fix: improve search relevance ranking

backend/README.md

@@ -1,6 +1,6 @@
 # Backend Акылдаш
 
-Версия: `0.5.0`
+Версия: `0.5.1`
 
 Первая backend-область проекта — загрузка правовых документов из официального
 Open Data API ЦБД Минюста Кыргызской Республики. Код расположен в
@@ -191,4 +191,4 @@ PYTHONPATH=backend python3 -m search.evaluate_relevance \
 
 ---
 
-Акылдаш · Backend v0.5.0 · Frontend — не создан
+Акылдаш · Backend v0.5.1 · Frontend — не создан

backend/ingestion/minjust_cbd.py

@@ -21,7 +21,7 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Callable, Iterable
 
-APP_VERSION = "0.5.0"
+APP_VERSION = "0.5.1"
 API_BASE_URL = "https://cbd.minjust.gov.kg/api/v1/OpenData/"
 LANGUAGES = {"Rus": "ru", "Kyr": "ky"}
 IMAGE_LANGUAGES = {"Russian": "ru", "Kyrgyz": "ky"}

backend/normalization/minjust_cbd.py

@@ -23,7 +23,7 @@ from pathlib import Path
 from typing import Callable
 from urllib.parse import urlsplit
 
-APP_VERSION = "0.5.0"
+APP_VERSION = "0.5.1"
 SCHEMA_VERSION = "1"
 NORMALIZER_VERSION = "1.0.0"
 LANGUAGES = ("ru", "ky")

backend/search/evaluate_relevance.py

@@ -55,6 +55,7 @@ def search(base_url: str, index: str, item: dict, top_k: int) -> list[str]:
                     "multi_match": {
                         "query": item["query"],
                         "fields": [f"document_name_{language}", f"text_{language}"],
+                        "type": "cross_fields",
                     }
                 },
             }

backend/search/minjust_opensearch.py

@@ -15,7 +15,7 @@ import urllib.request
 from pathlib import Path
 from typing import Iterator
 
-APP_VERSION = "0.5.0"
+APP_VERSION = "0.5.1"
 LANGUAGES = {"ru", "ky"}
 DEFAULT_MAPPING = Path(__file__).with_name("minjust-fragments-index.json")
 

backend/test_search_relevance.py

@@ -40,6 +40,7 @@ class SearchRelevanceTest(unittest.TestCase):
         body = json.loads(request.call_args_list[0].args[2])
         self.assertFalse(body["track_total_hits"])
         self.assertEqual(body["collapse"], {"field": "document_code"})
+        self.assertEqual(body["query"]["bool"]["must"]["multi_match"]["type"], "cross_fields")
 
 
 if __name__ == "__main__":