mirror of
https://github.com/khoaliber/khoj.git
synced 2026-03-09 13:25:11 +00:00
Run explicit filter on raw entry, add more terms to split entries by
- With \t Last Word in Headings was suffixed by \t and so couldn't be filtered by - User interacts with raw entries, so run explicit filters on raw entry - For semantic search using the filtered entry is cleaner, still
This commit is contained in:
@@ -18,8 +18,8 @@ def explicit_filter(raw_query, entries, embeddings):
|
|||||||
entries_by_word_set = [set(word.lower()
|
entries_by_word_set = [set(word.lower()
|
||||||
for word
|
for word
|
||||||
in re.split(
|
in re.split(
|
||||||
r',|\.| |\]|\[\(|\)|\{|\}', # split on fullstop, comma or any brackets
|
r',|\.| |\]|\[\(|\)|\{|\}|\t|\n|\:', # split on fullstop, comma or any brackets
|
||||||
entry[0])
|
entry[1])
|
||||||
if word != "")
|
if word != "")
|
||||||
for entry in entries]
|
for entry in entries]
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user