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
+25 -8
View File
@@ -401,12 +401,14 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
"PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
"DATALAB_MARKER_API_KEY": request.app.state.config.DATALAB_MARKER_API_KEY,
"DATALAB_MARKER_LANGS": request.app.state.config.DATALAB_MARKER_LANGS,
"DATALAB_MARKER_API_BASE_URL": request.app.state.config.DATALAB_MARKER_API_BASE_URL,
"DATALAB_MARKER_ADDITIONAL_CONFIG": request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG,
"DATALAB_MARKER_SKIP_CACHE": request.app.state.config.DATALAB_MARKER_SKIP_CACHE,
"DATALAB_MARKER_FORCE_OCR": request.app.state.config.DATALAB_MARKER_FORCE_OCR,
"DATALAB_MARKER_PAGINATE": request.app.state.config.DATALAB_MARKER_PAGINATE,
"DATALAB_MARKER_STRIP_EXISTING_OCR": request.app.state.config.DATALAB_MARKER_STRIP_EXISTING_OCR,
"DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION": request.app.state.config.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION,
"DATALAB_MARKER_FORMAT_LINES": request.app.state.config.DATALAB_MARKER_FORMAT_LINES,
"DATALAB_MARKER_USE_LLM": request.app.state.config.DATALAB_MARKER_USE_LLM,
"DATALAB_MARKER_OUTPUT_FORMAT": request.app.state.config.DATALAB_MARKER_OUTPUT_FORMAT,
"EXTERNAL_DOCUMENT_LOADER_URL": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL,
@@ -566,12 +568,14 @@ class ConfigForm(BaseModel):
CONTENT_EXTRACTION_ENGINE: Optional[str] = None
PDF_EXTRACT_IMAGES: Optional[bool] = None
DATALAB_MARKER_API_KEY: Optional[str] = None
DATALAB_MARKER_LANGS: Optional[str] = None
DATALAB_MARKER_API_BASE_URL: Optional[str] = None
DATALAB_MARKER_ADDITIONAL_CONFIG: Optional[str] = None
DATALAB_MARKER_SKIP_CACHE: Optional[bool] = None
DATALAB_MARKER_FORCE_OCR: Optional[bool] = None
DATALAB_MARKER_PAGINATE: Optional[bool] = None
DATALAB_MARKER_STRIP_EXISTING_OCR: Optional[bool] = None
DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION: Optional[bool] = None
DATALAB_MARKER_FORMAT_LINES: Optional[bool] = None
DATALAB_MARKER_USE_LLM: Optional[bool] = None
DATALAB_MARKER_OUTPUT_FORMAT: Optional[str] = None
EXTERNAL_DOCUMENT_LOADER_URL: Optional[str] = None
@@ -683,10 +687,15 @@ async def update_rag_config(
if form_data.DATALAB_MARKER_API_KEY is not None
else request.app.state.config.DATALAB_MARKER_API_KEY
)
request.app.state.config.DATALAB_MARKER_LANGS = (
form_data.DATALAB_MARKER_LANGS
if form_data.DATALAB_MARKER_LANGS is not None
else request.app.state.config.DATALAB_MARKER_LANGS
request.app.state.config.DATALAB_MARKER_API_BASE_URL = (
form_data.DATALAB_MARKER_API_BASE_URL
if form_data.DATALAB_MARKER_API_BASE_URL is not None
else request.app.state.config.DATALAB_MARKER_API_BASE_URL
)
request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG = (
form_data.DATALAB_MARKER_ADDITIONAL_CONFIG
if form_data.DATALAB_MARKER_ADDITIONAL_CONFIG is not None
else request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG
)
request.app.state.config.DATALAB_MARKER_SKIP_CACHE = (
form_data.DATALAB_MARKER_SKIP_CACHE
@@ -713,6 +722,11 @@ async def update_rag_config(
if form_data.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION is not None
else request.app.state.config.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION
)
request.app.state.config.DATALAB_MARKER_FORMAT_LINES = (
form_data.DATALAB_MARKER_FORMAT_LINES
if form_data.DATALAB_MARKER_FORMAT_LINES is not None
else request.app.state.config.DATALAB_MARKER_FORMAT_LINES
)
request.app.state.config.DATALAB_MARKER_OUTPUT_FORMAT = (
form_data.DATALAB_MARKER_OUTPUT_FORMAT
if form_data.DATALAB_MARKER_OUTPUT_FORMAT is not None
@@ -1006,7 +1020,8 @@ async def update_rag_config(
"CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
"PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
"DATALAB_MARKER_API_KEY": request.app.state.config.DATALAB_MARKER_API_KEY,
"DATALAB_MARKER_LANGS": request.app.state.config.DATALAB_MARKER_LANGS,
"DATALAB_MARKER_API_BASE_URL": request.app.state.config.DATALAB_MARKER_API_BASE_URL,
"DATALAB_MARKER_ADDITIONAL_CONFIG": request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG,
"DATALAB_MARKER_SKIP_CACHE": request.app.state.config.DATALAB_MARKER_SKIP_CACHE,
"DATALAB_MARKER_FORCE_OCR": request.app.state.config.DATALAB_MARKER_FORCE_OCR,
"DATALAB_MARKER_PAGINATE": request.app.state.config.DATALAB_MARKER_PAGINATE,
@@ -1393,12 +1408,14 @@ def process_file(
loader = Loader(
engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE,
DATALAB_MARKER_API_KEY=request.app.state.config.DATALAB_MARKER_API_KEY,
DATALAB_MARKER_LANGS=request.app.state.config.DATALAB_MARKER_LANGS,
DATALAB_MARKER_API_BASE_URL=request.app.state.config.DATALAB_MARKER_API_BASE_URL,
DATALAB_MARKER_ADDITIONAL_CONFIG=request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG,
DATALAB_MARKER_SKIP_CACHE=request.app.state.config.DATALAB_MARKER_SKIP_CACHE,
DATALAB_MARKER_FORCE_OCR=request.app.state.config.DATALAB_MARKER_FORCE_OCR,
DATALAB_MARKER_PAGINATE=request.app.state.config.DATALAB_MARKER_PAGINATE,
DATALAB_MARKER_STRIP_EXISTING_OCR=request.app.state.config.DATALAB_MARKER_STRIP_EXISTING_OCR,
DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION=request.app.state.config.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION,
DATALAB_MARKER_FORMAT_LINES=request.app.state.config.DATALAB_MARKER_FORMAT_LINES,
DATALAB_MARKER_USE_LLM=request.app.state.config.DATALAB_MARKER_USE_LLM,
DATALAB_MARKER_OUTPUT_FORMAT=request.app.state.config.DATALAB_MARKER_OUTPUT_FORMAT,
EXTERNAL_DOCUMENT_LOADER_URL=request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL,