"""
Example script showing how to use the document ingestion system programmatically.
"""
from ingestion import DocumentIngestion


def main():
    # Initialize the ingestion system
    ingestion = DocumentIngestion(embedding_model="all-MiniLM-L6-v2")
    
    # Example 1: Process PDFs
    pdf_paths = [
        # Add your PDF file paths here
        # "path/to/document1.pdf",
        # "path/to/document2.pdf",
    ]
    
    # Example 2: Process URLs
    urls = [
        # Add URLs here
        # "https://en.wikipedia.org/wiki/Artificial_intelligence",
        # "https://huggingface.co/docs/transformers",
    ]
    
    # Process documents
    if pdf_paths or urls:
        print("Processing documents...")
        documents = ingestion.process_documents(pdf_paths=pdf_paths, urls=urls)
        print(f"Processed {len(documents)} document chunks")
        
        # Build vector store
        ingestion.build_vector_store()
        
        # Save vector store
        ingestion.save("data/vector_store")
        
        # Example search
        query = "What is artificial intelligence?"
        results = ingestion.search(query, k=3)
        
        print(f"\nSearch results for: '{query}'")
        print("-" * 50)
        for i, result in enumerate(results, 1):
            print(f"\nResult {i}:")
            print(f"Source: {result['metadata']['source']}")
            print(f"Score: {result['score']:.4f}")
            print(f"Text: {result['text'][:200]}...")
    else:
        print("Please add PDF paths or URLs to the script to test ingestion.")


if __name__ == "__main__":
    main()