Skip to main content
Open In ColabOpen on GitHub

Activeloop Deep Lake

Activeloop Deep Lake 作为多模态向量存储，可存储嵌入向量及其元数据，包括文本、JSON、图像、音频、视频等。它可将数据保存在本地、您的云存储中或Activeloop存储上，并支持结合嵌入向量及其属性的混合搜索。

这个笔记本展示了与Activeloop Deep Lake基本功能相关的示例。虽然Deep Lake可以存储嵌入向量，但它能够存储任何类型的数据。它是一个无服务器的数据湖，具有版本控制、查询引擎和流式数据加载器，支持深度学习框架。

对于更多信息，请参见Deep Lake 文档

设置​

%pip install --upgrade --quiet  langchain-openai langchain-deeplake tiktoken

由Activeloop提供的示例​

与LangChain集成.

本地的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()
API 参考:文本加载器

创建本地数据集​

在本地创建数据集于./my_deeplake/，然后运行相似性搜索。Deeplake+LangChain 集成使用 Deep Lake 数据集底层实现，因此dataset和vector store可以互换使用。要在自己的云中或 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)

无需重新计算向量，您可以稍后重新加载数据集

db = DeeplakeVectorStore(
    dataset_path="./my_deeplake/", embedding_function=embeddings, read_only=True
)
docs = db.similarity_search(query)

设置read_only=True可以防止在不需要更新时意外修改向量存储，从而确保数据保持不变，除非明确意图更改。通常建议指定此参数以避免无意中的更新。

检索问答​

from langchain.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)

基于属性的元数据过滤 ​

让我们创建另一个包含文档创建年份的元数据的向量存储。

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 表示欧几里得距离，cos 表示余弦相似度

db.similarity_search(
    "What did the president say about Ketanji Brown Jackson?", distance_metric="l2"
)

Maximal Marginal relevance​

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()

使用云（Activeloop、AWS、GCS 等）或内存中的 Deep Lake 数据集​

默认情况下，Deep Lake 数据集存储在本地。为了将其存储在内存中、Deep Lake 管理数据库或任何对象存储中，您可以在创建向量存储时提供相应的路径和凭据。一些路径需要在 Activeloop 处注册并创建一个 API 令牌，该令牌可以在这里获取

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)

此外，在similarity_search方法中也支持查询的执行，用户可以通过Deep Lake的Tensor Query Language (TQL) 来指定查询。

search_id = db.dataset["ids"][0]
docs = db.similarity_search(
    query=None,
    tql=f"SELECT * WHERE ids == '{search_id}'",
)
db.dataset.summary()

创建向量存储在AWS S3​

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
    },
)

深湖 API​

您可以访问Deep Lake数据集，请参阅db.vectorstore

# get structure of the dataset
db.dataset.summary()
# get embeddings numpy array
embeds = db.dataset["embeddings"][:]

将本地数据集传输到云端​

将已创建的数据集复制到云端。您也可以从云端传输到本地。

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)