feat: allow artifacts_path to be defined as ENV (#940)

* allow the artifacts_path to be defined as ENV Signed-off-by: Michele Dolfi <[email protected]> * add check if artifacts_path exists and is dir Signed-off-by: Michele Dolfi <[email protected]> --------- Signed-off-by: Michele Dolfi <[email protected]>
DS4SD · Feb 12, 2025 · 5101e25 · 5101e25
1 parent c47ae70
commit 5101e25
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 1 deletion.
diff --git 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
@@ -61,6 +61,14 @@ def __init__(self, pipeline_options: PdfPipelineOptions):
         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()
+
+        if artifacts_path is not None and not artifacts_path.is_dir():
+            raise RuntimeError(
+                f"The value of {artifacts_path=} is not valid. "
+                "When defined, it must point to a folder containing all models required by the pipeline."
+            )
 
         self.keep_images = (
             self.pipeline_options.generate_page_images