import streamlit as st
from transformers import pipeline
import google.generativeai as genai
import json
import random

# Load the JSON data
with open('emotion_templates.json', 'r') as f:
    data = json.load(f)
    
# Configure Gemini (replace with your API key)
genai.configure(api_key="AIzaSyCYRYNwCU1f9cgJYn8pd86Xcf6hiSMwJr0")

model = genai.GenerativeModel('gemini-2.0-flash') 


def generate_text(prompt, context=""):
    """
    Generates text using the Gemini model.
    """
    try:
        response = model.generate_content(prompt)
        return response.text
    except Exception as e:
        print(f"Error generating text: {e}")
        return "I am sorry, I encountered an error while generating the text."

def create_prompt(emotion, topic = None):
  """
  Chooses a random prompt from the template list.
  """

  templates = data["emotion_templates"][emotion]
  prompt = random.choice(templates)

  if topic:
    prompt = prompt.replace("[topic/person]",topic)
    prompt = prompt.replace("[topic]",topic)
    prompt = prompt.replace("[person]",topic)
    prompt = prompt.replace("[object]",topic) # added object replace
    prompt = prompt.replace("[outcome]",topic) # added outcome replace
  subfix_prompt = "Make the generated text in the same language as the topic.\n"
  prefix_prompt = "## topic language and contant\n"+topic
  prompt = prefix_prompt + prompt + subfix_prompt
  return prompt

    

# 1. Emotion Detection Model (Using Hugging Face's transformer)
# Choose a suitable model -  'emotion-classification' is the task, you can specify a model from Hugging Face Model Hub.
emotion_classifier = pipeline("text-classification", model="AnasAlokla/multilingual_go_emotions")  # Or choose another model

# 2. Conversational Agent Logic
def get_ai_response(user_input, emotion_predictions):
    """Generates AI response based on user input and detected emotions."""


    dominant_emotion = None
    max_score = 0
    responses = None
    for prediction in emotion_predictions:
      if prediction['score'] > max_score:
        max_score = prediction['score']
        dominant_emotion = prediction['label']


    prompt_text = create_prompt(dominant_emotion,user_input)

    responses = generate_text(prompt_text)
    
    # Handle cases where no specific emotion is clear
    if dominant_emotion is None:
       return "Error for response"
    else:
        return responses

# 3. Streamlit Frontend
st.title("Emotionally Aware Chatbot")

# Input Text Box
user_input = st.text_input("Enter your message:", "")

if user_input:
    # Emotion Detection
    emotion_predictions = emotion_classifier(user_input)

    # Display Emotions
    st.subheader("Detected Emotions:")
    for prediction in emotion_predictions:
        st.write(f"- {prediction['label']}: {prediction['score']:.2f}") # Show emotion score.

    # Get AI Response
    ai_response = get_ai_response(user_input, emotion_predictions)

    # Display AI Response
    st.subheader("AI Response:")
    st.write(ai_response)