danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update docs

Browse source
This commit is contained in:
Yiorgis Gozadinos 2026-01-14 12:55:02 +02:00
parent 929c29250e
commit 7b6b2e2f38
No known key found for this signature in database
2 changed files with 15 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
CHANGELOG.md
View file

@ -1,6 +1,14 @@
# Changelog # Changelog
## [Unreleased] ## [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 ## [0.26.2] - 2026-01-13
### Changed ### Changed

9
docs/configuration/processing.md
View file

@ -35,7 +35,8 @@ processing:
# Image settings # Image settings
images_scale: 2.0 # Image scale factor 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) # VLM picture description (optional)
picture_description: picture_description:
@ -82,12 +83,16 @@ conversion_options:
```yaml ```yaml
conversion_options: conversion_options:
images_scale: 2.0 # Image resolution scale factor 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. - **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. - **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) #### 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. Use a Vision Language Model (VLM) to automatically describe images in documents. Descriptions become searchable text, improving RAG retrieval for visual content.