Skip to content

GitLab

Commit c91a5d8b authored by Doug Danat's avatar Doug Danat
Browse files

switch to using BeautifulSoup HTML loader so title is also captured

parent 77f4ffdd
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
backend/apps/rag/main.py
View file @ c91a5d8b
...@@ -21,7 +21,7 @@ from langchain_community.document_loaders import ( ...@@ -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): ...@@ -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":
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment