操作Milvus数据库

核心操作示例

from pymilvus import MilvusClient
import numpy as np

# 初始化客户端
client = MilvusClient("./milvus_demo.db")  # 本地
# client = MilvusClient(uri="http://host:19530")  # 远程

# 创建集合
client.create_collection(
    collection_name="demo_collection",
    dimension=384
)

# 准备数据
docs = [
    "Artificial intelligence was founded as an academic discipline in 1956.",
    "Alan Turing was the first person to conduct substantial research in AI.",
    "Born in Maida Vale, London, Turing was raised in southern England.",
]

# 生成随机向量
vectors = [[np.random.uniform(-1, 1) for _ in range(384)] for _ in range(len(docs))]

# 插入数据
data = [
    {"id": i, "vector": vectors[i], "text": docs[i], "subject": "history"}
    for i in range(len(vectors))
]
client.insert(collection_name="demo_collection", data=data)

# 相似性搜索
res = client.search(
    collection_name="demo_collection",
    data=[vectors[0]],
    filter="subject == 'history'",
    limit=2,
    output_fields=["text", "subject"]
)

# 条件查询
res = client.query(
    collection_name="demo_collection",
    filter="subject == 'history'",
    output_fields=["text", "subject"]
)

# 删除数据
client.delete(collection_name="demo_collection", filter="subject == 'history'")

常用 API

操作	方法
创建集合	create_collection(name, dimension)
插入数据	insert(collection, data)
向量搜索	search(collection, data, filter, limit)
条件查询	query(collection, filter, output_fields)
删除数据	delete(collection, filter)
查看集合	describe_collection(name)
删除集合	drop_collection(name)