Test the advanced OCR service.

Test all sample files in the sample_documents folder.

Test basic functionality of the enhanced library.

Test basic markdown structure parsing.

Test batch processing capabilities.

Test complex heading hierarchy.

Test different content types parsing.

Test conversion of a single document to a specific format.

Test empty or whitespace-only content.

Test error handling functionality.

Test field extraction functionality.

Test extraction capabilities on downloaded and created files.

Test extraction capabilities on downloaded files.

Test the HTML generation with various markdown elements.

Test the layout classification logic.

Test the enhanced layout detection functionality.

Test if the output is ready for LLM integration.

Test LLM integration with OCR results.

Test the quality of markdown output.

Test converting a markdown string to structured JSON.

Test the model downloader.

Test content without headers.

Test OCR capabilities with a sample image.

Test OCR capabilities specifically.

Compare OCR vs non-OCR results.

Test OCR with detailed debugging.

Test OCR functionality if available.

Test the OCR service factory with different providers.

Test OCR capabilities with the real sample.png file.

Test PaddleOCR model download functionality.

Test the PDF processor directly with different configurations.

Test the enhanced PDF processor with OCR support and markdown output.

Test specific processor functionality.

Test JSON schema extraction functionality.

Test URL extraction capabilities.

Cleanup resources.

Cleanup resources.

Initialize the file extractor. Args: preserve_layout: Whether to preserve document layout include_images: Whe

Initialize the parser.

Initialize the extractor.

Initialize the conversion result. Args: content: The converted content as string metadata: Optional metadata

Initialize Ollama field extractor. Args: base_url: Ollama server URL (default: http://localhost:11434) model:

Initialize the layout detector.

Initialize the model downloader. Args: cache_dir: Directory to cache downloaded models

Initialize the Neural Document Processor with Nanonets OCR.

Initialize the service.

Initialize the service.

Initialize the Neural Document Processor.

Initialize the processor. Args: preserve_layout: Whether to preserve document layout include_images: Whether

Representation of the result object.

String representation of the result.

Clean up the extracted Excel content. Args: content: Raw Excel text content Returns: Cle

Convert a PDF page to an image file. Args: pdf_path: Path to the PDF file page_num: Page number (0-based)

Extract OCR text from ImageProcessor result. Args: result: ConversionResult from ImageProcessor Retu

Format page content as markdown with enhanced structure. Args: text: Extracted text page_num: Page number

Check if all required models are cached. Returns: True if all required models are cached, False otherwise

Perform browser-based authentication and update API key. Args: force_reauth: Force re-authentication even if cac

Handle tool calls.

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check (or URL)

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Check if this processor can handle the given file. Args: file_path: Path to the file to check Return

Get center X coordinate.

Get center Y coordinate.

Convert text blocks to structured markdown with proper hierarchy.

Convert a file with specific output type for cloud processing. Args: file_path: Path to the file to extract o

Create a LayoutElement from a block of text data.

Handle GET request from OAuth callback.

API endpoint for document extraction.

Export as HTML with GPU processing styling.

Export as markdown without GPU processing metadata.

Export as markdown.

Extract text using Neural OCR (docling models).

Extract text from image using neural OCR.

Export as plain text.

Extract text with layout awareness using Nanonets OCR. Note: Nanonets OCR already provides layout-aware extraction, so this m

Extract text with layout awareness using Neural OCR.

Extract text with layout awareness using neural models.

Get information about cached models. Returns: Dictionary with cache information

Get information about the OCR processing used. Returns: Dictionary with OCR processing information