Improve regex

1 year ago · 5a80ef2571
parent ebfdfe3099
commit 5a80ef2571
1 changed files with 1 additions and 1 deletions
--- a/apps/web-crawl-q-and-a/web-qa.py
+++ b/apps/web-crawl-q-and-a/web-qa.py
@ -17,7 +17,7 @@ import numpy as np
 from openai.embeddings_utils import distances_from_embeddings, cosine_similarity

 # Regex pattern to match a URL
-HTTP_URL_PATTERN = r'^http[s]*://.+'
+HTTP_URL_PATTERN = r'^http[s]{0,1}://.+$'

 # Define root domain to crawl
 domain = "openai.com"