def create_collection(self):
list_collection = list_collections()
if self.collection_name in list_collection:
collection = Collection(name=self.collection_name)
else:
pk_face_id = FieldSchema(name=self.primary_name,
dtype=DataType.INT64,
is_primary=True,
auto_id=True)
field = FieldSchema(name=self.embedding_vector_field,
dtype=DataType.FLOAT_VECTOR,
dim=512)
schema = CollectionSchema(fields=[pk_face_id, field],
description="clover_staging collection")
collection = Collection(name=self.collection_name, schema=schema)
if self.partition_name is not None and collection.has_partition(
self.partition_name) is False:
collection.create_partition(self.partition_name)
return collection
def test_collection_by_DataFrame(self):
from pymilvus_orm import Collection, connections
from pymilvus_orm.schema import FieldSchema, CollectionSchema
from pymilvus_orm.types import DataType
fields = [
FieldSchema("int64", DataType.INT64),
FieldSchema("float", DataType.FLOAT),
FieldSchema("float_vector", DataType.FLOAT_VECTOR, dim=128)
]
collection_schema = CollectionSchema(fields, primary_field="int64")
connections.connect()
collection = Collection(name=gen_collection_name(),
schema=collection_schema)
collection.drop()
def __init__(self, name):
connections.add_connection(default={
'host': '127.0.0.1',
'port': '19530',
})
connections.connect(alias=name)
id_field = FieldSchema(name='id',
is_primary=True,
dtype=DataType.INT64,
description='id')
image_field = FieldSchema(name='image',
dtype=DataType.FLOAT_VECTOR,
dim=512,
description='image')
schema = CollectionSchema(fields=[id_field, image_field],
primary_field='id')
collection = Collection(name=name, schema=schema)
def test_construct_from_dataframe(self):
assert type(
Collection.construct_from_dataframe(
gen_collection_name(),
gen_pd_data(default_nb),
primary_field="int64")[0]) is Collection
def collection(self):
name = gen_collection_name()
schema = gen_schema()
yield Collection(name, schema=schema)
if connections.get_connection().has_collection(name):
connections.get_connection().drop_collection(name)
def hello_milvus():
# create connection
connections.connect()
print(f"\nList collections...")
print(list_collections())
# create collection
dim = 128
default_fields = [
FieldSchema(name="count", dtype=DataType.INT64, is_primary=True),
FieldSchema(name="random_value", dtype=DataType.DOUBLE),
FieldSchema(name="float_vector", dtype=DataType.FLOAT_VECTOR, dim=dim)
]
default_schema = CollectionSchema(fields=default_fields,
description="test collection")
print(f"\nCreate collection...")
collection = Collection(name="hello_milvus", schema=default_schema)
print(f"\nList collections...")
print(list_collections())
# insert data
nb = 3000
vectors = [[random.random() for _ in range(dim)] for _ in range(nb)]
collection.insert([[i for i in range(nb)],
[float(random.randrange(-20, -10)) for _ in range(nb)],
vectors])
print(f"\nGet collection entities...")
print(collection.num_entities)
# create index and load table
default_index = {
"index_type": "IVF_FLAT",
"params": {
"nlist": 128
},
"metric_type": "L2"
}
print(f"\nCreate index...")
collection.create_index(field_name="float_vector",
index_params=default_index)
print(f"\nload collection...")
collection.load()
# load and search
topK = 5
search_params = {"metric_type": "L2", "params": {"nprobe": 10}}
import time
start_time = time.time()
print(f"\nSearch...")
# define output_fields of search result
res = collection.search(vectors[-2:],
"float_vector",
search_params,
topK,
"count > 100",
output_fields=["count", "random_value"])
end_time = time.time()
# show result
for hits in res:
for hit in hits:
# Get value of the random value field for search result
print(hit, hit.entity.get("random_value"))
print("search latency = %.4fs" % (end_time - start_time))
# drop collection
collection.drop()
def index(self, name, field_name, collection_name, schema, get_simple_index):
# from pymilvus_orm.collection import Collection
collection = Collection(collection_name, schema=schema)
return Index(collection, field_name, get_simple_index)
def collection(self, collection_name, schema):
c = Collection(collection_name, schema=schema)
yield c
c.drop()