Test diverse grouped search results

This commit is contained in:
Sleeps
2026-10-07 17:02:54 +01:00
parent b03a006436
commit 8aff833340
+130 -1
View File
@@ -21,7 +21,10 @@ class FakeEmbedder:
text_vector: np.ndarray,
image_vectors: np.ndarray,
) -> np.ndarray:
return np.asarray([0.9, 0.7, 0.6], dtype=np.float32)
count = len(image_vectors)
if count == 0:
return np.asarray([], dtype=np.float32)
return np.linspace(0.9, 0.5, count, dtype=np.float32)
class SearchServiceTests(unittest.TestCase):
@@ -138,6 +141,12 @@ class SearchServiceTests(unittest.TestCase):
self.assertEqual(result["items"][0]["jellyfin_item_id"], "jf-1")
self.assertEqual(result["items"][0]["best_timestamp_ms"], 0)
self.assertEqual(result["items"][0]["scene_matches"], 3)
self.assertEqual(len(result["items"][0]["matching_scenes"]), 3)
self.assertEqual(
result["items"][0]["matching_scenes"][1]["timestamp_ms"],
10000,
)
self.assertEqual(result["candidate_scene_count"], 3)
self.assertAlmostEqual(result["scenes"][0]["siglip_score"], 0.9, places=5)
call = service.meili.search_vector.call_args
@@ -147,6 +156,126 @@ class SearchServiceTests(unittest.TestCase):
'source_kind = "jellyfin"',
)
def test_search_expands_candidates_until_unique_item_limit_is_met(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
db_path = Path(tmp) / "scenes.sqlite3"
init_db(db_path)
with connect(db_path) as con:
for media_number in range(1, 4):
con.execute(
"""
INSERT INTO media (
id, source_path, title, content_sha256, size_bytes, mtime_ns,
interval_ms, model_id, embedding_dim, source_kind,
jellyfin_item_id, jellyfin_library_id, jellyfin_item_type,
jellyfin_tags
)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
""",
(
f"media-{media_number}",
f"/media/example-{media_number}.mkv",
f"Movie {media_number}",
f"hash-{media_number}",
1,
0,
10000,
"model",
2,
"jellyfin",
f"jf-{media_number}",
"lib-1",
"Movie",
"[]",
),
)
frame_rows = [
(f"frame-{number}", "media-1", number, number * 10000)
for number in range(6)
] + [
("frame-6", "media-2", 0, 0),
("frame-7", "media-3", 0, 0),
]
for frame_id, media_id, frame_number, timestamp_ms in frame_rows:
con.execute(
"""
INSERT INTO frames (
id, media_id, frame_number, timestamp_ms,
thumb_path, embedding_f16, caption
)
VALUES (?, ?, ?, ?, ?, ?, ?)
""",
(
frame_id,
media_id,
frame_number,
timestamp_ms,
f"/tmp/{frame_id}.jpg",
pack_vector(np.asarray([1.0, 0.0], dtype=np.float32)),
f"caption {frame_id}",
),
)
def hit(frame_id: str, media_number: int, rank: float) -> dict:
return {
"id": frame_id,
"media_id": f"media-{media_number}",
"jellyfin_item_id": f"jf-{media_number}",
"jellyfin_library_id": "lib-1",
"jellyfin_item_type": "Movie",
"title": f"Movie {media_number}",
"timestamp_ms": 0,
"caption": f"caption {frame_id}",
"jellyfin_tags": [],
"_rankingScore": rank,
}
first_hits = [
hit(f"frame-{number}", 1, 0.99 - number * 0.01)
for number in range(6)
]
expanded_hits = first_hits + [
hit("frame-6", 2, 0.80),
hit("frame-7", 3, 0.79),
]
service = SearchService(
db_path=db_path,
meili_url="http://meili.test",
meili_master_key="key",
meili_index="scenes",
model_id="model",
device="cpu",
semantic_ratio=0.8,
)
service._embedder = FakeEmbedder() # type: ignore[assignment]
service.meili = Mock()
service.meili.search_vector.side_effect = [
{"hits": first_hits},
{"hits": expanded_hits},
]
result = service.search("person outside", scene_limit=2, item_limit=3)
self.assertEqual(
[call.args[2] for call in service.meili.search_vector.call_args_list],
[6, 12],
)
self.assertEqual(result["item_count"], 3)
self.assertEqual(
[item["jellyfin_item_id"] for item in result["items"]],
["jf-1", "jf-2", "jf-3"],
)
self.assertEqual(result["scene_count"], 2)
self.assertEqual(result["candidate_scene_count"], 8)
self.assertEqual(result["items"][0]["scene_matches"], 6)
self.assertEqual(
len(result["items"][0]["matching_scenes"]),
SearchService.SCENES_PER_ITEM,
)
def test_health_does_not_load_embedding_model(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
db_path = Path(tmp) / "scenes.sqlite3"