DashVector is a fully-managed vectorDB service that supports high-dimension dense and sparse vectors, real-time insertion and filtered search. It is built to scale automatically and can adapt to different application requirements.

This document demonstrates to leverage DashVector within the LangChain ecosystem. In particular, it shows how to install DashVector, and how to use it as a VectorStore plugin in LangChain.It is broken into two parts: installation and setup, and then references to specific DashVector wrappers.

Installation and Setup​

Install the Python SDK:

pip install dashvector

You must have an API key. Here are theinstallation instructions.

Embedding models​

from langchain_community.embeddingsimport DashScopeEmbeddings

See theuse example.

Vector Store​

A DashVector Collection is wrapped as a familiar VectorStore for native usage within LangChain,which allows it to be readily used for various scenarios, such as semantic search or example selection.

You may import the vectorstore by:

from langchain_community.vectorstoresimport DashVector

For a detailed walkthrough of the DashVector wrapper, please refer tothis notebook