klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-07 05:40:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make bi-encoder return fewer results to reduce cross-encoder latency

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2022-07-27 07:26:02 +04:00
parent 9ab3edf6d6
commit 09727ac3be
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/search_type/text_search.py
View File

@@ -20,7 +20,7 @@ def initialize_model(search_config: TextSearchConfig):
torch.set_num_threads(4) torch.set_num_threads(4)
# Number of entries we want to retrieve with the bi-encoder # Number of entries we want to retrieve with the bi-encoder
top_k = 30 top_k = 15
# The bi-encoder encodes all entries to use for semantic search # The bi-encoder encodes all entries to use for semantic search
bi_encoder = load_model( bi_encoder = load_model(