mcelwain
/
document-processor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use field extraction vision model label in route

This commit is contained in:
Sean McElwain 2026-05-30 21:25:55 -05:00
parent da538a99ee
commit 74bd259bd7
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
app/routes/documents.py
View File

@ -2235,7 +2235,7 @@ def document_detail(document_id: str, request: Request, queue: str | None = None
)
image_path = getattr(document_for_vision, "current_path", None) or getattr(document_for_vision, "source_path", None)
vision_result = analyze_document_image(image_path or "", model_name="placeholder")
vision_result = analyze_document_image(image_path or "", model_name="opencv_regions_tesseract_fields_v1")
source_layout = source_version.layout_json if source_version and isinstance(source_version.layout_json, dict) else {"pages": []}
candidate_layout = build_vision_assisted_layout(source_layout, vision_result)