import streamlit as st
import requests
import os

# Define the endpoint and API key
api_url = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
api_key = os.getenv('HFSecret')

headers = {
    "Authorization": f"Bearer {api_key}"
}

# API call function
def call_huggingface_api(prompt):
    data = {"inputs": prompt, "parameters": {"max_length": 500, "temperature": 0.5}}
    response = requests.post(api_url, headers=headers, json=data)
    
    if response.status_code != 200:
        st.error(f"Error: {response.status_code} - {response.text}")
        return None
    
    return response.json()

# Streamlit layout
st.title("Sentiment Analysis, Summarization, and Keyword Extraction")

text_input = st.text_area("Enter text for analysis")

if st.button("Analyze"):
    if text_input:
        # Sentiment Analysis
        sentiment_prompt = f"Perform sentiment analysis on the following text: {text_input}"
        sentiment_result = call_huggingface_api(sentiment_prompt)
        if sentiment_result:
            st.write("Sentiment Analysis Result:", sentiment_result[0]['generated_text'])

        # Summarization
        summarization_prompt = f"Summarize the following text: {text_input}"
        summarization_result = call_huggingface_api(summarization_prompt)
        if summarization_result:
            st.write("Summarization Result:", summarization_result[0]['generated_text'])

        # Keyword Extraction (Using LLM, not RAKE)
        keyword_prompt = f"Extract important keywords from the following text: {text_input}"
        keyword_result = call_huggingface_api(keyword_prompt)
        if keyword_result:
            st.write("Keyword Extraction Result:", keyword_result[0]['generated_text'])
    else:
        st.warning("Please enter some text for analysis.")