# microsoft/markitdown

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/microsoft-markitdown).**

154,485 stars · 10,685 forks · Python · MIT

## Links

- GitHub: https://github.com/microsoft/markitdown
- awesome-repositories: https://awesome-repositories.com/repository/microsoft-markitdown.md

## Topics

`autogen` `autogen-extension` `langchain` `markdown` `microsoft-office` `openai` `pdf`

## Description

This project is an AI-powered document processing engine designed to transform diverse file formats into structured Markdown. By leveraging multimodal language models, it performs complex layout analysis and semantic text extraction, allowing for the conversion of both unstructured files and scanned images into machine-readable content.

The toolkit distinguishes itself through a modular, plugin-based architecture that orchestrates multi-stage extraction pipelines. Users can steer the parsing behavior by injecting custom instructions, enabling the system to adapt to domain-specific document structures and formatting requirements. This flexibility is supported by an integrated optical character recognition capability that ensures text recovery from embedded images during the conversion process.

The system provides both a command-line interface and a programmatic library, facilitating automated batch processing and custom integration into data pipelines. To ensure consistent performance across different environments, the project supports deployment within containerized architectures that encapsulate all necessary system-level dependencies and binaries.

## Tags

### Artificial Intelligence & ML

- [Model-Driven Text Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/document-data-intelligence/model-driven-text-extraction.md) — Leverages multimodal models to analyze visual document layouts and perform semantic extraction on embedded content.
- [Multimodal Layout Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/document-data-intelligence/multimodal-layout-analysis.md) — Employs multimodal language models to interpret visual document structures and perform semantic character recognition on embedded image content.
- [AI-Powered Data Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/document-data-intelligence/ai-powered-data-extraction.md) — Parses and extracts structured data from unstructured documents like invoices, forms, and reports using language models.
- [Document Intelligence Services](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/document-data-intelligence/document-intelligence-services.md) — Analyzes complex document layouts and extracts structured information using intelligent, model-driven processing services. ([source](https://github.com/microsoft/markitdown#readme))
- [Semantic Parsing Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/document-data-intelligence/semantic-parsing-tools.md) — Extracts structured data from unstructured files by using multimodal language models to interpret complex document layouts.
- [Prompt Injection Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/prompt-injection-strategies.md) — Enables dynamic instruction overriding to steer the underlying model's parsing behavior for domain-specific document structures and formatting.
- [OCR Configuration Plugins](https://awesome-repositories.com/f/artificial-intelligence-ml/optical-character-recognition/ocr-configuration-plugins.md) — Configures extraction plugins with external language model clients to automate text recognition from images during the conversion process. ([source](https://github.com/microsoft/markitdown/blob/main/packages/markitdown-ocr/README.md))
- [Prompt Libraries](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-libraries.md) — Allows users to override default extraction instructions to improve character recognition accuracy for specialized document types. ([source](https://github.com/microsoft/markitdown/blob/main/packages/markitdown-ocr/README.md))

### Content Management & Publishing

- [AI-Powered Extraction Engines](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/intelligent-extraction-frameworks/ai-powered-extraction-engines.md) — Applies machine learning to perform layout analysis and extract structured data from complex, multi-format files.
- [Document Automation Pipelines](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/document-automation-interfaces/document-automation-pipelines.md) — Automates the parsing, transformation, and conversion of binary and text document formats into structured Markdown.
- [Plugin-Based Document Parsers](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/document-automation-interfaces/plugin-based-document-parsers.md) — Utilizes a modular system of specialized parsers to transform diverse binary and text formats into a unified, structured representation.
- [Optical Character Recognition Engines](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/intelligent-extraction-frameworks/optical-character-recognition-engines.md) — Integrates advanced recognition models to convert scanned images and non-searchable documents into accessible, machine-readable text.
- [Markdown Converters](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing/format-specific-parsers/markdown-converters.md) — Converts diverse file formats into structured Markdown syntax to facilitate automated document processing and data integration. ([source](https://github.com/microsoft/markitdown#readme))
- [Document Conversion Utilities](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/content-processing/document-conversion-utilities.md) — Normalizes disparate file formats into a unified, lightweight syntax to facilitate seamless content management and cross-platform compatibility.

### Data & Databases

- [LLM-Powered Parsers](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-extraction-ingestion/document-processing-tools/llm-powered-parsers.md) — Interprets diverse file formats and generates structured, context-aware Markdown output using advanced language models.
- [LLM-Integrated Extraction Pipelines](https://awesome-repositories.com/f/data-databases/data-pipeline-orchestration/data-engineering-pipelines/llm-integrated-extraction-pipelines.md) — Orchestrates sequential workflows that chain file ingestion, layout analysis, and model-based generation into a unified pipeline.
- [Automated Document Ingestion](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-extraction-ingestion/document-processing-tools/automated-document-ingestion.md) — Streamlines the ingestion and transformation of diverse file formats into structured text for downstream data processing pipelines.
- [Document and LLM Preparation](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/document-llm-preparation.md) — Converts diverse document formats into structured text output by executing programmatic parsing logic to automate complex data extraction workflows. ([source](https://github.com/microsoft/markitdown#readme))

### Development Tools & Productivity

- [Document Conversion Toolkits](https://awesome-repositories.com/f/development-tools-productivity/project-scaffolding-config-code-generation/document-conversion-toolkits.md) — Provides a command-line utility that transforms diverse file formats into standardized, machine-readable Markdown for automated data pipelines.
- [Containerized Development Environments](https://awesome-repositories.com/f/development-tools-productivity/development-environment-management/development-environments/isolated-execution-environments/containerized-development-environments.md) — Encapsulates necessary system binaries and runtime dependencies within portable images to guarantee consistent execution across diverse host infrastructures.

### DevOps & Infrastructure

- [Asynchronous Pipeline Orchestrators](https://awesome-repositories.com/f/devops-infrastructure/cicd-pipeline-automation/workflow-orchestration/asynchronous-pipeline-orchestrators.md) — Coordinates multi-stage document processing tasks by chaining file ingestion, layout analysis, and text generation into sequential, automated workflows.
- [Dependency-Isolated](https://awesome-repositories.com/f/devops-infrastructure/containerization/runtime-deployment/dependency-isolated.md) — Packages runtime environments and system-level binaries into portable images to ensure consistent execution across heterogeneous infrastructures.

### Part of an Awesome List

- [Data Ingestion and Parsing](https://awesome-repositories.com/f/awesome-lists/data/data-ingestion-and-parsing.md) — Utility for converting office documents into Markdown.
- [Data Preprocessing](https://awesome-repositories.com/f/awesome-lists/data/data-preprocessing.md) — Lightweight tool for converting various file formats into Markdown.
- [Data Processing](https://awesome-repositories.com/f/awesome-lists/data/data-processing.md) — Tool for converting office documents and files to Markdown.
- [Document and File Processing](https://awesome-repositories.com/f/awesome-lists/data/document-and-file-processing.md) — Converts various office and data files into Markdown format.
- [Document Parsing and Extraction](https://awesome-repositories.com/f/awesome-lists/data/document-parsing-and-extraction.md) — Python utility for converting various file formats to Markdown.
- [Developer Tooling](https://awesome-repositories.com/f/awesome-lists/devtools/developer-tooling.md) — Facilitates AI-driven parsing and transformation of Markdown content.
- [Documentation and Processing](https://awesome-repositories.com/f/awesome-lists/devtools/documentation-and-processing.md) — Tool for converting various files to Markdown.
- [File System Access](https://awesome-repositories.com/f/awesome-lists/devtools/file-system-access.md) — Converts various file formats into Markdown for LLM consumption.