Allow parsers to declare uses remote, and remote ocr_mode (#13634)

* uses_remote_service + allow_remote to allow opt-in / out of remote OCR

* Add to parser dev docs

* remote_ocr_mode config setting

* Checks for remote_ocr_mode and fix import

* Update config.component.spec.ts

* More tests for remote_ocr_mode

* Docs for remote_ocr_mode

* Ok, wire up the remote_ocr_mode with allow_remote for consumer

* Update consumer.py

* Format remote OCR mode check tests

* Use get_choice_from_env
This commit is contained in:
shamoon
2026-08-24 14:43:04 -07:00
committed by GitHub
parent a1f20c9fe7
commit 7f1609332a
20 changed files with 425 additions and 1 deletions
+10 -1
View File
@@ -67,6 +67,7 @@ from documents.utils import identity
from documents.versioning import annotate_effective_content
from documents.workflows.utils import get_workflows_for_trigger
from paperless.config import AIConfig
from paperless.config import RemoteOCRConfig
from paperless.logging import consume_task_id
from paperless.parsers import ParserContext
from paperless.parsers.registry import get_parser_registry
@@ -338,10 +339,17 @@ def bulk_update_documents(document_ids) -> None:
@shared_task
def update_document_content_maybe_archive_file(document_id) -> None:
def update_document_content_maybe_archive_file(
document_id,
*,
remote_ocr: bool = False,
) -> None:
"""
Re-creates OCR content and thumbnail for a document, and archive file if
it exists.
Remote OCR is used only when the engine is configured to handle everything
or if explicitly asked for via ``remote_ocr``.
"""
document = Document.objects.get(id=document_id)
@@ -351,6 +359,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
mime_type,
document.original_filename or "",
document.source_path,
allow_remote=remote_ocr or RemoteOCRConfig().remote_ocr_by_default,
)
if not parser_class: