feat: add PaddleOCR-vl loader support and implement retrieval router infrastructure (#23945)

Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com>
This commit is contained in:
goodbey857
2026-04-24 15:19:37 +09:00
committed by GitHub
co-authored by Tim Baek joaoback
parent 0e311a95a7
commit 58bc254809
10 changed files with 199 additions and 2 deletions
+10 -1
View File
@@ -23,7 +23,7 @@ from open_webui.retrieval.loaders.external_document import ExternalDocumentLoade
from open_webui.retrieval.loaders.mistral import MistralLoader
from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
from open_webui.retrieval.loaders.mineru import MinerULoader
from open_webui.retrieval.loaders.paddleocr_vl import PaddleOCRVLLoader
from open_webui.env import GLOBAL_LOG_LEVEL, REQUESTS_VERIFY
@@ -399,6 +399,15 @@ class Loader:
api_key=self.kwargs.get('MISTRAL_OCR_API_KEY'),
file_path=file_path,
)
elif (
self.engine == 'paddleocr_vl'
and self.kwargs.get('PADDLEOCR_VL_TOKEN') != ''
):
loader = PaddleOCRVLLoader(
api_url=self.kwargs.get('PADDLEOCR_VL_BASE_URL'),
token=self.kwargs.get('PADDLEOCR_VL_TOKEN'),
file_path=file_path,
)
else:
if file_ext == 'pdf':
loader = PyPDFLoader(