Skip to main content
Activeloop Deep Lake 是一个多模态向量存储，可存储嵌入向量及其元数据，包括文本、JSON、图像、音频、视频等多种类型的数据。它支持将数据保存在本地、您的云端或 Activeloop 的存储服务上，并支持包含嵌入向量及其属性的混合搜索。
本 notebook 展示了 Activeloop Deep Lake 的基本功能。Deep Lake 不仅能存储嵌入向量，还能存储任何类型的数据。它是一个无服务器的数据湖，具备版本控制、查询引擎以及面向深度学习框架的流式数据加载器。 更多信息请参阅 Deep Lake 文档

​
环境准备

pip install -qU  langchain-openai langchain-deeplake tiktoken

​
Activeloop 官方示例

与 LangChain 集成。

​
本地使用 Deep Lake

from langchain_deeplake.vectorstores import DeeplakeVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

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.document_loaders import TextLoader

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

​
创建本地数据集

在 ./my_deeplake/ 本地创建数据集，然后执行相似度搜索。Deeplake+LangChain 集成在底层使用 Deep Lake 数据集，因此 dataset（数据集）和 vector store（向量存储）可互换使用。要在自己的云端或 Deep Lake 存储中创建数据集，请相应调整路径。 
db = DeeplakeVectorStore(
    dataset_path="./my_deeplake/", embedding_function=embeddings, overwrite=True
)
db.add_documents(docs)
# or shorter
# db = DeepLake.from_documents(docs, dataset_path="./my_deeplake/", embedding_function=embeddings, overwrite=True)

​
查询数据集

query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)

print(docs[0].page_content)
之后，您可以在不重新计算嵌入向量的情况下重新加载数据集 
db = DeeplakeVectorStore(
    dataset_path="./my_deeplake/", embedding_function=embeddings, read_only=True
)
docs = db.similarity_search(query)
设置 read_only=True 可防止在不需要更新时意外修改向量存储，确保数据保持不变，除非有明确的修改意图。通常建议指定此参数以避免意外更新。

​
检索问答

from langchain_classic.chains import RetrievalQA
from langchain_openai import ChatOpenAI

qa = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model="gpt-3.5-turbo"),
    chain_type="stuff",
    retriever=db.as_retriever(),
)

query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)

​
基于元数据属性的过滤

让我们创建另一个向量存储，其元数据中包含文档创建年份。 
import random

for d in docs:
    d.metadata["year"] = random.randint(2012, 2014)

db = DeeplakeVectorStore.from_documents(
    docs, embeddings, dataset_path="./my_deeplake/", overwrite=True
)

db.similarity_search(
    "What did the president say about Ketanji Brown Jackson",
    filter={"metadata": {"year": 2013}},
)

​
选择距离函数

距离函数：L2 表示欧氏距离，cos 表示余弦相似度 
db.similarity_search(
    "What did the president say about Ketanji Brown Jackson?", distance_metric="l2"
)

​
最大边际相关性

使用最大边际相关性 
db.max_marginal_relevance_search(
    "What did the president say about Ketanji Brown Jackson?"
)

​
删除数据集

db.delete_dataset()

​
云端 Deep Lake 数据集（Activeloop、AWS、GCS 等）或内存模式

默认情况下，Deep Lake 数据集存储在本地。要将其存储在内存、Deep Lake 托管数据库或任何对象存储中，您可以在创建向量存储时提供对应的路径和凭证。某些路径需要在 Activeloop 注册并创建 API token，可在此处获取。 
os.environ["ACTIVELOOP_TOKEN"] = activeloop_token

# Embed and store the texts
username = "<USERNAME_OR_ORG>"  # your username on app.activeloop.ai
dataset_path = f"hub://{username}/langchain_testing_python"  # could be also ./local/path (much faster locally), s3://bucket/path/to/dataset, gcs://path/to/dataset, etc.

docs = text_splitter.split_documents(documents)

embedding = OpenAIEmbeddings()
db = DeeplakeVectorStore(
    dataset_path=dataset_path, embedding_function=embeddings, overwrite=True
)
ids = db.add_documents(docs)

query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)
print(docs[0].page_content)

# Embed and store the texts
username = "<USERNAME_OR_ORG>"  # your username on app.activeloop.ai
dataset_path = f"hub://{username}/langchain_testing"

docs = text_splitter.split_documents(documents)

embedding = OpenAIEmbeddings()
db = DeeplakeVectorStore(
    dataset_path=dataset_path,
    embedding_function=embeddings,
    overwrite=True,
)
ids = db.add_documents(docs)

​
TQL 搜索

此外，similarity_search 方法支持执行查询，可利用 Deep Lake 的张量查询语言（TQL）来指定查询条件。 
search_id = db.dataset["ids"][0]

docs = db.similarity_search(
    query=None,
    tql=f"SELECT * WHERE ids == '{search_id}'",
)

db.dataset.summary()

​
在 AWS S3 上创建向量存储

dataset_path = "s3://BUCKET/langchain_test"  # could be also ./local/path (much faster locally), hub://bucket/path/to/dataset, gcs://path/to/dataset, etc.

embedding = OpenAIEmbeddings()
db = DeeplakeVectorStore.from_documents(
    docs,
    dataset_path=dataset_path,
    embedding=embeddings,
    overwrite=True,
    creds={
        "aws_access_key_id": os.environ["AWS_ACCESS_KEY_ID"],
        "aws_secret_access_key": os.environ["AWS_SECRET_ACCESS_KEY"],
        "aws_session_token": os.environ["AWS_SESSION_TOKEN"],  # Optional
    },
)

​
Deep Lake API

您可以通过 db.vectorstore 访问 Deep Lake 数据集 
# get structure of the dataset
db.dataset.summary()

# get embeddings numpy array
embeds = db.dataset["embeddings"][:]

​
将本地数据集迁移至云端

将已创建的数据集复制到云端。您也可以从云端迁移到本地。 
import deeplake

username = "<USERNAME_OR_ORG>"  # your username on app.activeloop.ai
source = f"hub://{username}/langchain_testing"  # could be local, s3, gcs, etc.
destination = f"hub://{username}/langchain_test_copy"  # could be local, s3, gcs, etc.


deeplake.copy(src=source, dst=destination)

db = DeeplakeVectorStore(dataset_path=destination, embedding_function=embeddings)
db.add_documents(docs)
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.