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

@@ -226,12 +226,14 @@ from open_webui.config import (
CHUNK_SIZE,
CONTENT_EXTRACTION_ENGINE,
DATALAB_MARKER_API_KEY,
DATALAB_MARKER_LANGS,
DATALAB_MARKER_API_BASE_URL,
DATALAB_MARKER_ADDITIONAL_CONFIG,
DATALAB_MARKER_SKIP_CACHE,
DATALAB_MARKER_FORCE_OCR,
DATALAB_MARKER_PAGINATE,
DATALAB_MARKER_STRIP_EXISTING_OCR,
DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION,
DATALAB_MARKER_FORMAT_LINES,
DATALAB_MARKER_OUTPUT_FORMAT,
DATALAB_MARKER_USE_LLM,
EXTERNAL_DOCUMENT_LOADER_URL,
@@ -771,7 +773,8 @@ app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION = ENABLE_WEB_LOADER_SSL_VERI
app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
app.state.config.DATALAB_MARKER_API_KEY = DATALAB_MARKER_API_KEY
app.state.config.DATALAB_MARKER_LANGS = DATALAB_MARKER_LANGS
app.state.config.DATALAB_MARKER_API_BASE_URL = DATALAB_MARKER_API_BASE_URL
app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG = DATALAB_MARKER_ADDITIONAL_CONFIG
app.state.config.DATALAB_MARKER_SKIP_CACHE = DATALAB_MARKER_SKIP_CACHE
app.state.config.DATALAB_MARKER_FORCE_OCR = DATALAB_MARKER_FORCE_OCR
app.state.config.DATALAB_MARKER_PAGINATE = DATALAB_MARKER_PAGINATE
@@ -779,6 +782,7 @@ app.state.config.DATALAB_MARKER_STRIP_EXISTING_OCR = DATALAB_MARKER_STRIP_EXISTI
app.state.config.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION = (
DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION
)
app.state.config.DATALAB_MARKER_FORMAT_LINES = DATALAB_MARKER_FORMAT_LINES
app.state.config.DATALAB_MARKER_USE_LLM = DATALAB_MARKER_USE_LLM
app.state.config.DATALAB_MARKER_OUTPUT_FORMAT = DATALAB_MARKER_OUTPUT_FORMAT
app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = EXTERNAL_DOCUMENT_LOADER_URL