admin/milvus
1
0
Fork 0
mirror of https://gitee.com/milvus-io/milvus.git synced 2025-12-06 17:18:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

test: add field case about dynamic and compaction (#45694)

Browse Source 
related issue: #42126

Signed-off-by: qixuan <673771573@qq.com>
This commit is contained in:
qixuan 2025-11-21 10:07:05 +08:00 committed by GitHub
parent 1cd0ef943e
commit 3202847092
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 73 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
tests/python_client/milvus_client/test_add_field_feature.py
View File

@ -78,45 +78,66 @@ class TestMilvusClientAddFieldFeature(TestMilvusClientV2Base):
"""
client = self._client()
collection_name = cf.gen_collection_name_by_testcase_name()
dim = 128
dim, default_value = 128, 1
# 1. create collection
schema = self.create_schema(client, enable_dynamic_field=False)[0]
schema.add_field(default_primary_key_field_name, DataType.INT64, is_primary=True, auto_id=False)
schema.add_field(default_vector_field_name, DataType.FLOAT_VECTOR, dim=dim)
schema.add_field(default_vector_field_name+"new", DataType.FLOAT_VECTOR, dim=dim)
schema.add_field(default_string_field_name, DataType.VARCHAR, max_length=64, is_partition_key=True)
schema.add_field(default_string_field_name, DataType.VARCHAR, max_length=64)
index_params = self.prepare_index_params(client)[0]
index_params.add_index(default_vector_field_name, metric_type="COSINE")
index_params.add_index(default_vector_field_name+"new", metric_type="L2")
self.create_collection(client, collection_name, dimension=dim, schema=schema, index_params=index_params)
# 2. insert
rng = np.random.default_rng(seed=19530)
rows = [
{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
default_vector_field_name+"new": list(rng.random((1, default_dim))[0]),
default_string_field_name: str(i)} for i in range(10*default_nb)]
self.insert(client, collection_name, rows)
# 3. add collection field
self.add_collection_field(client, collection_name, field_name=default_new_field_name, data_type=DataType.INT64,
nullable=True, is_clustering_key=True)
# 3. insert new field after add field
rows_new = [
{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
default_vector_field_name+"new": list(rng.random((1, default_dim))[0]),default_string_field_name: str(i),
default_new_field_name: random.randint(1, 1000)} for i in range(10*default_nb, 11*default_nb)]
self.insert(client, collection_name, rows_new)
self.flush(client, collection_name)
# 4. compact
compact_id = self.compact(client, collection_name, is_clustering=True)[0]
nullable=True, is_clustering_key=True, default_value=default_value)
cost = 180
vectors = cf.gen_vectors(default_nb, dim, vector_data_type=DataType.FLOAT_VECTOR)
vectors_to_search = [vectors[0]]
# 4. insert new field after add field
rows_new = [{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
default_string_field_name: str(i), default_new_field_name: random.randint(1, 1000)}
for i in range(10*default_nb, 11*default_nb)]
self.insert(client, collection_name, rows_new)
# 5. compact
compact_id = self.compact(client, collection_name)[0]
start = time.time()
while True:
time.sleep(1)
res = self.get_compaction_state(client, compact_id, is_clustering=True)[0]
res = self.get_compaction_state(client, compact_id)[0]
if res == "Completed":
break
if time.time() - start > cost:
raise Exception(1, f"Compact after index cost more than {cost}s")
self.wait_for_index_ready(client, collection_name, default_vector_field_name)
self.release_collection(client, collection_name)
time.sleep(10)
self.load_collection(client, collection_name)
insert_ids = [i for i in range(10*default_nb)]
# 6. search with default value
self.search(client, collection_name, vectors_to_search, filter=f'{default_new_field_name} == {default_value}',
output_fields=[default_new_field_name],
check_task=CheckTasks.check_search_results,
check_items={"enable_milvus_client_api": True,
"nq": len(vectors_to_search),
"ids": insert_ids,
"pk_name": default_primary_key_field_name,
"limit": default_limit})
insert_ids = [i for i in range(10*default_nb, 11*default_nb)]
# 7. search with new data(no default value)
self.search(client, collection_name, vectors_to_search,
filter=f'{default_new_field_name} != {default_value}',
check_task=CheckTasks.check_search_results,
check_items={"enable_milvus_client_api": True,
"nq": len(vectors_to_search),
"ids": insert_ids,
"pk_name": default_primary_key_field_name,
"limit": default_limit})
self.drop_collection(client, collection_name)
@pytest.mark.tags(CaseLabel.L1)
@ -360,7 +381,8 @@ class TestMilvusClientAddFieldFeature(TestMilvusClientV2Base):
"stop_words": ["for", "the", "is", "a"]
}
self.add_collection_field(client, collection_name, field_name="text_content", data_type=DataType.VARCHAR,
nullable=True, max_length=1000, enable_analyzer=True, analyzer_params=analyzer_params)
nullable=True, max_length=1000, enable_analyzer=True, analyzer_params=analyzer_params,
enable_match=True)
# 4. insert data with the new analyzer field
text_data = [

49
tests/python_client/milvus_client/test_milvus_client_alter.py
View File

@ -165,10 +165,10 @@ class TestMilvusClientAlterCollection(TestMilvusClientV2Base):
self.drop_collection_properties(client, collection_name, property_keys=["lazyload.enabled"],
check_task=CheckTasks.err_res, check_items=error)
# TODO
# error = {ct.err_code: 999,
# ct.err_msg: "can not delete dynamicfield properties"}
# self.drop_collection_properties(client, collection_name, property_keys=["dynamicfield.enabled"],
# check_task=CheckTasks.err_res, check_items=error)
error = {ct.err_code: 999,
ct.err_msg: "cannot delete key dynamicfield.enabled"}
self.drop_collection_properties(client, collection_name, property_keys=["dynamicfield.enabled"],
check_task=CheckTasks.err_res, check_items=error)
res3 = self.describe_collection(client, collection_name)[0]
assert len(res1.get('properties', {})) == 1
self.drop_collection_properties(client, collection_name, property_keys=["collection.ttl.seconds"])
@ -224,35 +224,52 @@ class TestMilvusClientAlterCollection(TestMilvusClientV2Base):
vectors = cf.gen_vectors(default_nb, dim, vector_data_type=DataType.FLOAT_VECTOR)
rows_new = [{default_primary_key_field_name: i, default_vector_field_name: vectors[i],
default_string_field_name: str(i), default_new_field_name: i,
default_dynamic_field_name: i} for i in range(default_nb)]
default_dynamic_field_name: {'a': {"b": i}}} for i in range(default_nb)]
self.insert(client, collection_name, rows_new)
# 6. query using filter with dynamic field and new field
# 6. create index
index_params = self.prepare_index_params(client)[0]
index_params.add_index(field_name=default_dynamic_field_name,
index_type="INVERTED",
params={"json_cast_type": "DOUBLE",
"json_path": f"{default_dynamic_field_name}['a']['b']"})
self.create_index(client, collection_name, index_params)
index_name = "$meta/" + default_dynamic_field_name
self.describe_index(client, collection_name, index_name + "/a/b",
check_task=CheckTasks.check_describe_index_property,
check_items={
"json_cast_type": "DOUBLE",
"json_path": f"{default_dynamic_field_name}['a']['b']",
"index_type": "INVERTED",
"field_name": default_dynamic_field_name,
"index_name": index_name + "/a/b"})
# 7. query using filter with dynamic field and new field
res = self.query(client, collection_name,
filter="{} >= 0 and field_new < {}".format(default_dynamic_field_name, default_value),
filter=f"{default_dynamic_field_name}['a']['b'] >= 0 and field_new < {default_value}",
output_fields=[default_dynamic_field_name],
check_task=CheckTasks.check_query_results,
check_items={exp_res: [{"id": item["id"],
default_dynamic_field_name: item[default_dynamic_field_name]}
for item in rows_new]})[0]
assert set(res[0].keys()) == {default_dynamic_field_name, default_primary_key_field_name}
# 7. search using filter with dynamic field and new field
# 8. search using filter with dynamic field and new field
vectors_to_search = [vectors[0]]
insert_ids = [i for i in range(default_nb)]
self.search(client, collection_name, vectors_to_search,
filter="{} >= 0 and field_new < {}".format(default_dynamic_field_name, default_value),
filter=f"{default_dynamic_field_name}['a']['b'] >= 0 and field_new < {default_value}",
check_task=CheckTasks.check_search_results,
check_items={"enable_milvus_client_api": True,
"nq": len(vectors_to_search),
"ids": insert_ids,
"pk_name": default_primary_key_field_name,
"limit": default_limit})
# 8. add new field same as dynamic field name
# 9. add new field same as dynamic field name
self.add_collection_field(client, collection_name, field_name=default_dynamic_field_name,
data_type=DataType.INT64, nullable=True, default_value=default_value)
# 9. query using filter with dynamic field and new field
# 10. query using filter with dynamic field and new field
res = self.query(client, collection_name,
filter='$meta["{}"] >= 0 and {} == {}'.format(default_dynamic_field_name,
default_dynamic_field_name, default_value),
filter='$meta["{}"]["a"]["b"] >= 0 and {} == {}'.format(default_dynamic_field_name,
default_dynamic_field_name,
default_value),
output_fields=[default_dynamic_field_name, f'$meta["{default_dynamic_field_name}"]'],
check_task=CheckTasks.check_query_results,
check_items={exp_res: [{"id": item["id"], default_dynamic_field_name: default_value}
@ -260,10 +277,10 @@ class TestMilvusClientAlterCollection(TestMilvusClientV2Base):
# dynamic field same as new field name, output_fields contain dynamic field, result do not contain dynamic field
# https://github.com/milvus-io/milvus/issues/41702
assert set(res[0].keys()) == {default_dynamic_field_name, default_primary_key_field_name}
# 10. search using filter with dynamic field and new field
# 11. search using filter with dynamic field and new field
self.search(client, collection_name, vectors_to_search,
filter='$meta["{}"] >= 0 and {} == {}'.format(default_dynamic_field_name,
default_dynamic_field_name, default_value),
filter='$meta["{}"]["a"]["b"] >= 0 and {} == {}'.format(default_dynamic_field_name,
default_dynamic_field_name, default_value),
check_task=CheckTasks.check_search_results,
check_items={"enable_milvus_client_api": True,
"nq": len(vectors_to_search),