# Convert PDFs and document images into agent-ready Markdown with Docext

> Run Docext locally or with a chosen model backend to turn PDFs and document images into structured Markdown for RAG, extraction, and review workflows.

- Skill: `agentskillexchange/convert-pdfs-and-document-images-into-agent-ready-markdown-w` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/convert-pdfs-and-document-images-into-agent-ready-markdown-w`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/convert-pdfs-and-document-images-into-agent-ready-markdown-w/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/convert-pdfs-and-document-images-into-agent-ready-markdown-w

---


# Convert PDFs and document images into agent-ready Markdown with Docext

Run Docext locally or with a chosen model backend to turn PDFs and document images into structured Markdown for RAG, extraction, and review workflows.

## Prerequisites

Python 3.11 environment, Docext package, source PDFs or document images, and a supported VLM backend such as vLLM, Ollama, or a configured hosted model provider

## Installation

Basic usage or getting-started notes:
- **On-premises deployment**: Run entirely on your own infrastructure (Linux, MacOS)
- For more details (Installation, Usage, and so on), please check out the [feature guide](https://github.com/NanoNets/docext/blob/main/EXT_README.md).

- Source: https://github.com/NanoNets/docext
- Extracted from upstream docs: https://raw.githubusercontent.com/NanoNets/docext/HEAD/README.md

## Documentation

- https://github.com/NanoNets/docext/blob/main/PDF2MD_README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/convert-pdfs-and-document-images-into-agent-ready-markdown-with-docext/)