From b4602b0cab7c9aea59e1c92fd16fe33df6a8f8a1 Mon Sep 17 00:00:00 2001 From: Yiorgis Gozadinos Date: Thu, 27 Nov 2025 15:23:17 +0200 Subject: [PATCH] use `OcrAutoOptions` for automatic OCR engine selection. --- CHANGELOG.md | 8 ++++++++ haiku_rag_slim/haiku/rag/converters/docling_local.py | 4 ++-- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index a086dfeb..888356ed 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,14 @@ # Changelog ## [Unreleased] +### Changed + +- **Async Chunker**: `DoclingServeChunker` now uses `httpx.AsyncClient` instead of sync `requests` + +### Fixed + +- **OCR Options**: Fixed `DoclingLocalConverter` using base `OcrOptions` class which docling's OCR factory doesn't recognize. Now uses `OcrAutoOptions` for automatic OCR engine selection. + ## [0.19.2] - 2025-11-27 ### Changed diff --git a/haiku_rag_slim/haiku/rag/converters/docling_local.py b/haiku_rag_slim/haiku/rag/converters/docling_local.py index a1ebfbc8..59cadbb4 100644 --- a/haiku_rag_slim/haiku/rag/converters/docling_local.py +++ b/haiku_rag_slim/haiku/rag/converters/docling_local.py @@ -59,7 +59,7 @@ class DoclingLocalConverter(DocumentConverter): from docling.backend.docling_parse_backend import DoclingParseDocumentBackend from docling.datamodel.base_models import InputFormat from docling.datamodel.pipeline_options import ( - OcrOptions, + OcrAutoOptions, PdfPipelineOptions, TableFormerMode, TableStructureOptions, @@ -86,7 +86,7 @@ class DoclingLocalConverter(DocumentConverter): else TableFormerMode.ACCURATE ), ), - ocr_options=OcrOptions( + ocr_options=OcrAutoOptions( force_full_page_ocr=opts.force_ocr, lang=opts.ocr_lang if opts.ocr_lang else [], ),