{ "documents": [ { "pdf_file": "sample_hierarchy_1.pdf", "pages": [ { "page_number": 1, "blocks": [ { "text": "Document Title", "level": "H1", "bbox": { "left": 50.0, "top": 50.0, "right": 550.0, "bottom": 100.0 } }, { "text": "Introduction Section", "level": "H2", "bbox": { "left": 50.0, "top": 120.0, "right": 450.0, "bottom": 160.0 } }, { "text": "This is the introductory paragraph that provides background information about the document. It contains multiple sentences explaining the context and purpose of the content.", "level": "Body", "bbox": { "left": 50.0, "top": 170.0, "right": 550.0, "bottom": 250.0 } }, { "text": "Main Content Section", "level": "H2", "bbox": { "left": 50.0, "top": 270.0, "right": 450.0, "bottom": 310.0 } }, { "text": "Subsection A", "level": "H3", "bbox": { "left": 70.0, "top": 330.0, "right": 400.0, "bottom": 360.0 } }, { "text": "This subsection contains detailed information about topic A. The content is organized hierarchically for better readability and structure.", "level": "Body", "bbox": { "left": 70.0, "top": 370.0, "right": 550.0, "bottom": 450.0 } }, { "text": "Subsection B", "level": "H3", "bbox": { "left": 70.0, "top": 470.0, "right": 400.0, "bottom": 500.0 } }, { "text": "Further elaboration on topic B follows here. This demonstrates how hierarchical structure helps organize complex information.", "level": "Body", "bbox": { "left": 70.0, "top": 510.0, "right": 550.0, "bottom": 570.0 } }, { "text": "Conclusion", "level": "H2", "bbox": { "left": 50.0, "top": 590.0, "right": 350.0, "bottom": 630.0 } }, { "text": "In conclusion, this document has demonstrated the importance of proper document hierarchy. Structured documents are easier to parse, understand, and process automatically.", "level": "Body", "bbox": { "left": 50.0, "top": 640.0, "right": 550.0, "bottom": 720.0 } } ] } ] }, { "pdf_file": "sample_hierarchy_2.pdf", "pages": [ { "page_number": 1, "blocks": [ { "text": "Research Paper: Machine Learning", "level": "H1", "bbox": { "left": 50.0, "top": 40.0, "right": 550.0, "bottom": 90.0 } }, { "text": "Abstract", "level": "H2", "bbox": { "left": 50.0, "top": 110.0, "right": 350.0, "bottom": 150.0 } }, { "text": "Machine learning is a subset of artificial intelligence that focuses on enabling computer systems to learn from data. This paper provides a comprehensive overview of modern ML techniques.", "level": "Body", "bbox": { "left": 50.0, "top": 160.0, "right": 550.0, "bottom": 240.0 } }, { "text": "1. Introduction", "level": "H2", "bbox": { "left": 50.0, "top": 260.0, "right": 400.0, "bottom": 300.0 } }, { "text": "1.1 Background", "level": "H3", "bbox": { "left": 70.0, "top": 320.0, "right": 400.0, "bottom": 360.0 } }, { "text": "The field of machine learning has grown exponentially over the past decade. Novel algorithms and abundant data have enabled unprecedented advancements.", "level": "Body", "bbox": { "left": 70.0, "top": 370.0, "right": 550.0, "bottom": 440.0 } }, { "text": "1.2 Problem Statement", "level": "H3", "bbox": { "left": 70.0, "top": 460.0, "right": 400.0, "bottom": 500.0 } }, { "text": "Despite the progress made, several challenges remain in the field of machine learning. This work addresses key limitations in current approaches.", "level": "Body", "bbox": { "left": 70.0, "top": 510.0, "right": 550.0, "bottom": 580.0 } } ] } ] }, { "pdf_file": "sample_hierarchy_3.pdf", "pages": [ { "page_number": 1, "blocks": [ { "text": "Technical Documentation", "level": "H1", "bbox": { "left": 40.0, "top": 30.0, "right": 560.0, "bottom": 80.0 } }, { "text": "Installation Guide", "level": "H2", "bbox": { "left": 40.0, "top": 100.0, "right": 400.0, "bottom": 140.0 } }, { "text": "Prerequisites", "level": "H3", "bbox": { "left": 60.0, "top": 160.0, "right": 350.0, "bottom": 195.0 } }, { "text": "Before beginning the installation process, ensure you have the following requirements met. Operating system compatibility and necessary dependencies must be verified.", "level": "Body", "bbox": { "left": 60.0, "top": 205.0, "right": 560.0, "bottom": 280.0 } }, { "text": "System Requirements", "level": "H4", "bbox": { "left": 80.0, "top": 300.0, "right": 400.0, "bottom": 335.0 } }, { "text": "Minimum: 4GB RAM, 2GHz processor. Recommended: 8GB RAM, modern multi-core processor with SSD.", "level": "Body", "bbox": { "left": 80.0, "top": 345.0, "right": 560.0, "bottom": 400.0 } }, { "text": "Installation Steps", "level": "H3", "bbox": { "left": 60.0, "top": 420.0, "right": 350.0, "bottom": 455.0 } }, { "text": "Follow these numbered steps in order to complete the installation successfully. Each step builds on the previous one.", "level": "Body", "bbox": { "left": 60.0, "top": 465.0, "right": 560.0, "bottom": 520.0 } } ] } ] } ] }