Update utils/DocsLoader.py

utils/DocsLoader.py

@@ -3,7 +3,8 @@ import tempfile
 import requests
 
 from fastapi import HTTPException
-from langchain_community.document_loaders import PyPDFLoader, Docx2txtLoader
+# from langchain_community.document_loaders import PyPDFLoader, Docx2txtLoader
+from langchain_community.document_loaders import PyMuPDFLoader, Docx2txtLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.schema import Document
 
@@ -21,7 +22,7 @@ def load_and_chunk(url: str) -> list[Document]:
             tmp.write(resp.content)
             tmp_path = tmp.name
         try:
-            loader = PyPDFLoader(tmp_path)
+            loader = PyMuPDFLoader(tmp_path)
             docs = loader.load_and_split()
         finally:
             os.remove(tmp_path)