Merge pull request #15903 from Hisma/marker-api-update

feat: Add configurable API URL (for self-hosting) and additional_config parameter for Datalab Marker API
This commit is contained in:
Tim Jaeryang Baek
2025-08-04 15:21:03 +04:00
committed by GitHub
6 changed files with 215 additions and 98 deletions
+7 -1
View File
@@ -281,10 +281,15 @@ class Loader:
"tiff",
]
):
api_base_url = self.kwargs.get("DATALAB_MARKER_API_BASE_URL", "")
if not api_base_url or api_base_url.strip() == "":
api_base_url = "https://www.datalab.to/api/v1/marker"
loader = DatalabMarkerLoader(
file_path=file_path,
api_key=self.kwargs["DATALAB_MARKER_API_KEY"],
langs=self.kwargs.get("DATALAB_MARKER_LANGS"),
api_base_url=api_base_url,
additional_config=self.kwargs.get("DATALAB_MARKER_ADDITIONAL_CONFIG"),
use_llm=self.kwargs.get("DATALAB_MARKER_USE_LLM", False),
skip_cache=self.kwargs.get("DATALAB_MARKER_SKIP_CACHE", False),
force_ocr=self.kwargs.get("DATALAB_MARKER_FORCE_OCR", False),
@@ -295,6 +300,7 @@ class Loader:
disable_image_extraction=self.kwargs.get(
"DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION", False
),
format_lines=self.kwargs.get("DATALAB_MARKER_FORMAT_LINES", False),
output_format=self.kwargs.get(
"DATALAB_MARKER_OUTPUT_FORMAT", "markdown"
),