mirror of
https://github.com/open-webui/open-webui.git
synced 2026-08-02 14:10:50 -05:00
f32b19c1f6
Custom per-connection headers can now forward the user's groups to
upstream backends via two new template placeholders:
- {{USER_GROUPS}}: comma-separated group names
- {{USER_GROUP_IDS}}: comma-separated group ids
The group lookup is async, so get_custom_headers becomes an async
wrapper around the sync template substitution (parse_custom_headers)
and fetches groups lazily — only when a header value actually
references a groups placeholder. The external document loader path
runs in a worker thread without an event loop, so Loader.aload
prefetches the groups before offloading and passes them through to
ExternalDocumentLoader.
Claude-Session: https://claude.ai/code/session_01EbBEfTyu8fFJmC13rnQthT
Co-authored-by: Claude <noreply@anthropic.com>
96 lines
3.0 KiB
Python
96 lines
3.0 KiB
Python
import logging
|
|
import os
|
|
from typing import Iterator, List, Union
|
|
from urllib.parse import quote
|
|
|
|
import requests
|
|
from langchain_core.document_loaders import BaseLoader
|
|
from langchain_core.documents import Document
|
|
from open_webui.utils.headers import include_user_info_headers, parse_custom_headers
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
|
|
class ExternalDocumentLoader(BaseLoader):
|
|
def __init__(
|
|
self,
|
|
file_path,
|
|
url: str,
|
|
api_key: str,
|
|
mime_type=None,
|
|
user=None,
|
|
user_groups=None,
|
|
headers=None,
|
|
metadata=None,
|
|
**kwargs,
|
|
) -> None:
|
|
self.url = url
|
|
self.api_key = api_key
|
|
|
|
self.file_path = file_path
|
|
self.mime_type = mime_type
|
|
|
|
self.user = user
|
|
self.user_groups = user_groups
|
|
self.headers = headers
|
|
self.metadata = metadata
|
|
|
|
def load(self) -> List[Document]:
|
|
with open(self.file_path, 'rb') as f:
|
|
data = f.read()
|
|
|
|
headers = {}
|
|
if self.mime_type is not None:
|
|
headers['Content-Type'] = self.mime_type
|
|
|
|
if self.api_key is not None:
|
|
headers['Authorization'] = f'Bearer {self.api_key}'
|
|
|
|
try:
|
|
headers['X-Filename'] = quote(os.path.basename(self.file_path))
|
|
except Exception:
|
|
pass
|
|
|
|
headers.update(parse_custom_headers(self.headers, self.user, self.metadata, user_groups=self.user_groups))
|
|
|
|
if self.user is not None:
|
|
headers = include_user_info_headers(headers, self.user)
|
|
|
|
url = self.url
|
|
if url.endswith('/'):
|
|
url = url[:-1]
|
|
|
|
try:
|
|
response = requests.put(f'{url}/process', data=data, headers=headers)
|
|
except Exception as e:
|
|
log.error(f'Error connecting to endpoint: {e}')
|
|
raise Exception(f'Error connecting to endpoint: {e}')
|
|
|
|
if response.ok:
|
|
response_data = response.json()
|
|
if response_data:
|
|
if isinstance(response_data, dict):
|
|
return [
|
|
Document(
|
|
page_content=response_data.get('page_content'),
|
|
metadata=response_data.get('metadata'),
|
|
)
|
|
]
|
|
elif isinstance(response_data, list):
|
|
documents = []
|
|
for document in response_data:
|
|
documents.append(
|
|
Document(
|
|
page_content=document.get('page_content'),
|
|
metadata=document.get('metadata'),
|
|
)
|
|
)
|
|
return documents
|
|
else:
|
|
raise Exception('Error loading document: Unable to parse content')
|
|
|
|
else:
|
|
raise Exception('Error loading document: No content returned')
|
|
else:
|
|
raise Exception(f'Error loading document: {response.status_code} {response.text}')
|