# from pydantic import NoneStr
import os
import mimetypes
import validators
import requests
import tempfile
import gradio as gr
from openai import OpenAI
import re
import json
from transformers import pipeline
import matplotlib.pyplot as plt
import plotly.express as px

class SentimentAnalyzer:
    def __init__(self):
        
        self.model="facebook/bart-large-mnli" 

        self.client = OpenAI()
        
    def analyze_sentiment(self, text):
        pipe = pipeline("zero-shot-classification", model=self.model)
        label=["positive","negative","neutral"]
        result = pipe(text, label)
        sentiment_scores= {result['labels'][0]:result['scores'][0],result['labels'][1]:result['scores'][1],result['labels'][2]:result['scores'][2]}
        sentiment_scores_str = f"Positive: {sentiment_scores['positive']:.2f}, Neutral: {sentiment_scores['neutral']:.2f}, Negative: {sentiment_scores['negative']:.2f}"
        return sentiment_scores_str
        
    def emotion_analysis(self,text):
        prompt = f""" Your task is to analyze {text} and predict the emotion using scores. Emotions are categorized into the following list: Sadness, Happiness, Joy, Fear, Disgust, and Anger. You need to provide the emotion with the highest score. The scores should be in the range of 0.0 to 1.0, where 1.0 represents the highest intensity of the emotion.
Please analyze the text and provide the output in the following format: emotion: score [with one result having the highest score]."""
        response = self.client.completions.create(
            model="text-davinci-003",
            prompt=prompt,
            temperature=1,
            max_tokens=60
        )

        message = response.choices[0].text.strip().replace("\n","")
        print(message)
        return message

    def analyze_sentiment_for_graph(self, text):
        pipe = pipeline("zero-shot-classification", model=self.model)
        label=["positive", "negative", "neutral"]
        result = pipe(text, label)
        sentiment_scores = {
            result['labels'][0]: result['scores'][0],
            result['labels'][1]: result['scores'][1],
            result['labels'][2]: result['scores'][2]
        }
        return sentiment_scores

    def emotion_analysis_for_graph(self,text):

        list_of_emotion=text.split(":")
        label=list_of_emotion[0]
        score=list_of_emotion[1]
        score_dict={
          label:float(score)
        }
        print(score_dict)
        return score_dict


class Summarizer:
    
    def __init__(self):
        self.client = OpenAI()       
        
    def generate_summary(self, text):
        model_engine = "text-davinci-003"
        prompt = f"""summarize the following conversation delimited by triple backticks.
                     write within 30 words.
                     ```{text}``` """
        completions = self.client.completions.create(
            model=model_engine,
            prompt=prompt,
            max_tokens=60,
            n=1,
            temperature=0
        )
        message = completions.choices[0].text.strip()
        return message

history_state = gr.State()
summarizer = Summarizer()
sentiment = SentimentAnalyzer()

class LangChain_Document_QA:

    def __init__(self):
        self.client = OpenAI() 
        
    def _add_text(self,history, text):
        history = history + [(text, None)]
        history_state.value = history
        return history,gr.update(value="", interactive=False)

    def _agent_text(self,history, text):
        response = text
        history[-1][1] = response
        history_state.value = history
        return history

    def _chat_history(self):
        history = history_state.value
        print("history_state  ",history)
        formatted_history = " "
        for entry in history:
            customer_text, agent_text = entry
            formatted_history += f"Customer: {customer_text}\n"
            if agent_text:
                formatted_history += f"Agent: {agent_text}\n"
        return formatted_history

    def _display_history(self):
        formatted_history=self._chat_history()
        summary=summarizer.generate_summary(formatted_history)
        return summary

    def _display_graph(self,sentiment_scores):
        labels = sentiment_scores.keys()
        scores = sentiment_scores.values()
        fig = px.bar(x=scores, y=labels, orientation='h', color=labels, color_discrete_map={"Negative": "red", "Positive": "green", "Neutral": "gray"})
        fig.update_traces(texttemplate='%{x:.2f}%', textposition='outside')
        fig.update_layout(height=500, width=200)
        return fig

    def _history_of_chat(self):
        history = history_state.value
        formatted_history = ""
        client=""
        agent=""
        for entry in history:
            customer_text, agent_text = entry
            client+=customer_text
            formatted_history += f"Customer: {customer_text}\n"
            if agent_text:
                agent+=agent_text
                formatted_history += f"Agent: {agent_text}\n"
        return client,agent


    def _suggested_answer(self,text):
        try:
            history = self._chat_history()
            start_sequence = "\nUser:"
            restart_sequence = "\n Employee Data Managing Assistant:"
            # prompt = 'your is Employee Management Assistant. your task is make a conversation from given employee details in json.end with thanking greetings at end of the conversation. 
            file_path = "employee_data.json"
            with open(file_path) as file:
                customer_details = json.load(file)
            prompt = f"""{history}{start_sequence}{text}{restart_sequence} give the polite answers to the user's questions. Use this data {customer_details}. give detailed analysis answer from given json.
                      if User say thanks or thankyou tone related messages You should not ask anything to end the conversation with greetings tone without ask 'Is there anything else I can help you with today?'.
            """
            response = self.client.completions.create(
                model="text-davinci-003",
                prompt=prompt,
                temperature=0,
                max_tokens=500
            )

            message = response.choices[0].text.strip()
            if  ":" in message:
              message = re.sub(r'^.*:', '', message)
            return message.strip()
        except:
            return "Hi, How can I help you?"
    

    def _text_box(self,customer_emotion,agent_emotion,agent_sentiment_score,customer_sentiment_score):
        agent_score = ", ".join([f"{key}: {value:.2f}" for key, value in agent_sentiment_score.items()])
        customer_score = ", ".join([f"{key}: {value:.2f}" for key, value in customer_sentiment_score.items()])
        return f"customer_emotion:{customer_emotion}\nagent_emotion:{agent_emotion}\nAgent_Sentiment_score:{agent_score}\nCustomer_sentiment_score:{customer_score}"

    def _on_sentiment_btn_click(self):
        client,agent=self._history_of_chat()

        customer_emotion=sentiment.emotion_analysis(client)
        customer_sentiment_score = sentiment.analyze_sentiment_for_graph(client)

        agent_emotion=sentiment.emotion_analysis(agent)
        agent_sentiment_score = sentiment.analyze_sentiment_for_graph(agent)

        scores=self._text_box(customer_emotion,agent_emotion,agent_sentiment_score,customer_sentiment_score)

        customer_fig=self._display_graph(customer_sentiment_score)
        customer_fig.update_layout(title="Sentiment Analysis",width=800)

        agent_fig=self._display_graph(agent_sentiment_score)
        agent_fig.update_layout(title="Sentiment Analysis",width=800)

        agent_emotion_score = sentiment.emotion_analysis_for_graph(agent_emotion)

        agent_emotion_fig=self._display_graph(agent_emotion_score)
        agent_emotion_fig.update_layout(title="Emotion Analysis",width=800)

        customer_emotion_score = sentiment.emotion_analysis_for_graph(customer_emotion)

        customer_emotion_fig=self._display_graph(customer_emotion_score)
        customer_emotion_fig.update_layout(title="Emotion Analysis",width=800)

        return scores,customer_fig,agent_fig,customer_emotion_fig,agent_emotion_fig


    def clear_func(self):
      history_state.clear()


    def gradio_interface(self):
      with gr.Blocks(css="style.css",theme="snehilsanyal/scikit-learn") as demo:

          with gr.Row():
            gr.HTML("""<center><img src="https://hakunamatatatech.com/wp-content/uploads/2019/06/logohms-160x34.png" alt="Image"></center>""")
          with gr.Row():  
            gr.HTML("""<center><h1 style="color:#f26d25">Generative AI CRM ChatBot</h1></center>""")
          with gr.Row():
            gr.HTML("<br>")
          chatbot = gr.Chatbot([], elem_id="chatbot").style(height=300)
          with gr.Row():
              with gr.Column(scale=0.50):
                  txt = gr.Textbox(
                      show_label=False,
                      placeholder="Customer",
                  ).style(container=False)
              with gr.Column(scale=0.50):
                  txt2 = gr.Textbox(
                      show_label=False,
                      placeholder="Agent",
                  ).style(container=False)

              with gr.Column(scale=0.40):
                  txt3 =gr.Textbox(
                      show_label=False,
                      placeholder="Chatbot_Suggestion",
                  ).style(container=False)
              with gr.Column(scale=0.10, min_width=0):
                  button=gr.Button(
                      value="🚀"
                  )
              with gr.Row(scale=0.50):
                  emptyBtn = gr.Button(
                      "🧹 New Conversation",
                  )
          with gr.Row():
              with gr.Column(scale=0.40):
                  txt4 =gr.Textbox(
                      show_label=False,
                      lines=4,
                      placeholder="Summary",
                  ).style(container=False)
              with gr.Column(scale=0.10, min_width=0):
                  end_btn=gr.Button(
                      value="End"
                  )
              with gr.Column(scale=0.40):
                  txt5 =gr.Textbox(
                      show_label=False,
                      lines=4,
                      placeholder="Sentiment",
                  ).style(container=False)

              with gr.Column(scale=0.10, min_width=0):
                  Sentiment_btn=gr.Button(
                      value="📊",callback=self._on_sentiment_btn_click
                  )
          with gr.Row():
            gr.HTML("""<center><h1 style="color:#fff">Sentiment and Emotion Score Graph</h1></center>""")
          with gr.Row():
              with gr.Column(scale=0.70, min_width=0):
                  plot =gr.Plot(label="Customer", size=(500, 600))
          with gr.Row():
              with gr.Column(scale=0.70, min_width=0):
                  plot_2 =gr.Plot(label="Agent", size=(500, 600))
          with gr.Row():
              with gr.Column(scale=0.70, min_width=0):
                  plot_3 =gr.Plot(label="Customer_Emotion", size=(500, 600))
          with gr.Row():
              with gr.Column(scale=0.70, min_width=0):
                  plot_4 =gr.Plot(label="Agent_Emotion", size=(500, 600))


          txt_msg = txt.submit(self._add_text, [chatbot, txt], [chatbot, txt])
          txt_msg.then(lambda: gr.update(interactive=True), None, [txt])
          txt.submit(self._suggested_answer,txt,txt3)
          button.click(self._agent_text, [chatbot,txt3], chatbot)
          txt2.submit(self._agent_text, [chatbot, txt2], chatbot).then(
              self._agent_text, [chatbot, txt2], chatbot
          )
          end_btn.click(self._display_history, [], txt4)
          emptyBtn.click(self.clear_func,[],[])
          emptyBtn.click(lambda: None, None, chatbot, queue=False)

          Sentiment_btn.click(self._on_sentiment_btn_click,[],[txt5,plot,plot_2,plot_3,plot_4])

      demo.launch(debug = True)

document_qa =LangChain_Document_QA()
document_qa.gradio_interface()