mirror of
https://github.com/open-webui/open-webui
synced 2025-02-23 13:51:07 +00:00
fix: Filter out invalid RAG web URLs (continued)
This commit is contained in:
parent
121a13d4ed
commit
3db6b4352f
@ -42,6 +42,15 @@ def validate_url(url: Union[str, Sequence[str]]):
|
||||
else:
|
||||
return False
|
||||
|
||||
def safe_validate_urls(url: Sequence[str]) -> Sequence[str]:
|
||||
valid_urls = []
|
||||
for u in url:
|
||||
try:
|
||||
if validate_url(u):
|
||||
valid_urls.append(u)
|
||||
except ValueError:
|
||||
continue
|
||||
return valid_urls
|
||||
|
||||
def resolve_hostname(hostname):
|
||||
# Get address information
|
||||
@ -86,11 +95,11 @@ def get_web_loader(
|
||||
verify_ssl: bool = True,
|
||||
requests_per_second: int = 2,
|
||||
):
|
||||
# Check if the URL is valid
|
||||
if not validate_url(urls):
|
||||
raise ValueError(ERROR_MESSAGES.INVALID_URL)
|
||||
# Check if the URLs are valid
|
||||
safe_urls = safe_validate_urls([urls] if isinstance(urls, str) else urls)
|
||||
|
||||
return SafeWebBaseLoader(
|
||||
urls,
|
||||
safe_urls,
|
||||
verify_ssl=verify_ssl,
|
||||
requests_per_second=requests_per_second,
|
||||
continue_on_failure=True,
|
||||
|
Loading…
Reference in New Issue
Block a user