fix: RAG scan unsupported mimetype

This fixes an issue with RAG that stops loading documents as soon
as it reaches a file with unsupported mimetype.
This commit is contained in:
Ased Mammad 2024-02-23 14:27:31 +03:30
parent b1fa32c5d6
commit b473ad574f

View File

@ -423,7 +423,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
] or file_ext in ["xls", "xlsx"]:
loader = UnstructuredExcelLoader(file_path)
elif file_ext in known_source_ext or file_content_type.find("text/") >= 0:
elif file_ext in known_source_ext or (file_content_type and file_content_type.find("text/") >= 0):
loader = TextLoader(file_path)
else:
loader = TextLoader(file_path)
@ -486,8 +486,8 @@ def store_doc(
@app.get("/scan")
def scan_docs_dir(user=Depends(get_admin_user)):
try:
for path in Path(DOCS_DIR).rglob("./**/*"):
for path in Path(DOCS_DIR).rglob("./**/*"):
try:
if path.is_file() and not path.name.startswith("."):
tags = extract_folders_after_data_docs(path)
filename = path.name
@ -535,8 +535,8 @@ def scan_docs_dir(user=Depends(get_admin_user)):
),
)
except Exception as e:
print(e)
except Exception as e:
print(e)
return True