MCPcopy Create free account

hub / github.com/NanoNets/docstrange / types & classes

Types & classes41 in github.com/NanoNets/docstrange

⨍ Functions 340◇ Types & classes 41↳ Endpoints 6
↓ 39 callersClassDocumentExtractor
Main class for converting documents to LLM-ready formats.
docstrange/extractor.py:27
↓ 36 callersClassConversionError
Raised when document conversion fails.
docstrange/exceptions.py:4
↓ 21 callersClassConversionResult
Result object with methods to export to different formats.
docstrange/result.py:689
↓ 13 callersClassFileNotFoundError
Raised when the input file is not found.
docstrange/exceptions.py:14
↓ 12 callersClassLayoutElement
Represents a layout element with position and content.
docstrange/pipeline/layout_detector.py:11
↓ 4 callersClassAuthService
Handles browser-based authentication for DocStrange using Auth0.
docstrange/services/auth_service.py:306
↓ 4 callersClassModelDownloader
Downloads pre-trained models from Hugging Face or Nanonets S3.
docstrange/pipeline/model_downloader.py:14
↓ 3 callersClassGPUConversionResult
Enhanced ConversionResult for GPU processing with Nanonets OCR capabilities.
docstrange/processors/gpu_processor.py:20
↓ 3 callersClassImageProcessor
Processor for image files (JPG, PNG, etc.) with OCR capabilities.
docstrange/processors/image_processor.py:16
↓ 3 callersClassNanonetsOCRService
Nanonets OCR implementation using NanonetsDocumentProcessor.
docstrange/pipeline/ocr_service.py:39
↓ 3 callersClassPDFProcessor
Processor for PDF files using PDF-to-image conversion with OCR.
docstrange/processors/pdf_processor.py:19
↓ 2 callersClassCloudProcessor
Processor for cloud-based document conversion using Nanonets API.
docstrange/processors/cloud_processor.py:213
↓ 2 callersClassDocumentSection
Represents a section in a document.
mcp_server_module/server.py:32
↓ 2 callersClassNeuralOCRService
Neural OCR implementation using docling's pre-trained models.
docstrange/pipeline/ocr_service.py:122
↓ 2 callersClassOllamaFieldExtractor
Service for extracting structured data from markdown using local Ollama models.
docstrange/services/ollama_service.py:10
↓ 1 callersClassAuthCallbackHandler
Handle OAuth callback from the browser.
docstrange/services/auth_service.py:22
↓ 1 callersClassCloudConversionResult
Enhanced ConversionResult for cloud mode with lazy API calls.
docstrange/processors/cloud_processor.py:16
↓ 1 callersClassDOCXProcessor
Processor for Microsoft Word DOCX and DOC files.
docstrange/processors/docx_processor.py:11
↓ 1 callersClassDocstrangeServer
MCP Server for document processing using docstrange.
mcp_server_module/server.py:52
↓ 1 callersClassDocumentCache
Cache for processed documents.
mcp_server_module/server.py:42
↓ 1 callersClassExcelProcessor
Processor for Excel files (XLSX, XLS) and CSV files.
docstrange/processors/excel_processor.py:15
↓ 1 callersClassGPUProcessor
Processor for image files and PDFs with Nanonets OCR capabilities.
docstrange/processors/gpu_processor.py:256
↓ 1 callersClassHTMLProcessor
Processor for HTML files using markdownify for conversion.
docstrange/processors/html_processor.py:15
↓ 1 callersClassLayoutDetector
Handles layout detection and markdown generation.
docstrange/pipeline/layout_detector.py:38
↓ 1 callersClassMarkdownToHTMLConverter
Comprehensive markdown to HTML extractor.
docstrange/result.py:356
↓ 1 callersClassMarkdownToJSONParser
Comprehensive markdown to structured JSON parser.
docstrange/result.py:13
↓ 1 callersClassNanonetsDocumentProcessor
Neural Document Processor using Nanonets OCR model.
docstrange/pipeline/nanonets_processor.py:12
↓ 1 callersClassNetworkError
Raised when network operations fail (e.g., URL fetching).
docstrange/exceptions.py:19
↓ 1 callersClassNeuralDocumentProcessor
Neural Document Processor using docling's pre-trained models.
docstrange/pipeline/neural_document_processor.py:61
↓ 1 callersClassPPTXProcessor
Processor for PowerPoint files (PPT, PPTX).
docstrange/processors/pptx_processor.py:15
↓ 1 callersClassTXTProcessor
Processor for plain text files.
docstrange/processors/txt_processor.py:11
↓ 1 callersClassURLProcessor
Processor for URLs and web pages.
docstrange/processors/url_processor.py:14
↓ 1 callersClassUnsupportedFormatError
Raised when the input format is not supported.
docstrange/exceptions.py:9
Class
docstrange/static/script.js:3
ClassBaseProcessor
Base class for all document processors.
docstrange/processors/base.py:12
ClassDocStrangeApp
docstrange/static/script.js:3
ClassInternalConfig
docstrange/config.py:3
ClassOCRService
Abstract base class for OCR services.
docstrange/pipeline/ocr_service.py:11
ClassOCRServiceFactory
Factory for creating OCR services based on configuration.
docstrange/pipeline/ocr_service.py:190
ClassTestConversionResult
Test cases for ConversionResult class.
tests/test_converter.py:116
ClassTestFileConverter
Test cases for DocumentExtractor class.
tests/test_converter.py:10