apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-19 18:45:15 +02:00
Code Issues Projects Releases Packages Wiki Activity

Merge remote-tracking branch 'upstream/dev' into feature/multi-agent-with-task-parallelization

Browse source
This commit is contained in:
CREDO23 2026-05-15 16:44:22 +02:00
commit 4980f9f1ba
193 changed files with 32777 additions and 565 deletions
Download patch file Download diff file Expand all files Collapse all files

12
surfsense_backend/app/services/docling_service.py
View file

@ -77,10 +77,16 @@ class DoclingService:
# Create pipeline options with version-safe attribute checking
pipeline_options = PdfPipelineOptions()
# Disable OCR (user request)
# Enable OCR so text-in-image (chart axes, ECG annotations,
# lab tables embedded as images, scanned pages, etc.) is
# lifted into the main markdown stream. This pairs with the
# vision-LLM picture-description pass downstream — OCR
# captures literal text; vision LLM captures the visual
# content. Together they give a faithful representation of
# PDFs that mix text and images.
if hasattr(pipeline_options, "do_ocr"):
pipeline_options.do_ocr = False
logger.info("⚠️ OCR disabled by user request")
pipeline_options.do_ocr = True
logger.info("✅ OCR enabled for embedded text-in-image extraction")
else:
logger.warning("⚠️ OCR attribute not available in this Docling version")