{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/2"}],"enrichment":{"capability":"Docling Slim is a lightweight, modular SDK for parsing and converting documents (PDF, DOCX, HTML, Markdown, and others) into a unified representation, with optional extras for specific formats and features.","skillfed_tags":["document-conversion","modular-dependencies","pdf-parsing"],"use_cases":["Extract structured data from PDFs or Word documents for downstream gen AI applications or RAG pipelines","Build a lightweight document processing microservice with only the format handlers your application needs","Parse HTML or Markdown content into a unified document representation for content management systems","Add OCR capabilities to extract text from scanned documents or images on demand","Deploy document conversion in resource-constrained environments by selecting minimal extras"],"what_it_does":"Docling Slim is a modular, lightweight alternative to the full Docling package for developers who want fine-grained control over dependencies. It provides core document parsing and conversion capabilities with a base install of approximately 50MB, and you add only the format handlers and features you need through optional extras. The package converts PDFs, Word documents, Excel sheets, PowerPoint presentations, HTML, Markdown, LaTeX, and other formats into a unified document representation suitable for downstream processing like gen AI applications or data extraction.\n\nThe package is built on a foundation of standard Python libraries (pydantic, requests, tqdm) plus docling-core for the core parsing logic. You can optionally add PDF support (via pypdfium2 or docling-parse), Office format support, OCR engines (RapidOCR, EasyOCR, Tesseract), local or remote model inference, and CLI tools. This modular design makes it suitable for constrained environments, containerized deployments, or edge cases where you need only a subset of Docling's capabilities.","worth_installing":"Yes, if you need modular document parsing with minimal dependencies. The package is actively maintained, permissively licensed, and has low install friction. Install the full `docling` package instead if you want all standard features and CLI tools out of the box without managing extras. Docling Slim is the right choice when you need fine-grained control over what gets installed or are optimizing for deployment size."},"id":"docling-slim","links":{"html":"https://skillfed.io/packages/docling-slim","md":"https://skillfed.io/packages/docling-slim.md","pypi":"https://pypi.org/project/docling-slim/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-14","license_spdx":"MIT","license_treatment":"permissive","name":"docling-slim","python_support":"supports_current","summary":"Modular version of the Docling package: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."},"popularity":{"monthly_downloads":5699785,"position":2049,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"2.120.1"}