DashVector

DashVector 是一個完全託管的向量資料庫服務，支援高維度稠密和稀疏向量、即時插入和過濾搜尋。它旨在自動擴展，並能適應不同的應用需求。向量檢索服務 DashVector 基於 DAMO Academy 獨立開發的高效向量引擎 Proxima 核心，並提供具備水平擴展能力的雲原生、完全託管的向量檢索服務。DashVector 通過簡單易用的 SDK/API 介面，公開其強大的向量管理、向量查詢和其他多樣化功能，可被上層 AI 應用快速整合，從而為包括大型模型生態、多模態 AI 搜尋、分子結構分析等多種應用場景提供服務，並提供所需的高效向量檢索能力。

在本筆記本中，我們將示範如何使用 DashVector 向量資料庫的 SelfQueryRetriever。

建立 DashVector 向量資料庫

首先，我們需要建立一個 DashVector 向量資料庫，並用一些資料來初始化它。我們建立了一個小型示範文件集，其中包含電影摘要。

要使用 DashVector，您必須安裝 dashvector 套件，並且必須擁有 API 金鑰和環境。這裡有安裝說明。

注意：自我查詢檢索器需要您安裝 lark 套件。

%pip install --upgrade --quiet  lark dashvector

import os

import dashvector

client = dashvector.Client(api_key=os.environ["DASHVECTOR_API_KEY"])

from langchain_community.embeddings import DashScopeEmbeddings
from langchain_community.vectorstores import DashVector
from langchain_core.documents import Document

embeddings = DashScopeEmbeddings()

# create DashVector collection
client.create("langchain-self-retriever-demo", dimension=1536)

API Reference:DashScopeEmbeddings | DashVector | Document

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

建立您的自我查詢檢索器

現在我們可以實例化我們的檢索器。為此，我們需要預先提供一些關於文件支援的元數據欄位資訊，以及文件內容的簡短描述。

from langchain.chains.query_constructor.schema import AttributeInfo
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain_community.llms import Tongyi

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 = Tongyi(temperature=0)
retriever = SelfQueryRetriever.from_llm(
    llm, vectorstore, document_content_description, metadata_field_info, verbose=True
)

API Reference:AttributeInfo | SelfQueryRetriever | Tongyi

測試一下

現在我們可以嘗試實際使用我們的檢索器了！

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

query='dinosaurs' filter=None limit=None

[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.699999809265137, 'genre': 'action'}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),
 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': 8.199999809265137}),
 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': 8.600000381469727})]

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

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

[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'rating': 9.899999618530273, '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': 8.600000381469727})]

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

query='Greta Gerwig' 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': 8.300000190734863})]

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

query='science fiction' 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)]) limit=None

[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'rating': 9.899999618530273, 'genre': 'science fiction'})]

篩選 k

我們也可以使用自我查詢檢索器來指定 k：要獲取的文件數量。

我們可以通過將 enable_limit=True 傳遞給建構函式來做到這一點。

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")

query='dinosaurs' filter=None limit=2

[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.699999809265137, 'genre': 'action'}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]

建立 DashVector 向量資料庫​

建立您的自我查詢檢索器​

測試一下​

篩選 k​

此頁面是否有幫助？

建立 DashVector 向量資料庫

建立您的自我查詢檢索器

測試一下

篩選 k