Astra DB

DataStax Astra DB 是一个构建于 Apache Cassandra® 之上，通过易于使用的 JSON API 方便地提供的无服务器 AI 就绪数据库。

在本教程中，我们将演示使用 Astra DB 向量存储的 SelfQueryRetriever。

创建 Astra DB 向量存储

首先，创建一个 Astra DB 向量存储并使用一些数据对其进行初始化。

我们创建了一个包含电影摘要的小型演示文档集。

注意：自查询检索器需要安装 `lark` 包（`pip install lark`）。

!pip install "langchain-astradb>=0.6,<0.7" \
  "langchain_openai>=0.3,<0.4" \
  "lark>=1.2,<2.0"

在此示例中，您将使用 OpenAIEmbeddings。请输入 OpenAI API 密钥。

import os
from getpass import getpass

from langchain_openai.embeddings import OpenAIEmbeddings

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass("OpenAI API Key:")

embeddings = OpenAIEmbeddings()

API 参考：OpenAIEmbeddings

OpenAI API Key: ········

创建 Astra DB VectorStore

API 端点类似于 https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com
Token 类似于 AstraCS:aBcD0123...

ASTRA_DB_API_ENDPOINT = input("ASTRA_DB_API_ENDPOINT = ")
ASTRA_DB_APPLICATION_TOKEN = getpass("ASTRA_DB_APPLICATION_TOKEN = ")

ASTRA_DB_API_ENDPOINT =  https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com
ASTRA_DB_APPLICATION_TOKEN =  ········

from langchain_astradb import AstraDBVectorStore
from langchain_core.documents import Document

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 = AstraDBVectorStore.from_documents(
    docs,
    embeddings,
    collection_name="astra_self_query_demo",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)

API 参考：AstraDBVectorStore | Document

创建自查询检索器

现在您可以实例化该检索器。

为此，您需要预先提供有关文档支持的元数据字段的一些信息，以及文档内容的简短描述。

from langchain.chains.query_constructor.schema 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,
)

API 参考：AttributeInfo | SelfQueryRetriever | OpenAI

试用

现在您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?")

[Document(id='d7b9ec1edafa467caab524455e8c1f5d', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}, page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose'),
 Document(id='8ad04ef2a73d4f74897a51e49be1a8d2', metadata={'year': 1995, 'genre': 'animated'}, page_content='Toys come alive and have a blast doing so'),
 Document(id='5b07e600d3494506952b60e0a45a0546', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'rating': 9.9}, page_content='Three men walk into the Zone, three men walk out of the Zone'),
 Document(id='a0cef19e27c341929098ac4793602829', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea')]

# This example specifies a filter
retriever.invoke("I want to watch a movie rated higher than 8.5")

[Document(id='5b07e600d3494506952b60e0a45a0546', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'rating': 9.9}, page_content='Three men walk into the Zone, three men walk out of the Zone'),
 Document(id='a0cef19e27c341929098ac4793602829', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea')]

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

[Document(id='0539843fd203484c9be486c2a0e2454c', metadata={'year': 2019, 'director': 'Greta Gerwig', 'rating': 8.3}, page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them')]

# This example specifies a composite filter
retriever.invoke("What's a highly rated (above 8.5), science fiction movie ?")

[Document(id='a0cef19e27c341929098ac4793602829', metadata={'year': 2006, 'director': 'Satoshi Kon', 'rating': 8.6}, page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea'),
 Document(id='5b07e600d3494506952b60e0a45a0546', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'rating': 9.9}, page_content='Three men walk into the Zone, three men walk out of the Zone')]

# This example specifies a query and composite filter
retriever.invoke(
    "What's a movie about toys after 1990 but before 2005, and is animated"
)

[Document(id='8ad04ef2a73d4f74897a51e49be1a8d2', metadata={'year': 1995, 'genre': 'animated'}, page_content='Toys come alive and have a blast doing so')]

设置限制 ('k')

您还可以使用自查询检索器来指定 k，即要获取的文档数量。

通过向构造函数传递 enable_limit=True 即可实现此目的。

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

# This example only specifies a relevant query
retriever_k.invoke("What are two movies about dinosaurs?")

[Document(id='d7b9ec1edafa467caab524455e8c1f5d', metadata={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}, page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose'),
 Document(id='8ad04ef2a73d4f74897a51e49be1a8d2', metadata={'year': 1995, 'genre': 'animated'}, page_content='Toys come alive and have a blast doing so')]

清理

如果您想从 Astra DB 实例中完全删除集合，请运行此命令。

（您将丢失其中存储的数据。）

vectorstore.delete_collection()

创建 Astra DB 向量存储​

创建自查询检索器​

试用​

设置限制 ('k')​

清理​

创建 Astra DB 向量存储

创建自查询检索器

试用

设置限制 ('k')

清理