Mirrors/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-16 20:07:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat: merge with main

Browse Source
This commit is contained in:
Fabio Polito
2025-03-05 22:04:34 +00:00
parent a44b35e99e 4770285c04
commit 9aa407dbd2
372 changed files with 26027 additions and 10944 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
backend/open_webui/retrieval/loaders/main.py
View File

@@ -4,6 +4,7 @@ import ftfy
import sys
from langchain_community.document_loaders import (
AzureAIDocumentIntelligenceLoader,
BSHTMLLoader,
CSVLoader,
Docx2txtLoader,
@@ -76,6 +77,7 @@ known_source_ext = [
"jsx",
"hs",
"lhs",
"json",
]
@@ -221,12 +223,33 @@ class Loader:
file_path=file_path,
mime_type=file_content_type,
)
elif self.engine == "docling":
elif self.engine == "docling" and self.kwargs.get("DOCLING_SERVER_URL"):
loader = DoclingLoader(
url=self.kwargs.get("DOCLING_SERVER_URL"),
file_path=file_path,
mime_type=file_content_type,
)
elif (
self.engine == "document_intelligence"
and self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT") != ""
and self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY") != ""
and (
file_ext in ["pdf", "xls", "xlsx", "docx", "ppt", "pptx"]
or file_content_type
in [
"application/vnd.ms-excel",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"application/vnd.ms-powerpoint",
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
]
)
):
loader = AzureAIDocumentIntelligenceLoader(
file_path=file_path,
api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
api_key=self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY"),
)
else:
if file_ext == "pdf":
loader = PyPDFLoader(