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)