sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2025-02-17 16:14:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

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
Show stats 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)
# 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
bi_encoder = load_model(