chagu-demo / app.py
talexm
update
a463e6e
raw
history blame
4.92 kB
import streamlit as st
from googlesearch import search
import pandas as pd
from pathlib import Path
import os
from PIL import Image
from rag_sec.document_search_system import DocumentSearchSystem
from chainguard.blockchain_logger import BlockchainLogger
# Blockchain Logger
blockchain_logger = BlockchainLogger()
# Initialize DocumentSearchSystem
@st.cache_resource
def initialize_system():
"""Initialize the DocumentSearchSystem and load documents."""
home_dir = Path(os.getenv("HOME", "/"))
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 and load system
st.write("Initializing the Document Search System...")
system = initialize_system()
st.success("System initialized and documents loaded!")
# Directory for storing uploaded files
UPLOAD_DIR = "uploaded_files"
os.makedirs(UPLOAD_DIR, exist_ok=True)
# Streamlit Layout
st.title("Memora: Secure File Upload and Search with Blockchain & Neo4j")
st.subheader("Securely upload, organize, and query your files")
# Google Search Section
st.subheader("Find User Information via Google Search")
search_query = st.text_input("Enter a name or topic to search on Google")
if st.button("Google Search"):
if search_query:
try:
results = list(search(search_query, num_results=5)) # Fetch top 5 results
if results:
st.success(f"Top {len(results)} results for '{search_query}':")
result_data = {"URL": results}
df = pd.DataFrame(result_data)
st.dataframe(df)
else:
st.warning("No results found for the search query.")
except Exception as e:
st.error(f"An error occurred during the search: {str(e)}")
else:
st.warning("Please enter a search query.")
# File Upload Section
uploaded_files = st.file_uploader("Upload your files", accept_multiple_files=True, type=['jpg', 'jpeg', 'png', 'mp4', 'avi'])
if uploaded_files:
for uploaded_file in uploaded_files:
# Save file locally
file_path = os.path.join(UPLOAD_DIR, uploaded_file.name)
with open(file_path, "wb") as f:
f.write(uploaded_file.getbuffer())
st.success(f"File saved locally: {file_path}")
# Display uploaded file details
if uploaded_file.type.startswith('image'):
image = Image.open(uploaded_file)
st.image(image, caption=uploaded_file.name, use_column_width=True)
# Metadata Input
album = st.text_input(f"Album for {uploaded_file.name}", "Default Album")
tags = st.text_input(f"Tags for {uploaded_file.name} (comma-separated)", "")
# Log Metadata and Transaction
if st.button(f"Log Metadata for {uploaded_file.name}"):
metadata = {"file_name": uploaded_file.name, "tags": tags.split(','), "album": album}
blockchain_details = blockchain_logger.log_data(metadata)
blockchain_hash = blockchain_details.get("block_hash", "N/A")
# Use Neo4jHandler from DocumentSearchSystem to log the transaction
system.neo4j_handler.log_relationships(uploaded_file.name, tags, blockchain_hash, [album])
st.write(f"Metadata logged successfully! Blockchain Details: {blockchain_details}")
# Blockchain Integrity Validation
if st.button("Validate Blockchain Integrity"):
is_valid = blockchain_logger.is_blockchain_valid()
st.write("Blockchain Integrity:", "Valid βœ…" if is_valid else "Invalid ❌")
# Document Search Section
st.subheader("Search Documents")
# Query Input
query = st.text_input("Enter your query (e.g., 'sports news', 'machine learning')")
if st.button("Search"):
if query:
# Process query through the DocumentSearchSystem
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)}")