Merge pull request #568 from christianlouis/copilot/add-multi-language-ocr-support

feat(ocr): per-pipeline language override for multi-language OCR
This commit is contained in:
Christian Krakau-Louis
2026-03-08 23:11:41 +01:00
committed by GitHub
9 changed files with 816 additions and 19 deletions
+47
View File
@@ -404,6 +404,53 @@
</label>
</template>
<!-- ocr_language (only shown for ocr step) -->
<template x-if="stepModal.form.step_type === 'ocr'">
<div>
<label for="ocrLanguage" class="block text-sm font-medium text-gray-700 dark:text-gray-300 mb-1">
OCR Language
</label>
<select
id="ocrLanguage"
x-model="stepModal.form.config.ocr_language"
class="w-full border border-gray-300 dark:border-gray-600 rounded-md px-3 py-2 text-sm focus:outline-none focus:ring-2 focus:ring-blue-400 dark:bg-gray-700 dark:text-white"
>
<option value="auto">Auto (use system default)</option>
<option value="ara">Arabic</option>
<option value="chi_sim">Chinese (Simplified)</option>
<option value="chi_tra">Chinese (Traditional)</option>
<option value="ces">Czech</option>
<option value="dan">Danish</option>
<option value="nld">Dutch</option>
<option value="eng">English</option>
<option value="fin">Finnish</option>
<option value="fra">French</option>
<option value="deu">German</option>
<option value="ell">Greek</option>
<option value="heb">Hebrew</option>
<option value="hin">Hindi</option>
<option value="hun">Hungarian</option>
<option value="ita">Italian</option>
<option value="jpn">Japanese</option>
<option value="kor">Korean</option>
<option value="nor">Norwegian</option>
<option value="pol">Polish</option>
<option value="por">Portuguese</option>
<option value="ron">Romanian</option>
<option value="rus">Russian</option>
<option value="spa">Spanish</option>
<option value="swe">Swedish</option>
<option value="tha">Thai</option>
<option value="tur">Turkish</option>
<option value="ukr">Ukrainian</option>
<option value="vie">Vietnamese</option>
</select>
<p class="mt-1 text-xs text-gray-400">
Overrides the global language setting for Tesseract/EasyOCR. Azure and Mistral auto-detect the language.
</p>
</div>
</template>
<!-- Enabled -->
<label class="inline-flex items-center gap-2 cursor-pointer">
<input