tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Releases 2 Packages Activity Actions

switch to using BeautifulSoup HTML loader so title is also captured

Browse source
This commit is contained in:
Doug Danat 2024-03-25 11:26:18 +01:00
parent 77f4ffddc1
commit c91a5d8b1f
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
backend/apps/rag/main.py
View file

@ -21,7 +21,7 @@ from langchain_community.document_loaders import (
TextLoader, TextLoader,
PyPDFLoader, PyPDFLoader,
CSVLoader, CSVLoader,
UnstructuredHTMLLoader, BSHTMLLoader,
Docx2txtLoader, Docx2txtLoader,
UnstructuredEPubLoader, UnstructuredEPubLoader,
UnstructuredWordDocumentLoader, UnstructuredWordDocumentLoader,
@ -404,7 +404,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
elif file_ext == "xml": elif file_ext == "xml":
loader = UnstructuredXMLLoader(file_path) loader = UnstructuredXMLLoader(file_path)
elif file_ext in ["htm", "html"]: elif file_ext in ["htm", "html"]:
loader = UnstructuredHTMLLoader(file_path) loader = BSHTMLLoader(file_path)
elif file_ext == "md": elif file_ext == "md":
loader = UnstructuredMarkdownLoader(file_path) loader = UnstructuredMarkdownLoader(file_path)
elif file_content_type == "application/epub+zip": elif file_content_type == "application/epub+zip":