Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import os | |
| import shutil | |
| from SimpleRAG import read_doc, chunk_data, retrieve_answers | |
| from dotenv import load_dotenv | |
| # Load environment variables | |
| load_dotenv() | |
| # Initialize session state | |
| if 'docs_processed' not in st.session_state: | |
| st.session_state['docs_processed'] = False | |
| # Set page config | |
| st.set_page_config( | |
| page_title="Document Q&A System", | |
| page_icon="📚", | |
| layout="wide" | |
| ) | |
| # Title and description | |
| st.title("📚 Document Question & Answer System") | |
| st.markdown(""" | |
| This application allows you to upload documents and ask questions about their content. | |
| The system uses advanced RAG (Retrieval Augmented Generation) to provide accurate answers. | |
| """) | |
| # Check for required environment variables | |
| if not os.environ.get('OPENAI_API_KEY'): | |
| st.error("⚠️ OPENAI_API_KEY is not set in the environment variables!") | |
| st.stop() | |
| # Sidebar for document upload | |
| with st.sidebar: | |
| st.header("Document Upload") | |
| uploaded_files = st.file_uploader( | |
| "Upload your documents (DOCX format)", | |
| type=['docx'], | |
| accept_multiple_files=True | |
| ) | |
| if uploaded_files: | |
| # Create/clear documents directory | |
| if os.path.exists('documents'): | |
| shutil.rmtree('documents') | |
| os.makedirs('documents') | |
| # Save uploaded files | |
| for uploaded_file in uploaded_files: | |
| try: | |
| with open(os.path.join('documents', uploaded_file.name), 'wb') as f: | |
| f.write(uploaded_file.getbuffer()) | |
| st.success(f"✅ Successfully uploaded: {uploaded_file.name}") | |
| except Exception as e: | |
| st.error(f"❌ Error uploading {uploaded_file.name}: {str(e)}") | |
| if st.button("Process Documents"): | |
| try: | |
| with st.spinner("Processing documents..."): | |
| # Read and process documents | |
| documents = read_doc('documents/') | |
| if not documents: | |
| st.error("❌ No valid documents found in the uploaded files.") | |
| st.session_state['docs_processed'] = False | |
| else: | |
| chunks = chunk_data(documents) | |
| st.session_state['docs_processed'] = True | |
| st.success(f"✅ Successfully processed {len(documents)} documents into {len(chunks)} chunks!") | |
| except Exception as e: | |
| st.error(f"❌ Error processing documents: {str(e)}") | |
| st.session_state['docs_processed'] = False | |
| # Main content area | |
| st.header("Ask Questions") | |
| # Input for user question | |
| user_question = st.text_input("Enter your question about the documents:", key="user_question") | |
| # Process question | |
| if user_question: | |
| if st.session_state.get('docs_processed', False): | |
| try: | |
| with st.spinner("Finding answer..."): | |
| answer = retrieve_answers(user_question) | |
| # Display answer in a nice format | |
| st.markdown("### Answer") | |
| st.write(answer) | |
| except Exception as e: | |
| st.error(f"❌ Error generating answer: {str(e)}") | |
| else: | |
| st.warning("⚠️ Please upload and process documents first!") | |