path
 
+ # Creates the Gradio interface objects
+ # The submit button triggers a cascade of
+ # events that each engage a different 
+ # component as input/output
  with gr.Row():
  with gr.Column(scale=1):
  user_audio = gr.Audio(source="microphone", type="filepath", label="Input Phrase")