feat: add search relevance baseline

backend/test_search_relevance.py

@@ -0,0 +1,46 @@
+import json
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from search.evaluate_relevance import evaluate, load_queries
+
+
+class SearchRelevanceTest(unittest.TestCase):
+    def test_loads_queries_and_calculates_document_metrics(self):
+        queries = [
+            {
+                "id": "ru-01",
+                "language": "ru",
+                "query": "трудовой договор",
+                "relevant_document_codes": ["7", "8"],
+            },
+            {
+                "id": "ky-01",
+                "language": "ky",
+                "query": "эмгек келишими",
+                "relevant_document_codes": ["9"],
+            },
+        ]
+        with tempfile.TemporaryDirectory() as temporary:
+            path = Path(temporary) / "queries.json"
+            path.write_text(json.dumps(queries, ensure_ascii=False), encoding="utf-8")
+            loaded = load_queries(path)
+
+        responses = [
+            {"hits": {"hits": [{"_source": {"document_code": code}} for code in ["7", "10", "8"]]}},
+            {"hits": {"hits": [{"_source": {"document_code": code}} for code in ["10", "9"]]}},
+        ]
+        with patch("search.evaluate_relevance.request_json", side_effect=responses) as request:
+            result = evaluate(loaded, "http://127.0.0.1:9200", "test", 10)
+
+        self.assertEqual(result["summary"], {"query_count": 2, "recall_at_10": 1.0, "mrr_at_10": 0.75})
+        self.assertEqual(result["queries"][0]["reciprocal_rank_at_10"], 1.0)
+        body = json.loads(request.call_args_list[0].args[2])
+        self.assertFalse(body["track_total_hits"])
+        self.assertEqual(body["collapse"], {"field": "document_code"})
+
+
+if __name__ == "__main__":
+    unittest.main()