app.py

import streamlit as st
import pandas as pd
from transformers import pipeline
from sklearn.metrics.pairwise import cosine_similarity
from sentence_transformers import SentenceTransformer
import numpy as np

# Set modern page configuration
st.set_page_config(page_title="News Analyzer", layout="wide")

# Inject custom CSS for sleek dark blue theme with black fonts
st.markdown("""
    <style>
    /* Global Styling */
    body {
        background: #0b132b;
        color: black;
        font-family: 'Arial', sans-serif;
    }
    
    /* Header Styling */
    .custom-header {
        background: linear-gradient(to right, #1f4068, #1b1b2f);
        padding: 1.5rem;
        border-radius: 12px;
        text-align: center;
        color: white;
        font-size: 30px;
        font-weight: bold;
        box-shadow: 0px 4px 15px rgba(0, 217, 255, 0.3);
    }
    /* Card Container */
    .glass-container {
        background: rgba(255, 255, 255, 0.08);
        border-radius: 15px;
        padding: 25px;
        backdrop-filter: blur(15px);
        box-shadow: 0px 4px 20px rgba(0, 217, 255, 0.2);
        transition: transform 0.3s ease-in-out;
    }
    .glass-container:hover {
        transform: scale(1.02);
    }
    /* Buttons */
    .stButton>button {
        background: linear-gradient(45deg, #0072ff, #00c6ff);
        color: black;
        border-radius: 8px;
        padding: 14px 28px;
        font-size: 18px;
        transition: 0.3s ease;
        border: none;
    }
    .stButton>button:hover {
        transform: scale(1.05);
        box-shadow: 0px 4px 10px rgba(0, 255, 255, 0.5);
    }
    /* Text Input */
    .stTextInput>div>div>input {
        background-color: rgba(255, 255, 255, 0.1);
        border-radius: 8px;
        color: black;
        padding: 12px;
        font-size: 18px;
    }
    /* Dataframe Container */
    .dataframe-container {
        background: rgba(255, 255, 255, 0.1);
        padding: 15px;
        border-radius: 12px;
        color: black;
    }
    /* Answer Display Box - Larger */
    .answer-box {
        background: rgba(0, 217, 255, 0.15);
        padding: 35px;
        border-radius: 15px;
        border: 2px solid rgba(0, 217, 255, 0.6);
        color: black;
        font-size: 22px;
        text-align: center;
        margin-bottom: 20px;
        min-height: 150px;
        box-shadow: 0px 2px 12px rgba(0, 217, 255, 0.3);
        display: flex;
        align-items: center;
        justify-content: center;
        transition: all 0.3s ease;
    }
    /* CSV Display Box */
    .csv-box {
        background: rgba(255, 255, 255, 0.1);
        padding: 15px;
        border-radius: 12px;
        margin-top: 20px;
        box-shadow: 0px 2px 12px rgba(0, 217, 255, 0.3);
    }
    </style>
    """, unsafe_allow_html=True)

# Modern Header
st.markdown("<div class='custom-header'> 🧩 AI-Powered News Analyzer</div>", unsafe_allow_html=True)

# Load the Hugging Face model
pipe = pipeline("question-answering", model="distilbert/distilbert-base-cased-distilled-squad")

# Initialize sentence transformer model
sentence_model = SentenceTransformer('all-MiniLM-L6-v2')  # Pre-trained sentence model

# Responsive Layout - Uses full width
col1, col2 = st.columns([1.1, 1])

# Left Section - File Upload & CSV/Excel Display
with col1:
    st.markdown("<div class='glass-container'>", unsafe_allow_html=True)
    st.subheader("📂 Upload News Data")
    uploaded_file = st.file_uploader("Upload a CSV or Excel file", type=["csv", "xlsx"])
    
    if uploaded_file is not None:
        # Determine the file extension
        file_extension = uploaded_file.name.split('.')[-1]
        
        if file_extension == 'csv':
            df = pd.read_csv(uploaded_file)
        elif file_extension == 'xlsx':
            df = pd.read_excel(uploaded_file)
        
        # Download button
        st.download_button(
            label="⬇️ Download Processed Data",
            data=df.to_csv(index=False).encode('utf-8'),
            file_name="output.csv",
            mime="text/csv"
        )

        # CSV Preview Box
        st.markdown("<div class='csv-box'><h4 style='color: black;'>📜 CSV/Excel Preview</h4>", unsafe_allow_html=True)
        st.dataframe(df, use_container_width=True)
        st.markdown("</div>", unsafe_allow_html=True)

    st.markdown("</div>", unsafe_allow_html=True)

# Right Section - Q&A Interface
with col2:
    st.markdown("<div class='glass-container'>", unsafe_allow_html=True)
    st.subheader("🤖 AI Assistant")

    # Answer Display Box (Initially Empty)
    answer_placeholder = st.empty()
    answer_placeholder.markdown("<div class='answer-box'></div>", unsafe_allow_html=True)

    # Question Input
    st.markdown("### 🔍 Ask Your Question:")
    user_question = st.text_input("Enter your question here", label_visibility="hidden")  # Hides the label
    
    # Button & Answer Display
    if st.button("🔮 Get Answer"):
        if user_question.strip() and uploaded_file is not None:
            with st.spinner("⏳ Wait, our agent will look into that..."):
                # Extract the 1st column as context (0-indexed)
                context = df.iloc[:, 0].dropna().tolist()
                
                # Generate embeddings for the context rows and the question
                context_embeddings = sentence_model.encode(context)
                question_embedding = sentence_model.encode([user_question])
                
                # Calculate cosine similarity
                similarities = cosine_similarity(question_embedding, context_embeddings)
                top_indices = similarities[0].argsort()[-5:][::-1]  # Get top 5 similar rows
                
                # Prepare the top 5 similar context rows
                top_context = "\n".join([context[i] for i in top_indices])
                
                # Get answer from Hugging Face model using top context
                result = pipe(question=user_question, context=top_context)
                answer = result['answer']
        else:
            answer = "⚠️ Please upload a valid file first!"

        answer_placeholder.markdown(f"<div class='answer-box'>{answer}</div>", unsafe_allow_html=True)

    st.markdown("</div>", unsafe_allow_html=True)