This commit is contained in:
Timothy Jaeryang Baek
2026-04-21 15:47:32 +09:00
parent c7b6de6ca4
commit b9fc3f367a
2 changed files with 117 additions and 38 deletions
+4 -34
View File
@@ -48,7 +48,7 @@ from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
from open_webui.retrieval.vector.async_client import ASYNC_VECTOR_DB_CLIENT
# Document loaders
from open_webui.retrieval.loaders.main import Loader
from open_webui.retrieval.loaders.youtube import YoutubeLoader
# Web search engines
@@ -82,6 +82,7 @@ from open_webui.retrieval.web.yandex import search_yandex
from open_webui.retrieval.web.ydc import search_youcom
from open_webui.retrieval.utils import (
build_loader_from_config,
filter_accessible_collections,
get_content_from_url,
get_embedding_function,
@@ -1623,39 +1624,8 @@ async def process_file(
file_path = file.path
if file_path:
file_path = await asyncio.to_thread(Storage.get_file, file_path)
loader = Loader(
engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE,
user=user,
DATALAB_MARKER_API_KEY=request.app.state.config.DATALAB_MARKER_API_KEY,
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,
EXTERNAL_DOCUMENT_LOADER_API_KEY=request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,
DOCLING_SERVER_URL=request.app.state.config.DOCLING_SERVER_URL,
DOCLING_API_KEY=request.app.state.config.DOCLING_API_KEY,
DOCLING_PARAMS=request.app.state.config.DOCLING_PARAMS,
PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
PDF_LOADER_MODE=request.app.state.config.PDF_LOADER_MODE,
DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
DOCUMENT_INTELLIGENCE_MODEL=request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL,
MISTRAL_OCR_API_BASE_URL=request.app.state.config.MISTRAL_OCR_API_BASE_URL,
MISTRAL_OCR_API_KEY=request.app.state.config.MISTRAL_OCR_API_KEY,
MINERU_API_MODE=request.app.state.config.MINERU_API_MODE,
MINERU_API_URL=request.app.state.config.MINERU_API_URL,
MINERU_API_KEY=request.app.state.config.MINERU_API_KEY,
MINERU_API_TIMEOUT=request.app.state.config.MINERU_API_TIMEOUT,
MINERU_PARAMS=request.app.state.config.MINERU_PARAMS,
)
loader = build_loader_from_config(request)
loader.user = user
docs = await loader.aload(file.filename, file.meta.get('content_type'), file_path)
docs = [