From 58901d0376ad0a3f45847b124301cd1cc2489fb8 Mon Sep 17 00:00:00 2001 From: Classic298 <27028174+Classic298@users.noreply.github.com> Date: Tue, 2 Dec 2025 09:45:48 +0100 Subject: [PATCH] Update env-configuration.mdx --- docs/getting-started/env-configuration.mdx | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/docs/getting-started/env-configuration.mdx b/docs/getting-started/env-configuration.mdx index 83ecf74..5dec0df 100644 --- a/docs/getting-started/env-configuration.mdx +++ b/docs/getting-started/env-configuration.mdx @@ -2208,7 +2208,7 @@ The old individual environment variables (`DOCLING_OCR_ENGINE`, `DOCLING_OCR_LAN - `do_ocr` (bool): Enable OCR processing - `force_ocr` (bool): Force OCR even when text layer exists - `ocr_engine` (str): OCR engine to use (`tesseract`, `easyocr`, `ocrmac`, `rapidocr`, `tesserocr`) - - `ocr_lang` (str): OCR language codes (e.g., `eng,fra,deu,spa`) + - `ocr_lang` (list[str]): OCR language codes (e.g., `["en", "de", "fr"]`) - `pdf_backend` (str): PDF processing backend - `table_mode` (str): Table extraction mode - `pipeline` (str): Processing pipeline to use @@ -2223,8 +2223,10 @@ The old individual environment variables (`DOCLING_OCR_ENGINE`, `DOCLING_OCR_LAN { "do_ocr": true, "ocr_engine": "tesseract", - "ocr_lang": "eng,fra,deu,spa", + "ocr_lang": ["eng", "fra", "deu", "spa"], "force_ocr": false, + "pdf_backend": "dlparse_v4", + "table_mode": "accurate", "do_picture_description": true, "picture_description_mode": "api", "vlm_pipeline_model_api": "openai://gpt-4o"