Weaviate

Weaviate 是一个开源的向量数据库。它允许您存储数据对象和来自您喜欢的机器学习模型的向量嵌入，并能够无缝扩展到数十亿个数据对象。

在笔记本中，我们将演示围绕 Weaviate 向量存储的 SelfQueryRetriever。

创建 Weaviate 向量存储

首先，我们需要创建一个 Weaviate 向量存储，并用一些数据进行初始化。我们创建了一小组包含电影摘要的演示文档。

注意： 自查询检索器要求您安装 lark (pip install lark)。我们还需要 weaviate-client 包。

%pip install --upgrade --quiet  lark weaviate-client

from langchain_community.vectorstores import Weaviate
from langchain_core.documents import Document
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()

docs = [
    Document(
        page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose",
        metadata={"year": 1993, "rating": 7.7, "genre": "science fiction"},
    ),
    Document(
        page_content="Leo DiCaprio gets lost in a dream within a dream within a dream within a ...",
        metadata={"year": 2010, "director": "Christopher Nolan", "rating": 8.2},
    ),
    Document(
        page_content="A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea",
        metadata={"year": 2006, "director": "Satoshi Kon", "rating": 8.6},
    ),
    Document(
        page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them",
        metadata={"year": 2019, "director": "Greta Gerwig", "rating": 8.3},
    ),
    Document(
        page_content="Toys come alive and have a blast doing so",
        metadata={"year": 1995, "genre": "animated"},
    ),
    Document(
        page_content="Three men walk into the Zone, three men walk out of the Zone",
        metadata={
            "year": 1979,
            "director": "Andrei Tarkovsky",
            "genre": "science fiction",
            "rating": 9.9,
        },
    ),
]
vectorstore = Weaviate.from_documents(
    docs, embeddings, weaviate_url="http://127.0.0.1:8080"
)

创建自查询检索器

现在我们可以实例化我们的检索器。为此，我们需要提前提供一些关于文档支持的元数据字段的信息以及文档内容的简短描述。

from langchain.chains.query_constructor.base import AttributeInfo
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain_openai import OpenAI

metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genre of the movie",
        type="string or list[string]",
    ),
    AttributeInfo(
        name="year",
        description="The year the movie was released",
        type="integer",
    ),
    AttributeInfo(
        name="director",
        description="The name of the movie director",
        type="string",
    ),
    AttributeInfo(
        name="rating", description="A 1-10 rating for the movie", type="float"
    ),
]
document_content_description = "Brief summary of a movie"
llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(
    llm, vectorstore, document_content_description, metadata_field_info, verbose=True
)

测试一下

现在我们可以尝试实际使用我们的检索器！

# This example only specifies a relevant query
retriever.invoke("What are some movies about dinosaurs")

query='dinosaur' filter=None limit=None

[Document(page_content='一群科学家复活了恐龙，随之而来的是混乱', metadata={'genre': '科幻', 'rating': 7.7, 'year': 1993}),
 Document(page_content='玩具复活并乐在其中', metadata={'genre': '动画', 'rating': None, 'year': 1995}),
 Document(page_content='三个男人走进区域，三个男人走出区域', metadata={'genre': '科幻', 'rating': 9.9, 'year': 1979}),
 Document(page_content='一位心理学家/侦探在一系列梦中迷失，而《盗梦空间》重用了这个创意', metadata={'genre': None, 'rating': 8.6, 'year': 2006})]

# This example specifies a query and a filter
retriever.invoke("Has Greta Gerwig directed any movies about women")

query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None

[Document(page_content='一群正常身材的女性非常善良，一些男性对她们心怀向往', metadata={'genre': None, 'rating': 8.3, 'year': 2019})]

过滤 k

我们还可以使用自查询检索器来指定 k：要获取的文档数量。

我们可以通过将 enable_limit=True 传递给构造函数来实现这一点。

retriever = SelfQueryRetriever.from_llm(
    llm,
    vectorstore,
    document_content_description,
    metadata_field_info,
    enable_limit=True,
    verbose=True,
)

# 此示例仅指定一个相关查询
retriever.invoke("what are two movies about dinosaurs")

query='dinosaur' filter=None limit=2

[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'genre': 'science fiction', 'rating': 7.7, 'year': 1993}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'rating': None, 'year': 1995})]