本地Milvus数据库

Milvus Lite

Milvus Lite 是 Python 库，可嵌入到应用中，适合快速原型开发和边缘设备。

安装

pip install pymilvus

注意：pymilvus 2.4.2+ 已内置 milvus-lite

快速入门

from pymilvus import MilvusClient
import numpy as np

# 初始化客户端（本地文件存储）
client = MilvusClient("./milvus_demo.db")

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

# 准备数据
docs = [
    "Artificial intelligence was founded in 1956.",
    "Alan Turing was the first person to conduct substantial research in AI.",
]

# 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'")

支持环境

• Ubuntu >= 20.04（x86_64 / arm64）
• MacOS >= 11.0（M1/M2 / x86_64）

部署选择建议

场景	推荐
快速原型/RAG演示	Milvus Lite
早期生产（1亿以下）	Milvus Standalone
大规模生产（1亿以上）	Milvus Distributed
边缘设备私有搜索	Milvus Lite