Skip to main content

深湖 (Deep Lake)

This page covers how to use the Deep Lake ecosystem within LangChain. (本页介绍如何在LangChain中使用深湖生态系统。)

Why Deep Lake? (为什么选择深湖？)​

  • More than just a (multi-modal) vector store. You can later use the dataset to fine-tune your own LLM models. (不仅仅是一个（多模态）向量存储库。您还可以使用数据集来微调自己的LLM模型。)
  • Not only stores embeddings, but also the original data with automatic version control. (不仅存储嵌入向量，还具有自动版本控制的原始数据。)
  • Truly serverless. Doesn't require another service and can be used with major cloud providers (AWS S3, GCS, etc.) (真正的无服务器。不需要其他服务，可以与主要的云提供商（AWS S3、GCS等）一起使用。)

More Resources (更多资源)​

  1. Ultimate Guide to LangChain & Deep Lake: Build ChatGPT to Answer Questions on Your Financial Data (LangChain和Deep Lake的终极指南：构建ChatGPT以回答有关您的财务数据的问题)
  2. Twitter the-algorithm codebase analysis with Deep Lake (使用Deep Lake进行Twitter the-algorithm代码库分析)
  3. Here is whitepaper and academic paper for Deep Lake (这是Deep Lake的白皮书和学术论文)
  4. Here is a set of additional resources available for review: Deep Lake, Get started and Tutorials (这是一套可供查阅的其他资源：Deep Lake、入门指南和Tutorials)

Installation and Setup (安装和设置)​

  • Install the Python package with pip install deeplake (使用pip install deeplake安装Python包)

Wrappers (包装器)​

VectorStore (向量存储库)​

There exists a wrapper around Deep Lake, a data lake for Deep Learning applications, allowing you to use it as a vector store (for now), whether for semantic search or example selection. (存在一个围绕Deep Lake的包装器，它是一个用于深度学习应用的数据湖，允许您将其用作向量存储库（目前），无论是用于语义搜索还是示例选择。)

To import this vectorstore: (要导入此向量存储库:)

from langchain.vectorstores import DeepLake

For a more detailed walkthrough of the Deep Lake wrapper, see this notebook (有关Deep Lake包装器的更详细说明，请参阅此笔记本)