import openai
import gradio as gr
from gradio.components import Audio, Textbox
import os
import re
import tiktoken
from transformers import GPT2Tokenizer
import whisper
import pandas as pd
from datetime import datetime, timezone, timedelta
import notion_df
import concurrent.futures
from IPython.core.display import HTML
import spacy
from spacy import displacy

nlp = spacy.load("en_core_web_sm")

# Define the tokenizer and model
tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
model = openai.api_key = os.environ["OAPI_KEY"]

# Define the initial message and messages list
initialt = 'You are a Renal System USMLE Tutor. Respond with ALWAYS layered "bullet points" (listing rather than sentences) \
                   to all input with a fun mneumonics to memorize that list. But you can answer up to 1200 words if the user requests longer response. \
                    You are going to keep answer and also challenge the student to learn renal phsysiology.'
initial_message = {"role": "system", "content": initialt}
messages = [initial_message]
messages_rev = [initial_message]

# Define the answer counter
answer_count = 0

# Define the Notion API key
API_KEY = os.environ["NAPI_KEY"]

def transcribe(audio, text):
    global messages
    global answer_count
    transcript = {'text': ''} 
    input_text = []
    # Transcribe the audio if provided
    if audio is not None:
        audio_file = open(audio, "rb")
        transcript = openai.Audio.transcribe("whisper-1", audio_file, language="en")

    # Tokenize the text input
    if text is not None:
        # Split the input text into sentences
        sentences = re.split("(?<=[.!?]) +", text)
    
        # Initialize a list to store the tokens
        input_tokens = []
    
        # Add each sentence to the input_tokens list
        for sentence in sentences:
            # Tokenize the sentence using the GPT-2 tokenizer
            sentence_tokens = tokenizer.encode(sentence)
            # Check if adding the sentence would exceed the token limit
            if len(input_tokens) + len(sentence_tokens) < 1440:
                # Add the sentence tokens to the input_tokens list
                input_tokens.extend(sentence_tokens)
            else:
                # If adding the sentence would exceed the token limit, truncate it
                sentence_tokens = sentence_tokens[:1440-len(input_tokens)]
                input_tokens.extend(sentence_tokens)
                break
        # Decode the input tokens into text
        input_text = tokenizer.decode(input_tokens)
    
        # Add the input text to the messages list
    messages.append({"role": "user", "content": transcript["text"]+input_text})


    # Check if the accumulated tokens have exceeded 2096
    num_tokens = sum(len(tokenizer.encode(message["content"])) for message in messages)
    if num_tokens > 2096:
        # Concatenate the chat history
        chat_transcript = "\n\n".join([f"[ANSWER {answer_count}]{message['role']}: {message['content']}" for message in messages if message['role'] != 'system'])

        # Append the number of tokens used to the end of the chat transcript
        chat_transcript += f"\n\nNumber of tokens used: {num_tokens}\n\n"

        # Get the current time in Eastern Time (ET)
        now_et = datetime.now(timezone(timedelta(hours=-4)))
        # Format the time as string (YY-MM-DD HH:MM)
        published_date = now_et.strftime('%m-%d-%y %H:%M')

        # Upload the chat transcript to Notion
        df = pd.DataFrame([chat_transcript])
        notion_df.upload(df, 'https://www.notion.so/YENA-be569d0a40c940e7b6e0679318215790?pvs=4', title=str(published_date+'back_up'), api_key=API_KEY)

        # Reset the messages list and answer counter
        messages = [initial_message]
        messages.append({"role": "user", "content": initialt})
        answer_count = 0
        # Add the input text to the messages list
        messages.append({"role": "user", "content": input_text})
    else:
        # Increment the answer counter
        answer_count += 1

    # Generate the system message using the OpenAI API
    with concurrent.futures.ThreadPoolExecutor() as executor:
        prompt = [{"text": f"{message['role']}: {message['content']}\n\n"} for message in messages]
        system_message = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            max_tokens=2000
        )["choices"][0]["message"]
    # Wait for the completion of the OpenAI API call
        
    # Add the system message to the messages list
    messages.append(system_message)
        
    # Add the system message to the beginning of the messages list
    messages_rev.insert(0, system_message)
    # Add the input text to the messages list
    messages_rev.insert(0, {"role": "user", "content": input_text + transcript["text"]})

    # Concatenate the chat history
    chat_transcript = "\n\n".join([f"[ANSWER {answer_count}]{message['role']}: {message['content']}" for message in messages_rev if message['role'] != 'system'])

    # chat_transcript_copy = chat_transcript
    # Append the number of tokens used to the end of the chat transcript
    chat_transcript += f"\n\nNumber of tokens used: {num_tokens}\n\n"
    
    # Upload the chat transcript to Notion
    now_et = datetime.now(timezone(timedelta(hours=-4)))
    published_date = now_et.strftime('%m-%d-%y %H:%M')
    df = pd.DataFrame([chat_transcript])
    notion_df.upload(df, 'https://www.notion.so/YENA-be569d0a40c940e7b6e0679318215790?pvs=4', title=str(published_date), api_key=API_KEY)

    # Colorize the system message text
    colorized_system_message = colorize_text(system_message['content'])

    # Return the colorized chat transcript
    return colorized_system_message

    
def colorize_text(text):
    doc = nlp(text)
    colorized_text = ""

    for token in doc:
        if token.ent_type_:
            colorized_text += f'<span style="background-color: yellow;">{token.text_with_ws}</span>'
        elif token.pos_ in {'NOUN'}:
            colorized_text += f'<span style="color: blue;">{token.text_with_ws}</span>'
        else:
            colorized_text += token.text_with_ws

    return colorized_text


# Define the input and output components for Gradio
audio_input = Audio(source="microphone", type="filepath", label="Record your message")
text_input = Textbox(label="Type your message", max_length=4096)
output_text = Markdown()

# Define the Gradio interface
iface = gr.Interface(
    fn=transcribe,
    inputs=[audio_input, text_input],
    outputs=[output_text],
    title="Hold On, Pain Ends (HOPE)",
    description="Talk to Your USMLE Tutor HOPE",
    theme="compact",
    layout="vertical",
    allow_flagging=False
    )

# Run the Gradio interface
iface.launch(debug=True,enable_queue=True)