document parsing / PDF and office-to-LLM conversion
Docling is a Python library that parses PDFs, Office docs, and other formats into a unified document representation and exports Markdown/JSON for generative AI workflows.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
if you need an ETL-oriented document processing pipeline with data connectors
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
if you want a similarly capable Python parser with a larger community and active development
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
if you need direct URL extraction alongside office and image formats in one library
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
if you need an on-premises, OCR-free extraction toolkit with benchmarking pipelines
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
if you want ORM-style document workflows for LLM extraction
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
if you need to handle multimedia formats in addition to documents
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
if you need a parser emphasizing lossless structure for LLM ingestion
File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
if you need a Rust-native parser for performance or embedding in Rust codebases
A fast, helpful, and open-source document parser
if you need a Java library for PDF parsing in JVM environments
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
if you prefer a vision-model-based approach to OCR and document extraction
OCR & Document Extraction using vision models
if you want a self-hosted server with a REST API for document structuring
Transforms PDF, Documents and Images into Enriched Structured Data
if you want a framework to build custom document AI pipelines rather than a one-shot parser
A Repo For Document AI
if you want a Rust core with Python/Node bindings for multi-format conversion
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
if you need a Rust-based document intelligence framework with code intelligence support
A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
if you primarily need OCR for 100+ languages on images/PDFs, not full-format parsing
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
if you need a research-grade document image parsing model for specific image inputs
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
if you only need high-accuracy PDF-to-Markdown/JSON conversion
Convert PDF to markdown + JSON quickly with high accuracy
if you need a PDF-only extraction toolkit and can accept AGPL licensing
A Comprehensive Toolkit for High-Quality PDF Content Extraction
if you need a one-shot long-horizon OCR model for complex documents
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
if you need multilingual OCR and layout analysis for images/PDFs, not office format conversion
OCR, layout analysis, reading order, table recognition in 90+ languages
if you need an OCR model specialized in tables, forms, and handwriting
OCR model that handles complex tables, forms, handwriting with full layout.
if you need a single vision-language model for multilingual layout parsing
Multilingual Document Layout Parsing in a Single Vision-Language Model
if you need an OCR-free document understanding transformer for research or specific image inputs
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
if you need a lightweight LMM-based document parsing model for low-resource or on-device use
A lightweight LMM-based Document Parsing Model
These projects were analysed and named docling among their alternatives. The relationship is not symmetric — how docling rates them is a separate judgement, made when docling is analysed in its own right.
calls docling “drop-in Python library with broader format support and active development; choose for a robust alternative with similar integration.”
Python tool for converting files and office documents to Markdown.
calls docling “Direct Python competitor, use when you want an MIT-licensed parser with similar features.”
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
calls docling “When you want an IBM-backed, MIT-licensed converter with strong support for complex document structures.”
Convert PDF to markdown + JSON quickly with high accuracy
calls docling “Choose for a Python-native parser with broad format coverage and active development; seed is Java-based with a Python SDK, so Docling fits Python-centric stacks.”
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
calls docling “Python document converter with rich structure understanding; choose for Python pipelines needing detailed output.”
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
calls docling “Choose if you want an MIT-licensed, highly configurable document conversion library with IBM backing.”
Toolkit for linearizing PDFs for LLM datasets/training
calls docling “when you need a mature, MIT-licensed document conversion library with strong PDF/Office support and active maintenance.”
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
calls docling “drop-in peer for high-quality document conversion to Markdown/JSON with MIT license and active development”
A Comprehensive Toolkit for High-Quality PDF Content Extraction
calls docling “choose it for a widely-adopted MIT-licensed document parser with excellent PDF/Office fidelity, if you don't need multimedia.”
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
calls docling “mature MIT-licensed Python library, fast and actively developed for document structure extraction.”
Transforms PDF, Documents and Images into Enriched Structured Data
calls docling “choose when you need a mature, format-agnostic Python library with deeper pipeline control and custom model support; seed offers a simpler all-in-one 7B approach.”
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
calls docling “End-to-end document conversion library; choose if you need layout analysis and multiple output formats.”
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
calls docling “choose it for an AI-powered document-to-Markdown/JSON toolkit from IBM, heavier and Python-based.”
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
calls docling “when you want an IBM-supported document conversion library with rich format preservation.”
OCR & Document Extraction using vision models
calls docling “Modern Python document-understanding library using ML; choose for unified structured output across many document formats.”
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
calls docling “Choose for a maintained, general-purpose document-to-Markdown library supporting many formats; Nougat is targeted at academic PDFs.”
Implementation of Nougat Neural Optical Understanding for Academic Documents
calls docling “Use when you want clean structured document data for LLMs through parsing rather than pixel-based search.”
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
calls docling “when you want an IBM-maintained Python document conversion library with strong Office/PDF support and MIT license.”
A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.
calls docling “choose when you need full document conversion to multiple formats with metadata and chunking, not just image-to-markdown.”
Multilingual Document Layout Parsing in a Single Vision-Language Model
calls docling “document conversion pipeline for gen AI, not LMM-based but same job”
A lightweight LMM-based Document Parsing Model