Pinecone

Pinecone 是一个功能广泛的向量数据库。

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

创建一个 Pinecone 索引

首先，我们需要创建一个 Pinecone 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。

要使用 Pinecone，您必须安装 pinecone 包，并且必须拥有 API 密钥和环境。以下是 安装说明。

注意： 自查询检索器要求您安装 lark 包。

%pip install --upgrade --quiet  lark

%pip install --upgrade --quiet pinecone-notebooks pinecone-client==3.2.2

# Connect to Pinecone and get an API key.
from pinecone_notebooks.colab import Authenticate

Authenticate()

import os

api_key = os.environ["PINECONE_API_KEY"]

/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/pinecone/index.py:4: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)
  from tqdm.autonotebook import tqdm

我们想使用 OpenAIEmbeddings，所以我们必须获取 OpenAI API 密钥。

import getpass

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

from pinecone import Pinecone, ServerlessSpec

api_key = os.getenv("PINECONE_API_KEY") or "PINECONE_API_KEY"

index_name = "langchain-self-retriever-demo"

pc = Pinecone(api_key=api_key)

<!--IMPORTS:[{"imported": "Document", "source": "langchain_core.documents", "docs": "https://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html", "title": "Pinecone"}, {"imported": "OpenAIEmbeddings", "source": "langchain_openai", "docs": "https://python.langchain.com/api_reference/openai/embeddings/langchain_openai.embeddings.base.OpenAIEmbeddings.html", "title": "Pinecone"}, {"imported": "PineconeVectorStore", "source": "langchain_pinecone", "docs": "https://python.langchain.com/api_reference/pinecone/vectorstores/langchain_pinecone.vectorstores.PineconeVectorStore.html", "title": "Pinecone"}]-->
from langchain_core.documents import Document
from langchain_openai import OpenAIEmbeddings
from langchain_pinecone import PineconeVectorStore

embeddings = OpenAIEmbeddings()

# create new index
if index_name not in pc.list_indexes().names():
    pc.create_index(
        name=index_name,
        dimension=1536,
        metric="cosine",
        spec=ServerlessSpec(cloud="aws", region="us-east-1"),
    )

docs = [
    Document(
        page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose",
        metadata={"year": 1993, "rating": 7.7, "genre": ["action", "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", "thriller"],
            "rating": 9.9,
        },
    ),
]
vectorstore = PineconeVectorStore.from_documents(
    docs, embeddings, index_name="langchain-self-retriever-demo"
)

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。

<!--IMPORTS:[{"imported": "AttributeInfo", "source": "langchain.chains.query_constructor.base", "docs": "https://python.langchain.com/api_reference/langchain/chains/langchain.chains.query_constructor.schema.AttributeInfo.html", "title": "Pinecone"}, {"imported": "SelfQueryRetriever", "source": "langchain.retrievers.self_query.base", "docs": "https://python.langchain.com/api_reference/langchain/retrievers/langchain.retrievers.self_query.base.SelfQueryRetriever.html", "title": "Pinecone"}, {"imported": "OpenAI", "source": "langchain_openai", "docs": "https://python.langchain.com/api_reference/openai/llms/langchain_openai.llms.base.OpenAI.html", "title": "Pinecone"}]-->
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
)

测试它

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

[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'genre': ['action', 'science fiction'], 'rating': 7.7, 'year': 1993.0}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'year': 1995.0}),
 Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'director': 'Satoshi Kon', 'rating': 8.6, 'year': 2006.0}),
 Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'director': 'Christopher Nolan', 'rating': 8.2, 'year': 2010.0})]

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

query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)

[Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'director': 'Satoshi Kon', 'rating': 8.6, 'year': 2006.0}),
 Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'director': 'Andrei Tarkovsky', 'genre': ['science fiction', 'thriller'], 'rating': 9.9, 'year': 1979.0})]

# 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')

[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'director': 'Greta Gerwig', 'rating': 8.3, 'year': 2019.0})]

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

query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction'), Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)])

[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'director': 'Andrei Tarkovsky', 'genre': ['science fiction', 'thriller'], 'rating': 9.9, 'year': 1979.0})]

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

query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990.0), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005.0), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')])

[Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'year': 1995.0})]

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,
)

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