From 686b3a06161f898d227b9d18e5377185c875123b Mon Sep 17 00:00:00 2001 From: Michele Dolfi Date: Tue, 11 Feb 2025 10:32:30 +0100 Subject: [PATCH] allow the artifacts_path to be defined as ENV Signed-off-by: Michele Dolfi --- docling/datamodel/settings.py | 3 ++- docling/pipeline/standard_pdf_pipeline.py | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/docling/datamodel/settings.py b/docling/datamodel/settings.py index 439ffe74..fee871a2 100644 --- a/docling/datamodel/settings.py +++ b/docling/datamodel/settings.py @@ -1,6 +1,6 @@ import sys from pathlib import Path -from typing import Annotated, Tuple +from typing import Annotated, Optional, Tuple from pydantic import BaseModel, PlainValidator from pydantic_settings import BaseSettings, SettingsConfigDict @@ -62,6 +62,7 @@ class AppSettings(BaseSettings): debug: DebugSettings cache_dir: Path = Path.home() / ".cache" / "docling" + artifacts_path: Optional[Path] = None settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings()) diff --git a/docling/pipeline/standard_pdf_pipeline.py b/docling/pipeline/standard_pdf_pipeline.py index 13e435f9..11466ec2 100644 --- a/docling/pipeline/standard_pdf_pipeline.py +++ b/docling/pipeline/standard_pdf_pipeline.py @@ -61,6 +61,8 @@ class StandardPdfPipeline(PaginatedPipeline): artifacts_path: Optional[Path] = None if pipeline_options.artifacts_path is not None: 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.pipeline_options.generate_page_images