From a6ad2ac5d460f886c7d8685d62ac2ec76b70547c Mon Sep 17 00:00:00 2001
From: OpenClaw Agent <agent@openclaw.ai>
Date: Wed, 11 Mar 2026 22:21:32 +0800
Subject: [PATCH] docs: clarify OCR requires markitdown-ocr plugin

- Update feature list to note OCR requires markitdown-ocr plugin
- Add CLI usage example for OCR plugin
- Addresses issue #1601: OCR is not working
---
 README.md | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 6da3ee1d9..895ce0d76 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@ MarkItDown currently supports the conversion from:
 - PowerPoint
 - Word
 - Excel
-- Images (EXIF metadata and OCR)
+- Images (EXIF metadata and OCR — requires `markitdown-ocr` plugin)
 - Audio (EXIF metadata and speech transcription)
 - HTML
 - Text-based formats (CSV, JSON, XML)
@@ -162,6 +162,14 @@ print(result.text_content)
 
 If no `llm_client` is provided the plugin still loads, but OCR is silently skipped and the standard built-in converter is used instead.
 
+**CLI Usage:**
+
+```bash
+pip install markitdown-ocr
+export OPENAI_API_KEY="your-api-key"
+markitdown --use-plugins document_with_images.pdf -o document.md
+```
+
 See [`packages/markitdown-ocr/README.md`](packages/markitdown-ocr/README.md) for detailed documentation.
 
 ### Azure Document Intelligence