milvus的单向量搜索

准备测试数据:

为了方便观察，dim维度设置为3。

import uuid

import numpy as np
from pymilvus import (
    connections,
    FieldSchema, CollectionSchema, DataType,
    Collection,
)

collection_name = "hello_milvus"
host = "192.168.0.109"
port = 19530
username = ""
password = ""
num_entities, dim = 3000, 128

def generate_uuids(number_of_uuids):
    uuids = [str(uuid.uuid4()) for _ in range(number_of_uuids)]
    return uuids

print("start connecting to Milvus")
connections.connect("default", host=host, port=port,user=username,password=password)

fields = [
    FieldSchema(name="pk", dtype=DataType.INT64, is_primary=True, auto_id=False),
    FieldSchema(name="random", dtype=DataType.DOUBLE),
    FieldSchema(name="comment", dtype=DataType.VARCHAR, max_length=200),
    FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=dim)
]

schema = CollectionSchema(fields, "hello_milvus is the simplest demo to introduce the APIs")

print("Create collection `hello_world`")
coll = Collection(collection_name, schema, consistency_level="Bounded",shards_num=1)

print("Start inserting entities")
rng = np.random.default_rng(seed=19530)
entities = [
    [i for i in range(num_entities)],
    rng.random(num_entities).tolist(),
    generate_uuids(num_entities),
    rng.random((num_entities, dim)),
]
insert_result = coll.insert(entities)

print("Start flush")
coll.flush()

print("Start creating index")
index_params = {
    "index_type": "HNSW",
    "metric_type": "COSINE",
    "params": {
        "M": 16,
        "efConstruction": 40
    }
}

coll.create_index(
  field_name="embeddings",
  index_params=index_params,
  index_name="idx_em"
)

coll.load()

print("done")

执行向量搜索:

import random
from pymilvus import (
    connections,
    Collection,
)

dim = 3

if __name__ == '__main__':
    connections.connect(
        alias="default",
        user='',
        password='',
        host='192.168.0.109',
        port='19530'
    )

    coll = Collection("hello_milvus")

    search_param = {
        "metric_type": "COSINE",
        "params": {"ef": 40}
    }
    search_data = [random.random() for _ in range(dim)]
    results = coll.search(
        data=[search_data],
        anns_field="embeddings",
        param=search_param,
        limit=5,
        # expr=None,
        output_fields=['pk','embeddings'],
        # consistency_level="Eventually"
    )
    print(results)

注意:ef >= limit数量