sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2025-02-17 08:04:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Improve code comments. Do not import unused modules in asymmetric search

Browse source
This commit is contained in:
Debanjum Singh Solanky 2021-11-17 00:57:21 +05:30
parent 8cf2465e8e
commit f3fd5ae978
1 changed files with 4 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
src/search_type/asymmetric.py
View file

@ -2,10 +2,7 @@
# Standard Packages # Standard Packages
import json import json
import time
import gzip import gzip
import os
import sys
import re import re
import argparse import argparse
import pathlib import pathlib
@ -80,7 +77,7 @@ def query(raw_query: str, model: TextSearchModel):
hits = util.semantic_search(question_embedding, model.corpus_embeddings, top_k=model.top_k) hits = util.semantic_search(question_embedding, model.corpus_embeddings, top_k=model.top_k)
hits = hits[0] # Get the hits for the first query hits = hits[0] # Get the hits for the first query
# Filter results using explicit filters # Filter out entries that contain required words and do not contain blocked words
hits = explicit_filter(hits, hits = explicit_filter(hits,
[entry[0] for entry in model.entries], [entry[0] for entry in model.entries],
required_words,blocked_words) required_words,blocked_words)
@ -95,9 +92,9 @@ def query(raw_query: str, model: TextSearchModel):
for idx in range(len(cross_scores)): for idx in range(len(cross_scores)):
hits[idx]['cross-score'] = cross_scores[idx] hits[idx]['cross-score'] = cross_scores[idx]
# Order results by cross encoder score followed by biencoder score # Order results by cross-encoder score followed by bi-encoder score
hits.sort(key=lambda x: x['score'], reverse=True) # sort by biencoder score hits.sort(key=lambda x: x['score'], reverse=True) # sort by bi-encoder score
hits.sort(key=lambda x: x['cross-score'], reverse=True) # sort by cross encoder score hits.sort(key=lambda x: x['cross-score'], reverse=True) # sort by cross-encoder score
return hits return hits