from pathlib import Path from haystack.components.converters import PyPDFToDocument source = Path("operations-handbook.pdf") converter = PyPDFToDocument(store_full_path=False) result = converter.run( sources=[source], meta={ "collection": "operations", "source_format": "pdf", }, ) documents = result["documents"] document = documents[0] print(f"documents: {len(documents)}") print("content:") print(document.content.strip()) print("source:", document.meta["file_path"]) print("collection:", document.meta["collection"]) print("format:", document.meta["source_format"])