import os
import streamlit as st
import google.generativeai as genai
from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
from db import get_dataset_summary  # Import the dataset summary function

# Configure Gemini API key
GEMINI_API_KEY = os.getenv("gemini_api")
if GEMINI_API_KEY:
    genai.configure(api_key=GEMINI_API_KEY)
else:
    st.error("⚠️ Google API key is missing! Set it in Hugging Face Secrets.")

# Load pre-trained sentiment analysis model
MODEL_NAME = "cardiffnlp/twitter-roberta-base-sentiment"
try:
    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
    model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
    sentiment_pipeline = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
except Exception as e:
    st.error(f"❌ Error loading sentiment model: {e}")

# Load Topic Extraction Model
try:
    topic_pipeline = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
except Exception as e:
    st.error(f"❌ Error loading topic extraction model: {e}")

# Predefined topic labels for classification
TOPIC_LABELS = [
    "Technology", "Politics", "Business", "Sports", "Entertainment",
    "Health", "Science", "Education", "Finance", "Travel", "Food"
]

# Function to analyze sentiment using the pre-trained model
def analyze_sentiment(text):
    try:
        sentiment_result = sentiment_pipeline(text)[0]
        label = sentiment_result['label']
        score = sentiment_result['score']
        sentiment_mapping = {
            "LABEL_0": "Negative",
            "LABEL_1": "Neutral",
            "LABEL_2": "Positive"
        }
        return sentiment_mapping.get(label, "Unknown"), score
    except Exception as e:
        return f"Error analyzing sentiment: {e}", None

# Function to extract topic using zero-shot classification
def extract_topic(text):
    try:
        topic_result = topic_pipeline(text, TOPIC_LABELS)
        top_topic = topic_result["labels"][0]
        confidence = topic_result["scores"][0]
        return top_topic, confidence
    except Exception as e:
        return f"Error extracting topic: {e}", None

# Helper to check if the user query is about the dataset
def is_dataset_query(prompt):
    keywords = ["dataset", "data", "csv", "mongodb", "historical"]
    return any(keyword in prompt.lower() for keyword in keywords)

# Function to generate AI response along with sentiment and topic analysis
def chatbot_response(user_prompt):
    if not user_prompt:
        return None, None, None, None, None

    try:
        # If the query seems related to the dataset, fetch summary insights.
        if is_dataset_query(user_prompt):
            dataset_insights = get_dataset_summary()
            combined_prompt = (
                f"{user_prompt}\n\nDataset Insights:\n{dataset_insights}\n\n"
                "Provide a detailed answer that incorporates these dataset insights."
            )
        else:
            combined_prompt = user_prompt

        # Generate AI response using Gemini with the (possibly augmented) prompt.
        model_gen = genai.GenerativeModel("gemini-1.5-pro")
        ai_response = model_gen.generate_content(combined_prompt)

        # Perform sentiment analysis and topic extraction on the original user prompt.
        sentiment_label, sentiment_confidence = analyze_sentiment(user_prompt)
        topic_label, topic_confidence = extract_topic(user_prompt)

        return ai_response.text, sentiment_label, sentiment_confidence, topic_label, topic_confidence
    except Exception as e:
        return f"❌ Error: {e}", None, None, None, None