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

View File

@@ -2032,10 +2032,16 @@ DATALAB_MARKER_API_KEY = PersistentConfig(
os.environ.get("DATALAB_MARKER_API_KEY", ""),
)
DATALAB_MARKER_LANGS = PersistentConfig(
"DATALAB_MARKER_LANGS",
"rag.datalab_marker_langs",
os.environ.get("DATALAB_MARKER_LANGS", ""),
DATALAB_MARKER_API_BASE_URL = PersistentConfig(
"DATALAB_MARKER_API_BASE_URL",
"rag.datalab_marker_api_base_url",
os.environ.get("DATALAB_MARKER_API_BASE_URL", ""),
)
DATALAB_MARKER_ADDITIONAL_CONFIG = PersistentConfig(
"DATALAB_MARKER_ADDITIONAL_CONFIG",
"rag.datalab_marker_additional_config",
os.environ.get("DATALAB_MARKER_ADDITIONAL_CONFIG", ""),
)
DATALAB_MARKER_USE_LLM = PersistentConfig(
@@ -2075,6 +2081,12 @@ DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION = PersistentConfig(
== "true",
)
DATALAB_MARKER_FORMAT_LINES = PersistentConfig(
"DATALAB_MARKER_FORMAT_LINES",
"rag.datalab_marker_format_lines",
os.environ.get("DATALAB_MARKER_FORMAT_LINES", "false").lower() == "true",
)
DATALAB_MARKER_OUTPUT_FORMAT = PersistentConfig(
"DATALAB_MARKER_OUTPUT_FORMAT",
"rag.datalab_marker_output_format",