Deep Lake

Deep Lake 是一个用于构建 AI 应用的多模态数据库 Deep Lake 是一个用于 AI 的数据库。存储向量、图像、文本、视频等。与 LLMs/LangChain 一起使用。存储、查询、版本控制， & 可视化任何 AI 数据。实时将数据流式传输到 PyTorch/TensorFlow。

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

创建 Deep Lake 向量存储

首先，我们需要创建一个 Deep Lake 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： 自查询检索器需要您安装 lark（pip install lark）。我们还需要 deeplake 包。

%pip install --upgrade --quiet  lark

# 如果某些查询失败，请考虑手动安装 libdeeplake
%pip install --upgrade --quiet  libdeeplake

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

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
os.environ["ACTIVELOOP_TOKEN"] = getpass.getpass("Activeloop token:")

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

embeddings = OpenAIEmbeddings()

docs = [
    Document(
        page_content="一群科学家带回恐龙，混乱随之而来",
        metadata={"year": 1993, "rating": 7.7, "genre": "科幻"},
    ),
    Document(
        page_content="莱昂纳多·迪卡普里奥在梦中迷失，梦中又有梦，梦中又有梦...",
        metadata={"year": 2010, "director": "克里斯托弗·诺兰", "rating": 8.2},
    ),
    Document(
        page_content="一名心理学家/侦探在一系列梦中迷失，而《盗梦空间》重用了这个想法",
        metadata={"year": 2006, "director": "今敏", "rating": 8.6},
    ),
    Document(
        page_content="一群正常身材的女性极其健康，一些男性对她们心生向往",
        metadata={"year": 2019, "director": "格蕾塔·葛韦格", "rating": 8.3},
    ),
    Document(
        page_content="玩具复活并享受其中",
        metadata={"year": 1995, "genre": "动画"},
    ),
    Document(
        page_content="三名男子走进区域，三名男子走出区域",
        metadata={
            "year": 1979,
            "director": "安德烈·塔可夫斯基",
            "genre": "科幻",
            "rating": 9.9,
        },
    ),
]
username_or_org = "<USERNAME_OR_ORG>"
vectorstore = DeepLake.from_documents(
    docs,
    embeddings,
    dataset_path=f"hub://{username_or_org}/self_queery",
    overwrite=True,
)

您的 Deep Lake 数据集已成功创建！
``````output
/
``````output
数据集(path='hub://adilkhan/self_queery', tensors=['embedding', 'id', 'metadata', 'text'])

  tensor      htype      shape     dtype  compression
  -------    -------    -------   -------  ------- 
 embedding  embedding  (6, 1536)  float32   None   
    id        text      (6, 1)      str     None   
 metadata     json      (6, 1)      str     None   
   text       text      (6, 1)      str     None
``````output

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了！

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

/home/ubuntu/langchain_activeloop/langchain/libs/langchain/langchain/chains/llm.py:279: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.
  warnings.warn(
``````output
query='dinosaur' filter=None limit=None

[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='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, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'}),
 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})]

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

# in case if this example errored out, consider installing libdeeplake manually: `pip install libdeeplake`, and then restart notebook.

query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None

[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='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'})]

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

# 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.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None

[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'rating': 9.9, 'director': 'Andrei Tarkovsky', 'genre': 'science fiction'})]

# 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), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')]) limit=None

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

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={'year': 1993, 'rating': 7.7, 'genre': 'science fiction'}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]

Deep Lake

创建 Deep Lake 向量存储

创建自查询检索器

测试一下

过滤 k

此页面是否有帮助？

您还可以留下详细的反馈在 GitHub 上

Deep Lake

创建 Deep Lake 向量存储​

创建自查询检索器​

测试一下​

过滤 k​

此页面是否有帮助？

您还可以留下详细的反馈 在 GitHub 上

创建 Deep Lake 向量存储

创建自查询检索器

测试一下

过滤 k

您还可以留下详细的反馈在 GitHub 上