paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-12 17:04:40 -05:00
Code Issues Packages Projects Releases Wiki Activity

Update parsers.py

Browse Source
This commit is contained in:
shamoon 2025-07-09 11:02:57 -07:00
parent 88c69b83ea
commit d260a94740
No known key found for this signature in database
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/paperless_remote/parsers.py
View File

@ -25,14 +25,15 @@ class RemoteEngineConfig:
class RemoteDocumentParser(RasterisedDocumentParser):
"""
This parser uses a remote ocr engine to parse documents
This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
as this is the only service that provides a remote OCR API with text-embedded PDF output.
"""
logging_name = "paperless.parsing.remote"
def get_settings(self) -> RemoteEngineConfig:
"""
This parser uses the OCR configuration settings to parse documents
Returns the configuration for the remote OCR engine, loaded from Django settings.
"""
return RemoteEngineConfig(
engine=settings.REMOTE_OCR_ENGINE,
@ -59,7 +60,11 @@ class RemoteDocumentParser(RasterisedDocumentParser):
file: Path,
) -> str | None:
"""
This method uses the Azure AI Vision API to parse documents
Uses Azure AI Vision to parse the document and return the text content.
It requests a searchable PDF output with embedded text.
The PDF is saved to the archive_path attribute.
Returns the text content extracted from the document.
If the parsing fails, it returns None.
"""
from azure.ai.documentintelligence import DocumentIntelligenceClient
from azure.ai.documentintelligence.models import AnalyzeDocumentRequest