ti.sil/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-15 13:55:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

feat: Optionally forward user headers to external document loader

Browse source 
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com>
This commit is contained in:
Timothy Jaeryang Baek 2025-11-06 00:05:46 -05:00
parent f5c7152a6b
commit e2b9942648
3 changed files with 10 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
backend/open_webui/retrieval/loaders/external_document.py
View file

@ -5,6 +5,7 @@ from urllib.parse import quote
from langchain_core.document_loaders import BaseLoader from langchain_core.document_loaders import BaseLoader
from langchain_core.documents import Document from langchain_core.documents import Document
from open_webui.utils.headers import include_user_info_headers
from open_webui.env import SRC_LOG_LEVELS from open_webui.env import SRC_LOG_LEVELS
log = logging.getLogger(__name__) log = logging.getLogger(__name__)
@ -18,6 +19,7 @@ class ExternalDocumentLoader(BaseLoader):
url: str, url: str,
api_key: str, api_key: str,
mime_type=None, mime_type=None,
user=None,
**kwargs, **kwargs,
) -> None: ) -> None:
self.url = url self.url = url
@ -26,6 +28,8 @@ class ExternalDocumentLoader(BaseLoader):
self.file_path = file_path self.file_path = file_path
self.mime_type = mime_type self.mime_type = mime_type
self.user = user
def load(self) -> List[Document]: def load(self) -> List[Document]:
with open(self.file_path, "rb") as f: with open(self.file_path, "rb") as f:
data = f.read() data = f.read()
@ -42,6 +46,9 @@ class ExternalDocumentLoader(BaseLoader):
except: except:
pass pass
if self.user is not None:
headers = include_user_info_headers(headers, self.user)
url = self.url url = self.url
if url.endswith("/"): if url.endswith("/"):
url = url[:-1] url = url[:-1]

2
backend/open_webui/retrieval/loaders/main.py
View file

@ -228,6 +228,7 @@ class DoclingLoader:
class Loader: class Loader:
def __init__(self, engine: str = "", **kwargs): def __init__(self, engine: str = "", **kwargs):
self.engine = engine self.engine = engine
self.user = kwargs.get("user", None)
self.kwargs = kwargs self.kwargs = kwargs
def load( def load(
@ -264,6 +265,7 @@ class Loader:
url=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_URL"), url=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_URL"),
api_key=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_API_KEY"), api_key=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_API_KEY"),
mime_type=file_content_type, mime_type=file_content_type,
user=self.user,
) )
elif self.engine == "tika" and self.kwargs.get("TIKA_SERVER_URL"): elif self.engine == "tika" and self.kwargs.get("TIKA_SERVER_URL"):
if self._is_text_file(file_ext, file_content_type): if self._is_text_file(file_ext, file_content_type):

1
backend/open_webui/routers/retrieval.py
View file

@ -1574,6 +1574,7 @@ def process_file(
file_path = Storage.get_file(file_path) file_path = Storage.get_file(file_path)
loader = Loader( loader = Loader(
engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE, 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_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_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_ADDITIONAL_CONFIG=request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG,