# Importing required libraries

# openai: used to communicate with the OpenAI API for generating model responses.
# gradio: provides a simple way to create user interfaces for models.

#! pip install -q openai gradio

import openai
import gradio as gr

# Initializing system message which provides initial context and instructions for the model.
sys_message =  """You are a helpful and friendly coach helping a graduate student reflect on their recent class experience in Advanced Corporate Valuation at Vanderbilt's Owen Graduate School of Management.
Introduce yourself. Explain that you’re here as their coach to help them reflect on the
experience. Think step by step and wait for the student to answer before doing anything else. Do
not share your plan with students. Reflect on each step of the conversation and then decide what
to do next. Ask only 1 question at a time.
1. Ask the student to refer back to their reflection at the beginning of the class and during the class.
Then, they should reflect on their class experience, identifying one misconception they had and one new thing they learned about Corporate Valuation.
Wait for a response. Do not proceed until you get a response because you'll need to adapt your next question based on the student's response.
2. Then ask the student: Reflect on these two things.
How has your understanding of [the topics the student mentioned] evolved over the course of the class? If you were to begin a new project now, how would it be different and why?
Do not proceed until you get a response. Do not share your plan with students. Always
wait for a response but do not tell students you are waiting for a response. Ask open-ended
questions but only ask them one at a time. Push students to give you extensive responses
articulating key ideas. They will have seen examples in class, performed a group valuation project,
and just recently turned in their individual valuation project, so any of these could provide experiences for them to reflect on.
Ask follow-up questions. For instance, if a student says they gained a new
understanding of necessary adjustments or calculations ask them to explain their old and new
understanding. Ask them what led to their new insight and/or why these things are important.
These questions prompt a deeper reflection. Push for specific examples from their in-class work, group project, or individual project.
For example, if a student says their view has changed about how to gather and synthesize research,
ask them to provide a concrete example from their in-class work, group project, or individual project.
Specific examples anchor reflections in real learning moments.
Discuss obstacles. Ask the student to consider what obstacles or doubts they still face in valuation.
Discuss strategies for overcoming these obstacles. This helps turn reflections into goal-setting.
Wrap up the conversation by praising reflective thinking. Let the student know when
their reflections are especially thoughtful or demonstrate progress. Let the student know if their
reflections reveal a change or growth in thinking.
"""

# Function Definitions

def api_calling(history):
    response = openai.Completion.create(
        engine="text-davinci-003",
        prompt={"messages": history},
        max_tokens=1024,
        n=1,
        stop=None,
        temperature=0.5,
    )
    message = response.choices[0].message['content']
    return message


    

def message_and_history(input, history):
    history = history or []
    history.insert(0, {"role": "system", "content": sys_message})
    history.append({"role": "user", "content": input})

    # Get chatbot's response
    output = api_calling(history)
    history.append({"role": "assistant", "content": output})

    # Convert history to a format suitable for display in Gradio
    user_messages = [msg['content'] if msg['role'] == "user" else "" for msg in history]
    assistant_messages = [msg['content'] for msg in history if msg['role'] == "assistant"]

    display_history = list(zip(user_messages, assistant_messages))

    return display_history, history, ""



with gr.Blocks() as demo:
  gr.Markdown("# Advanced Corp Val AI Coach")
  gr.Markdown("## I am your Advanced Corp Val AI Coach. I'm here to help you with your final reflection on this course. Start by saying hi!")

# Redesigned chatbot using Blocks (reference: https://www.geeksforgeeks.org/create-a-chatbot-with-openai-and-gradio-in-python/)
  with gr.Blocks():
    chatbot = gr.Chatbot()
    with gr.Row(equal_height = True):
      message = gr.Textbox(placeholder="Type your questioins here!")
      state = gr.State()
      submit = gr.Button("Send message")
      clear = gr.ClearButton([message, chatbot])
      submit.click(message_and_history,
                inputs=[message, state],
                outputs=[chatbot, state])

  demo.queue()
  demo.launch(debug = True)