From 7b6b2e2f388614d26dbe13be269f8d7cd3fb0552 Mon Sep 17 00:00:00 2001 From: Yiorgis Gozadinos Date: Wed, 14 Jan 2026 12:55:02 +0200 Subject: [PATCH] Update docs --- CHANGELOG.md | 8 ++++++++ docs/configuration/processing.md | 9 +++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9338a977..052b764b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,14 @@ # Changelog ## [Unreleased] +### Added + +- **Page Image Generation Control**: New `generate_page_images` option in `ConversionOptions` to control PDF page image extraction + - `generate_page_images: bool = True` - Enable/disable rendered page images (used by `visualize_chunk()`) + - Works with both `docling-local` and `docling-serve` converters + - For `docling-serve`, maps to `image_export_mode` API parameter (`embedded`/`placeholder`) + - Note: `generate_picture_images` (embedded figures/diagrams) works with local converter but has limited support in docling-serve + ## [0.26.2] - 2026-01-13 ### Changed diff --git a/docs/configuration/processing.md b/docs/configuration/processing.md index eeaaa214..6588b75f 100644 --- a/docs/configuration/processing.md +++ b/docs/configuration/processing.md @@ -35,7 +35,8 @@ processing: # Image settings images_scale: 2.0 # Image scale factor - generate_picture_images: false # Include embedded images in output + generate_page_images: true # Include rendered page images (for visualize_chunk) + generate_picture_images: false # Include embedded figure/diagram images # VLM picture description (optional) picture_description: @@ -82,12 +83,16 @@ conversion_options: ```yaml conversion_options: images_scale: 2.0 # Image resolution scale factor - generate_picture_images: false # Include embedded images in output + generate_page_images: true # Include rendered page images + generate_picture_images: false # Include embedded figure/diagram images ``` - **images_scale**: Scale factor for extracted images. Higher values = better quality but larger size. Typical range: 1.0-3.0. +- **generate_page_images**: When `true` (default), rendered images of each PDF page are included in the document. Required for `visualize_chunk()` to show visual grounding. When `false`, page images are excluded to reduce document size. - **generate_picture_images**: When `true`, embedded images (figures, diagrams) are included as base64-encoded data in the document. When `false` (default), images are excluded to reduce chunk size and avoid context bloat. +**Note:** With `docling-serve`, `generate_picture_images` has limited support - picture image data may not be returned in the JSON response. Page images work correctly with both local and remote converters. + #### Picture Description (VLM) Use a Vision Language Model (VLM) to automatically describe images in documents. Descriptions become searchable text, improving RAG retrieval for visual content.