import openai
import os
from dotenv import load_dotenv

load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")


def generate_summarizer(
        max_tokens,
        temperature,
        top_p,
        frequency_penalty,
        question_type,
        question,
        answer
):
    res = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        max_tokens=int(max_tokens),
        temperature=float(temperature),
        top_p=float(top_p),
        frequency_penalty=float(frequency_penalty),
        messages=
        [
            {
                "role": "system",
                "content": "You are a IELTS examiner.",
            },
            {
                "role": "system",
                "content": f"The question you have to grade is of type {question_type} and is the following: {question}",
            },
            {
                "role": "system",
                "content": "Please provide a JSON object response with the overall grade and breakdown grades, "
                           "formatted as follows: {'overall': 7.0, 'task_response': {'Task Achievement': 8.0, "
                           "'Coherence and Cohesion': 6.5, 'Lexical Resource': 7.5, 'Grammatical Range and Accuracy': "
                           "6.0}}",
            },
            {
                "role": "system",
                "content": "Don't give explanations for the grades, just provide the json with the grades.",
            },
            {
                "role": "user",
                "content": f"Evaluate this answer according to ielts grading system: {answer}",
            },
        ],
    )
    return res["choices"][0]["message"]["content"]


import streamlit as st

# Set the application title
st.title("GPT-3.5 IELTS Examiner")

# qt_col, q_col = st.columns(2)

# Selection box to select the question type
# with qt_col:
question_type = st.selectbox(
    "What is the question type?",
    (
        "Writing Task 2"
    ),
)

# Provide the input area for question to be answered
# with q_col:
question = st.text_area("Enter the question:", height=100)

# Provide the input area for text to be summarized
answer = st.text_area("Enter the answer:", height=100)

# Initiate two columns for section to be side-by-side
# col1, col2 = st.columns(2)

# Slider to control the model hyperparameter
# with col1:
token = st.slider("Token", min_value=0.0, max_value=2000.0, value=1000.0, step=1.0)
temp = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.7, step=0.01)
top_p = st.slider("Top_p", min_value=0.0, max_value=1.0, value=0.9, step=0.01)
f_pen = st.slider("Frequency Penalty", min_value=-1.0, max_value=1.0, value=0.5, step=0.01)

# Showing the current parameter used for the model
# with col2:
with st.expander("Current Parameter"):
    st.write("Current Token :", token)
    st.write("Current Temperature :", temp)
    st.write("Current Nucleus Sampling :", top_p)
    st.write("Current Frequency Penalty :", f_pen)

# Creating button for execute the text summarization
if st.button("Grade"):
    st.write(generate_summarizer(token, temp, top_p, f_pen, question_type, question, answer))