Deep Lake
Deep Lake 是一個用於構建 AI 應用程式的多模態資料庫。Deep Lake 是一個用於 AI 的資料庫。儲存向量、圖像、文字、影片等。與 LLM/LangChain 搭配使用。儲存、查詢、版本控制和視覺化任何 AI 資料。即時將資料串流到 PyTorch/TensorFlow。
在筆記本中，我們將示範 SelfQueryRetriever 包裝在 Deep Lake 向量儲存庫周圍的用法。
建立 Deep Lake 向量儲存庫
首先，我們需要建立一個 Deep Lake 向量儲存庫，並使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。
注意： 自我查詢檢索器需要您安裝 lark (pip install lark)。我們還需要 deeplake 套件。
%pip install --upgrade --quiet lark
# in case if some queries fail consider installing libdeeplake manually
%pip install --upgrade --quiet libdeeplake
我們想要使用 OpenAIEmbeddings，因此我們必須取得 OpenAI API 金鑰。
import getpass
import os
if "OPENAI_API_KEY" not in os.environ:
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
if "ACTIVELOOP_TOKEN" not in os.environ:
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="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,
},
),
]
username_or_org = "<USERNAME_OR_ORG>"
vectorstore = DeepLake.from_documents(
docs,
embeddings,
dataset_path=f"hub://{username_or_org}/self_queery",
overwrite=True,
)
Your Deep Lake dataset has been successfully created!
``````output
/
``````output
Dataset(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
建立我們的自我查詢檢索器
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我們的文件支援的中繼資料欄位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_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
)
測試一下
現在我們可以嘗試實際使用我們的檢索器！
# 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'})]
篩選 k
我們也可以使用自我查詢檢索器來指定 k：要提取的文件數量。
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='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'})]