Skip to main content
Open In Colab在 GitHub 上打开

Activeloop Deep Lake

Activeloop Deep Lake 作为多模态矢量存储，用于存储嵌入及其元数据，包括文本、json、图像、音频、视频等。它将数据保存在本地、云中或 Activeloop 存储中。它执行混合搜索，包括嵌入及其属性。

此笔记本展示了与Activeloop Deep Lake.而Deep Lake可以存储嵌入，它能够存储任何类型的数据。它是一个无服务器数据湖，具有版本控制、查询引擎和流式数据加载器到深度学习框架。

有关更多信息，请参阅 Deep Lake 文档

建立

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

Activeloop 提供的示例

与 LangChain 集成。

Deep Lake 本地

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：TextLoader

创建本地数据集

在本地创建数据集./my_deeplake/，然后运行相似性搜索。Deeplake+LangChain 集成在后台使用 Deep Lake 数据集，因此dataset和vector store可以互换使用。要在您自己的云或 Deep Lake 存储中创建数据集，请相应地调整路径。

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)

稍后，您可以重新加载数据集，而无需重新计算嵌入向量

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

设置read_only=Truer事件 在不需要更新时意外修改 vector store。这可确保数据保持不变，除非明确表示。通常，最好指定此参数以避免意外更新。

检索问题/解答

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(),
)
API 参考：RetrievalQA | 聊天OpenAI
query = "What did the president say about Ketanji Brown Jackson"
qa.run(query)

元数据中基于属性的筛选

让我们创建另一个向量存储，其中包含元数据以及文档的创建年份。

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}},
)

选择距离功能

距离函数L2对于欧几里得，cos对于余弦相似度

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（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。要将它们存储在内存、Deep Lake 托管数据库或任何对象存储中，您可以在创建矢量存储时提供相应的路径和凭证。某些路径需要向 Activeloop 注册并创建可在此处检索的 API 令牌

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，similarity_search 方法还支持查询的执行，因此可以使用 Deep Lake 的张量查询语言 （TQL） 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()

在 AWS S3 上创建矢量存储

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
    },
)

深湖 API

您可以通过以下网址访问 Deep Lake 数据集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中。您还可以从云传输到本地。

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)