a375ca55b9
The artifact-upsert helper was duplicated four times (scanner.py, table_processor.py, figure_processor.py, pipeline.py) with slightly different signatures. Consolidates into a single keyword-only function keyed on (document_id, storage_key) - the identity the schema already enforces - so re-running the pipeline never creates duplicate rows. scanner / table_processor / figure_processor now import the shared helper directly. pipeline.py keeps a thin local wrapper to preserve the positional call sites at three artifact upsert points (OCR_PDF, MARKDOWN, DOCLING_JSON). Tests: 24 passed (5 health + 19 original). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 lines
175 B
Python
5 lines
175 B
Python
from app.storage.artifacts import ensure_artifact
|
|
from app.storage.minio_client import MinioStorage, get_storage
|
|
|
|
__all__ = ["MinioStorage", "ensure_artifact", "get_storage"]
|