Spaces:
Running
Running
| from pathlib import Path | |
| import streamlit as st | |
| from googlesearch import search | |
| import pandas as pd | |
| import os | |
| from rag_sec.document_search_system import DocumentSearchSystem | |
| from chainguard.blockchain_logger import BlockchainLogger | |
| # Blockchain Logger | |
| blockchain_logger = BlockchainLogger() | |
| # Initialize DocumentSearchSystem | |
| def initialize_system(): | |
| """Initialize the DocumentSearchSystem and load documents.""" | |
| system = DocumentSearchSystem( | |
| neo4j_uri="neo4j+s://0ca71b10.databases.neo4j.io", | |
| neo4j_user="neo4j", | |
| neo4j_password="HwGDOxyGS1-79nLeTiX5bx5ohoFSpvHCmTv8IRgt-lY" | |
| ) | |
| system.retriever.load_documents() | |
| return system | |
| # Initialize the system | |
| system = initialize_system() | |
| # Streamlit Layout | |
| st.title("Memora: Advanced Search and News Insights") | |
| st.subheader("Personalized news and global updates at your fingertips") | |
| # Google Search: User-Specific News | |
| st.subheader("1. Latest News About You") | |
| user_name = st.text_input("Enter your name or handle to search for recent news", value="Talex Maxim") | |
| if st.button("Search News About Me"): | |
| if user_name: | |
| st.write(f"Searching Google for news about **{user_name}**...") | |
| try: | |
| results = list(search(user_name, num_results=5)) | |
| if results: | |
| st.success(f"Top {len(results)} results for '{user_name}':") | |
| user_news_data = {"URL": results} | |
| df_user_news = pd.DataFrame(user_news_data) | |
| st.dataframe(df_user_news) | |
| else: | |
| st.warning("No recent news found about you.") | |
| except Exception as e: | |
| st.error(f"An error occurred during the search: {str(e)}") | |
| else: | |
| st.warning("Please enter your name or handle to search.") | |
| # Google Search: Global News Categories | |
| st.subheader("2. Global News Insights") | |
| categories = ["Technology", "Sports", "Politics", "Entertainment", "Science"] | |
| news_results = {} | |
| if st.button("Fetch Global News"): | |
| try: | |
| for category in categories: | |
| st.write(f"Fetching news for **{category}**...") | |
| try: | |
| category_results = list(search(f"latest {category} news", num_results=3)) | |
| news_results[category] = category_results | |
| except Exception as e: | |
| news_results[category] = [f"Error fetching news: {str(e)}"] | |
| # Display results | |
| for category, articles in news_results.items(): | |
| st.write(f"### Top News in {category}:") | |
| for idx, article in enumerate(articles, start=1): | |
| st.write(f"{idx}. [Read here]({article})") | |
| except Exception as e: | |
| st.error(f"An error occurred while fetching global news: {str(e)}") | |
| # Document Search | |
| st.subheader("3. Search Documents") | |
| query = st.text_input("Enter your query (e.g., 'sports news', 'machine learning')") | |
| if st.button("Search Documents"): | |
| if query: | |
| result = system.process_query(query) | |
| if result["status"] == "success": | |
| st.success(f"Query processed successfully!") | |
| st.write("### Query Response:") | |
| st.write(result["response"]) | |
| st.write("### Retrieved Documents:") | |
| for idx, doc in enumerate(result["retrieved_documents"], start=1): | |
| st.write(f"**Document {idx}:**") | |
| st.write(doc[:500]) # Display the first 500 characters | |
| st.write("### Blockchain Details:") | |
| st.json(result["blockchain_details"]) | |
| elif result["status"] == "no_results": | |
| st.warning("No relevant documents found for your query.") | |
| elif result["status"] == "rejected": | |
| st.error(result["message"]) | |
| else: | |
| st.warning("Please enter a query to search.") | |
| # Debugging Section | |
| if st.checkbox("Show Debug Information"): | |
| st.write(f"Total documents loaded: {len(system.retriever.documents)}") | |