from pathlib import Path from llama_index.core import SimpleDirectoryReader source_dir = Path("support_docs") directory_documents = SimpleDirectoryReader( input_dir=str(source_dir), required_exts=[".txt"], filename_as_id=True, ).load_data() billing_documents = SimpleDirectoryReader( input_files=[str(source_dir / "billing.txt")], filename_as_id=True, ).load_data() file_names = sorted( document.metadata["file_name"] for document in directory_documents ) metadata_fields = ["file_name", "file_path", "file_size", "file_type"] billing_text = billing_documents[0].get_content(metadata_mode="none").strip() assert file_names == ["billing.txt", "shipping.txt"] assert all(field in directory_documents[0].metadata for field in metadata_fields) assert len(billing_documents) == 1 assert "refund ticket 7421" in billing_text print(f"directory_documents={len(directory_documents)}") print("directory_files=" + ",".join(file_names)) print("metadata_fields=" + ",".join(metadata_fields)) print(f"selected_documents={len(billing_documents)}") print(f"selected_text={billing_text}")