跳至主要内容

Milvus

Milvus 是一个存储、索引和管理由深度神经网络和其他机器学习 (ML) 模型生成的庞大嵌入向量的数据库。

此笔记本展示了如何使用与 Milvus 向量数据库相关的功能。

设置

您需要使用 pip install -qU langchain-milvus 安装 langchain-milvus 才能使用此集成。

%pip install -qU  langchain_milvus

最新版本的 pymilvus 带有一个本地向量数据库 Milvus Lite,适用于原型设计。如果您有大量数据(例如超过一百万个文档),我们建议在 docker 或 kubernetes 上设置更高性能的 Milvus 服务器。

凭据

使用 Milvus 向量存储不需要任何凭据。

初始化

pip install -qU langchain-openai
import getpass

os.environ["OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
from langchain_milvus import Milvus

# The easiest way is to use Milvus Lite where everything is stored in a local file.
# If you have a Milvus server you can use the server URI such as "http://localhost:19530".
URI = "./milvus_example.db"

vector_store = Milvus(
embedding_function=embeddings,
connection_args={"uri": URI},
)

使用 Milvus 集合对数据进行分隔

您可以在同一 Milvus 实例中的不同集合中存储不同的无关文档以维护上下文

以下是如何创建新集合的方法

from langchain_core.documents import Document

vector_store_saved = Milvus.from_documents(
[Document(page_content="foo!")],
embeddings,
collection_name="langchain_example",
connection_args={"uri": URI},
)
API 参考:文档

以下是如何检索已存储的集合的方法

vector_store_loaded = Milvus(
embeddings,
connection_args={"uri": URI},
collection_name="langchain_example",
)

管理向量存储

创建向量存储后,我们可以通过添加和删除不同的项目与之交互。

将项目添加到向量存储

我们可以使用 add_documents 函数将项目添加到我们的向量存储中。

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
metadata={"source": "tweet"},
)

document_2 = Document(
page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
metadata={"source": "news"},
)

document_3 = Document(
page_content="Building an exciting new project with LangChain - come check it out!",
metadata={"source": "tweet"},
)

document_4 = Document(
page_content="Robbers broke into the city bank and stole $1 million in cash.",
metadata={"source": "news"},
)

document_5 = Document(
page_content="Wow! That was an amazing movie. I can't wait to see it again.",
metadata={"source": "tweet"},
)

document_6 = Document(
page_content="Is the new iPhone worth the price? Read this review to find out.",
metadata={"source": "website"},
)

document_7 = Document(
page_content="The top 10 soccer players in the world right now.",
metadata={"source": "website"},
)

document_8 = Document(
page_content="LangGraph is the best framework for building stateful, agentic applications!",
metadata={"source": "tweet"},
)

document_9 = Document(
page_content="The stock market is down 500 points today due to fears of a recession.",
metadata={"source": "news"},
)

document_10 = Document(
page_content="I have a bad feeling I am going to get deleted :(",
metadata={"source": "tweet"},
)

documents = [
document_1,
document_2,
document_3,
document_4,
document_5,
document_6,
document_7,
document_8,
document_9,
document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)
API 参考:文档
['b0248595-2a41-4f6b-9c25-3a24c1278bb3',
'fa642726-5329-4495-a072-187e948dd71f',
'9905001c-a4a3-455e-ab94-72d0ed11b476',
'eacc7256-d7fa-4036-b1f7-83d7a4bee0c5',
'7508f7ff-c0c9-49ea-8189-634f8a0244d8',
'2e179609-3ff7-4c6a-9e05-08978903fe26',
'fab1f2ac-43e1-45f9-b81b-fc5d334c6508',
'1206d237-ee3a-484f-baf2-b5ac38eeb314',
'd43cbf9a-a772-4c40-993b-9439065fec01',
'25e667bb-6f09-4574-a368-661069301906']

从向量存储中删除项目

vector_store.delete(ids=[uuids[-1]])
(insert count: 0, delete count: 1, upsert count: 0, timestamp: 0, success count: 0, err count: 0, cost: 0)

查询向量存储

创建向量存储并添加相关文档后,您很可能希望在运行链或代理时查询它。

直接查询

执行简单的相似性搜索并对元数据进行过滤,可以按如下方式进行

results = vector_store.similarity_search(
"LangChain provides abstractions to make working with LLMs easy",
k=2,
filter={"source": "tweet"},
)
for res in results:
print(f"* {res.page_content} [{res.metadata}]")
* Building an exciting new project with LangChain - come check it out! [{'pk': '9905001c-a4a3-455e-ab94-72d0ed11b476', 'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'pk': '1206d237-ee3a-484f-baf2-b5ac38eeb314', 'source': 'tweet'}]

带分数的相似性搜索

您也可以使用分数进行搜索

results = vector_store.similarity_search_with_score(
"Will it be hot tomorrow?", k=1, filter={"source": "news"}
)
for res, score in results:
print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")
* [SIM=21192.628906] bar [{'pk': '2', 'source': 'https://example.com'}]

有关使用 Milvus 向量存储时可用的所有搜索选项的完整列表,您可以访问 API 参考

通过转换为检索器进行查询

您还可以将向量存储转换为检索器,以便在您的链中更轻松地使用。

retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 1})
retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})
[Document(metadata={'pk': 'eacc7256-d7fa-4036-b1f7-83d7a4bee0c5', 'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]

检索增强生成的使用

有关如何将此向量存储用于检索增强生成 (RAG) 的指南,请参阅以下部分

每个用户的检索

在构建检索应用程序时,您通常需要考虑到多个用户。这意味着您可能不仅要为一个用户存储数据,还要为许多不同的用户存储数据,并且他们不应该能够看到彼此的数据。

Milvus 建议使用 partition_key 来实现多租户,以下是一个示例。

分区键的功能目前在 Milvus Lite 中不可用,如果您想使用它,则需要从 docker 或 kubernetes 启动 Milvus 服务器。

from langchain_core.documents import Document

docs = [
Document(page_content="i worked at kensho", metadata={"namespace": "harrison"}),
Document(page_content="i worked at facebook", metadata={"namespace": "ankush"}),
]
vectorstore = Milvus.from_documents(
docs,
embeddings,
connection_args={"uri": URI},
drop_old=True,
partition_key_field="namespace", # Use the "namespace" field as the partition key
)
API 参考:文档

要使用分区键进行搜索,您应该在搜索请求的布尔表达式中包含以下任一项

search_kwargs={"expr": '<partition_key> == "xxxx"'}

search_kwargs={"expr": '<partition_key> == in ["xxx", "xxx"]'}

请将 <partition_key> 替换为指定为分区键的字段的名称。

Milvus 根据指定的分区键更改为分区,根据分区键过滤实体,并在过滤后的实体中进行搜索。

# This will only get documents for Ankush
vectorstore.as_retriever(search_kwargs={"expr": 'namespace == "ankush"'}).invoke(
"where did i work?"
)
[Document(page_content='i worked at facebook', metadata={'namespace': 'ankush'})]
# This will only get documents for Harrison
vectorstore.as_retriever(search_kwargs={"expr": 'namespace == "harrison"'}).invoke(
"where did i work?"
)
[Document(page_content='i worked at kensho', metadata={'namespace': 'harrison'})]

API 参考

有关所有 __ModuleName__VectorStore 功能和配置的详细文档,请访问 API 参考: https://python.langchain.ac.cn/api_reference/milvus/vectorstores/langchain_milvus.vectorstores.milvus.Milvus.html


此页面是否有帮助?


您还可以留下详细的反馈 在 GitHub 上.