From df6ab9be0ca04c84c47168785d62440c1998bf36 Mon Sep 17 00:00:00 2001 From: sjhddh Date: Fri, 24 Apr 2026 10:31:30 +0200 Subject: [PATCH] docs: correct image converter description in README (EXIF + LLM, not OCR) The supported-formats list claims "Images (EXIF metadata and OCR)", but the built-in `ImageConverter` does not perform OCR. Per the converter's own docstring, it extracts EXIF metadata (when exiftool is available) and generates a description via a multimodal LLM when an `llm_client` is configured. OCR is only available through the separate Azure Document Intelligence converter (`[az-doc-intel]` optional dependency), which is documented elsewhere in the README. This mislabeling has caused recurring user confusion, visible in issues #1601, #1344, #1170, and #255 where users expected OCR to work out of the box on images and scanned PDFs. The one-word change brings the README in line with the actual behavior of `ImageConverter`. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 652afc057..8cb930891 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 LLM-based description) - Audio (EXIF metadata and speech transcription) - HTML - Text-based formats (CSV, JSON, XML)