mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

allow the artifacts_path to be defined as ENV

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2025-02-11 10:32:30 +01:00
parent de462090e7
commit 686b3a0616
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/datamodel/settings.py
View File

@ -1,6 +1,6 @@
import sys import sys
from pathlib import Path from pathlib import Path
from typing import Annotated, Tuple from typing import Annotated, Optional, Tuple
from pydantic import BaseModel, PlainValidator from pydantic import BaseModel, PlainValidator
from pydantic_settings import BaseSettings, SettingsConfigDict from pydantic_settings import BaseSettings, SettingsConfigDict
@ -62,6 +62,7 @@ class AppSettings(BaseSettings):
debug: DebugSettings debug: DebugSettings
cache_dir: Path = Path.home() / ".cache" / "docling" cache_dir: Path = Path.home() / ".cache" / "docling"
artifacts_path: Optional[Path] = None
settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings()) settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings())

2
docling/pipeline/standard_pdf_pipeline.py
View File

@ -61,6 +61,8 @@ class StandardPdfPipeline(PaginatedPipeline):
artifacts_path: Optional[Path] = None artifacts_path: Optional[Path] = None
if pipeline_options.artifacts_path is not None: if pipeline_options.artifacts_path is not None:
artifacts_path = Path(pipeline_options.artifacts_path).expanduser() artifacts_path = Path(pipeline_options.artifacts_path).expanduser()
elif settings.artifacts_path is not None:
artifacts_path = Path(settings.artifacts_path).expanduser()
self.keep_images = ( self.keep_images = (
self.pipeline_options.generate_page_images self.pipeline_options.generate_page_images