Prepare Images
🤖 AI Drafted (Not reviewed)
Normalize images/PDF pages for OCR without modifying source files.
|
|
| Tool id |
prepare_images |
| Category |
transform |
| Uses a language model |
no |
| Needs a generative model |
no |
| Runs over many items |
yes |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Files (files) |
files |
yes |
Image or PDF files to prepare. |
Documents (documents) |
json |
no |
Document metadata for future preview-editor integration. |
What it emits
| Port |
Type |
Required |
What it is |
Prepared Files (output_files) |
files |
— |
Prepared image files. |
Documents (documents) |
json |
— |
Documents index-aligned with the prepared files (#4298). |
Options
| Option |
Type |
Default |
What it does |
autocontrast |
boolean |
no |
Apply autocontrast to improve low-contrast scans. |
compression_quality |
integer |
85 |
JPEG/WebP compression quality. |
grayscale |
boolean |
no |
Convert prepared images to grayscale for OCR. |
output_dir |
string |
— |
Optional output directory. Defaults to a temp directory. |
output_format |
string |
jpg |
Prepared image format. One of: jpg, png, tiff, webp. |
pdf_dpi |
integer |
200 |
DPI used when rendering PDF pages. |
The prompt it sends
This tool does not send a prompt — it does its work in code.