Open-source alternatives to Markitdown

This project is a comprehensive framework and toolkit for developing, optimizing, and deploying transformer-based models across multimodal, document intelligence, and natural language processing tasks. It provides a unified neural architecture that processes text, vision, audio, and document layout data through a shared set of weights, enabling researchers and developers to build foundational models that align cross-modal representations. The platform distinguishes itself through advanced training and inference strategies designed for large-scale deep learning. It incorporates specialized mec

Zerox is a multimodal document parser and OCR tool that uses vision models to convert PDF files and images into structured Markdown text. It functions as a visual layout extraction engine, leveraging large multimodal models to digitize documents while maintaining their original structural formatting. The system differentiates itself through the use of coordinate-based element mapping and multimodal layout analysis to identify structural elements like tables, charts, and headers. It utilizes rasterization to convert vector PDF pages into high-resolution bitmaps, ensuring consistent input for t

Olmocr is a distributed document processing framework designed to convert PDF and image files into structured markdown. It functions as a vision-based document parser that utilizes multimodal neural networks to interpret complex visual layouts and translate them into standardized text representations. The system operates as a remote inference orchestrator, offloading heavy document analysis tasks to external servers or cloud APIs to minimize local computational requirements. By employing a stateless worker architecture, it decouples document ingestion from inference, allowing for the distribu

This project is a comprehensive retrieval-augmented generation platform designed for building, managing, and deploying knowledge-based AI applications. It provides a unified environment for organizing datasets, configuring conversational chat assistants, and developing autonomous agents that execute multi-step reasoning workflows. By integrating document intelligence with advanced retrieval pipelines, the platform enables the creation of grounded, verifiable responses supported by traceable citations. The platform distinguishes itself through deep document understanding and sophisticated know

Docling is a multimodal content converter and document parser designed to transform PDFs, Office files, and HTML into structured Markdown or JSON for generative AI applications. It functions as an OCR document processor and a PDF layout analyzer that extracts tables, charts, and hierarchical structures while preserving the original page layout. The system operates as a local-first inference engine, allowing for the processing of sensitive data in air-gapped environments without external network connectivity. It can also be deployed as an API or a Model Context Protocol server to provide parsi

Dolphin is a multimodal layout analyzer and image-to-structure converter that transforms photographed or digital document images into machine-readable structured data. It functions as an LLM document parser, utilizing vision-language models to simultaneously predict spatial layout and text content. The system is designed as a concurrent document processor, employing parallel document parsing to process multiple elements across distributed compute nodes. This high-throughput approach reduces the total time required to convert large volumes of images into structured formats. The project covers

MinerU is a document parsing pipeline designed to transform unstructured files into machine-readable, structured data. It utilizes deep learning models to perform layout analysis, identifying document regions and extracting complex content such as mathematical expressions. By combining these neural network inferences with geometric heuristics, the system reconstructs the reading order and structural hierarchy of documents to ensure accurate data representation. The project distinguishes itself through a multi-stage processing workflow that integrates layout detection, optical character recogn

Unstract is an unstructured data extraction system and ETL pipeline orchestrator that uses large language models to convert documents, images, and scans into structured JSON. It provides a document extraction API for integrating these capabilities into external automation tools and includes a Model Context Protocol server to connect AI agents to structured information retrieval. The system ensures data accuracy through a verification tool featuring dual-model verification and human-in-the-loop review with coordinate-based document highlighting. It utilizes natural language extraction schemas

Stirling-PDF is a self-hosted document processing suite designed for secure, private file management. It functions as a comprehensive transformation engine that executes complex operations—such as merging, splitting, converting, and redacting documents—directly on the host machine. The platform provides both a browser-based interface for interactive editing and a programmatic, API-first architecture that allows for the automation of document workflows through standard HTTP requests. The project distinguishes itself through its focus on private, infrastructure-agnostic deployment and granular

docetl is an AI-powered document ETL tool and map-reduce orchestrator designed to transform large collections of unstructured documents into structured, queryable tables using language models. It provides a declarative pipeline framework for extracting, cleaning, and transforming data from sources such as PDFs and text files into predefined schemas. The project distinguishes itself through a semantic data integration suite that enables joining datasets and resolving duplicate entities based on embedding-based similarity. It includes an interactive prompt playground for developing and optimizi

Omniparse is a multimodal content parser and generative AI ingestion engine designed to convert documents, images, and multimedia into a uniform format. It functions as a data preprocessing pipeline that transforms diverse raw data sources into structured markdown to improve the performance of large language model workflows. The system extracts text and structural data from PDFs, images, audio, and video files. It includes a web crawler that converts dynamic website content into clean markdown and a multimodal transformation process that maps disparate input formats into a unified data schema

Unstructured is an enterprise-grade data orchestration engine designed to transform raw, unstructured files into structured, machine-readable formats. It functions as a comprehensive platform for document ingestion, partitioning, and enrichment, specifically engineered to prepare complex data for retrieval-augmented generation and agentic AI workflows. The platform distinguishes itself through its sophisticated document processing strategies, which combine rule-based extraction with vision-language models to handle diverse file layouts, tables, and images. It provides a modular architecture t

Kreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo

PyMuPDF is a comprehensive PDF manipulation library and document analysis tool. It serves as a text extraction tool, OCR engine, and image converter, providing a programmatic interface to edit, merge, split, and optimize PDF and Office documents. The project distinguishes itself through high-performance capabilities, including the use of C-bindings for low-level manipulation and parallelized page processing to accelerate workloads. It provides specialized conversion paths, such as transforming PDF content into Markdown for retrieval-augmented generation and large language model pipelines. It

Crawl4AI is an AI-powered web crawling and data extraction engine designed to transform complex web content into structured formats. It functions as a headless browser orchestrator, enabling the navigation of dynamic websites, the execution of custom scripts, and the capture of visual assets like screenshots and PDFs. By integrating language models directly into the extraction workflow, the system converts raw HTML into clean, structured data or Markdown files optimized for downstream ingestion. The platform distinguishes itself through a distributed, self-hosted infrastructure that manages l

Note-gen is an artificial intelligence-assisted note-taking application and knowledge management tool designed for local-first data ownership. It functions as a workspace that leverages language models to organize, summarize, and synthesize personal notes into structured documents while maintaining offline accessibility. The platform distinguishes itself through a multimodal workflow orchestrator that chains sequences of tasks to process text, images, and external data. By integrating vision-language models, it extracts information from visual inputs like screenshots and documents, converting

Jo is a command-line utility designed to construct and manipulate JSON objects and arrays directly from shell arguments and standard input. It functions as a data processing tool that transforms raw input into structured formats, enabling the generation of complex payloads for APIs, configuration files, and automated data pipelines. The tool distinguishes itself through its ability to resolve hierarchical data structures using delimiter-based path definitions and its integrated type-inference engine, which automatically casts input values into native boolean, numeric, or null types. Users can

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Tablib is a Python library designed for importing, exporting, and manipulating tabular datasets. It functions as a multi-format data converter and manager, allowing users to move information between different file standards. The library supports data transformation across CSV, JSON, YAML, and Excel formats. It provides a programmatic interface to manage these datasets by adding rows, filtering columns, and segregating records. The system uses a common internal representation and adapter-based mapping to normalize diverse input sources. This allows for consistent reading and writing routines

This tool is a command-line processor designed for querying, updating, and transforming structured data files. It functions as a versatile engine for manipulating YAML, JSON, TOML, and XML documents, allowing users to perform complex operations directly from the terminal. By utilizing a path-based expression language, it enables precise navigation and modification of data structures within configuration files and infrastructure-as-code workflows. What distinguishes this tool is its ability to perform in-place document mutations while preserving original formatting, comments, and metadata. It

WeasyPrint is a Python-based library and layout engine that converts HTML and CSS into printable PDF documents. It functions as a CSS paged media engine, translating web technologies into formatted files for automated document generation. The project implements CSS standards for print and paginated documents, allowing for the design of layouts specifically for printed pages. This includes a specialized pagination engine used to control page breaks, headers, and footers to create professional PDF outputs. Its capability surface covers server-side PDF rendering and the programmatic conversion

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

sChandra is a document processing platform that converts images, PDFs, Word documents, spreadsheets, and other formats into structured output such as HTML, Markdown, or JSON while preserving layout. It can also extract specific data fields from invoices, contracts, or reports using user-defined JSON schemas, with citations back to source locations. The service supports form filling in PDF and image documents, document generation from Markdown, and extraction of tracked changes from Word files. The platform distinguishes itself with pipeline-based processing chains that combine multiple proces

Easy-dataset is a comprehensive platform designed for the end-to-end management of machine learning datasets, specifically tailored for language and vision model fine-tuning. It functions as a centralized environment for the entire data lifecycle, encompassing the automated generation of synthetic training data, the structural organization of document collections, and the systematic annotation of individual data points. The platform distinguishes itself through its integrated evaluation and orchestration capabilities. It provides a dedicated suite for benchmarking models, featuring blind side

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Sparrow is an LLM document extraction platform and vision-based inference engine designed to convert images and PDFs into validated structured data. It functions as an agentic workflow orchestrator that chains classification, extraction, and validation tasks into multi-step pipelines. The system distinguishes itself through a backend-agnostic inference layer that manages models across local GPUs, Apple Silicon, and cloud providers. It employs coordinate-based visual grounding to map extracted text to precise bounding box coordinates and utilizes hint-based model steering to guide attention an