feat: Marker api content extraction support

This commit is contained in:
Hisma
2025-05-27 00:44:07 -04:00
parent b8e16211b9
commit a9405cc101
6 changed files with 516 additions and 1 deletions

View File

@@ -353,6 +353,15 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
# Content extraction settings
"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_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_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,
"EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
"TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
@@ -500,6 +509,15 @@ class ConfigForm(BaseModel):
# Content extraction settings
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_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_USE_LLM: Optional[bool] = None
DATALAB_MARKER_OUTPUT_FORMAT: Optional[str] = None
EXTERNAL_DOCUMENT_LOADER_URL: Optional[str] = None
EXTERNAL_DOCUMENT_LOADER_API_KEY: Optional[str] = None
@@ -599,6 +617,51 @@ async def update_rag_config(
if form_data.PDF_EXTRACT_IMAGES is not None
else request.app.state.config.PDF_EXTRACT_IMAGES
)
request.app.state.config.DATALAB_MARKER_API_KEY = (
form_data.DATALAB_MARKER_API_KEY
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_SKIP_CACHE = (
form_data.DATALAB_MARKER_SKIP_CACHE
if form_data.DATALAB_MARKER_SKIP_CACHE is not None
else request.app.state.config.DATALAB_MARKER_SKIP_CACHE
)
request.app.state.config.DATALAB_MARKER_FORCE_OCR = (
form_data.DATALAB_MARKER_FORCE_OCR
if form_data.DATALAB_MARKER_FORCE_OCR is not None
else request.app.state.config.DATALAB_MARKER_FORCE_OCR
)
request.app.state.config.DATALAB_MARKER_PAGINATE = (
form_data.DATALAB_MARKER_PAGINATE
if form_data.DATALAB_MARKER_PAGINATE is not None
else request.app.state.config.DATALAB_MARKER_PAGINATE
)
request.app.state.config.DATALAB_MARKER_STRIP_EXISTING_OCR = (
form_data.DATALAB_MARKER_STRIP_EXISTING_OCR
if form_data.DATALAB_MARKER_STRIP_EXISTING_OCR is not None
else request.app.state.config.DATALAB_MARKER_STRIP_EXISTING_OCR
)
request.app.state.config.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION = (
form_data.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION
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_OUTPUT_FORMAT = (
form_data.DATALAB_MARKER_OUTPUT_FORMAT
if form_data.DATALAB_MARKER_OUTPUT_FORMAT is not None
else request.app.state.config.DATALAB_MARKER_OUTPUT_FORMAT
)
request.app.state.config.DATALAB_MARKER_USE_LLM = (
form_data.DATALAB_MARKER_USE_LLM
if form_data.DATALAB_MARKER_USE_LLM is not None
else request.app.state.config.DATALAB_MARKER_USE_LLM
)
request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = (
form_data.EXTERNAL_DOCUMENT_LOADER_URL
if form_data.EXTERNAL_DOCUMENT_LOADER_URL is not None
@@ -853,6 +916,15 @@ async def update_rag_config(
# Content extraction settings
"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_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_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,
"EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
"TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
@@ -1178,6 +1250,15 @@ def process_file(
file_path = Storage.get_file(file_path)
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_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_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,
EXTERNAL_DOCUMENT_LOADER_API_KEY=request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,