Milvus
Last updated
Last updated
This guide walks you through configuring a Retrieval-Augmented Generation (RAG) pipeline in Vectorize using Milvus as the vector database.
These instructions are the same if you're using Zilliz Cloud.
Ensure you have:
A Vectorize account (Create one free here ↗ )
A Milvus cluster
To configure a vector database integration to connect to your Milvus instance:
Click Vector Databases from the main menu.
Click New Vector Database Integration from the Vector Databases page.
Select the Milvus card.
Enter the parameters in the form using the Milvus Parameters table below as a guide, then click Create Milvus Integration.
Name
A descriptive name to identify the integration within Vectorize.
Yes
Public Endpoint
The public endpoint for your cluster.
Yes
Token
The cluster's token.
Yes, unless you provide a username/password
Username
The cluster's username.
Yes, unless you provide a token
Password
The cluster's password.
Yes, unless you provide a token
When you specify your Milvus integration in your pipeline configuration, Vectorize writes vector data to your Milvus instance.
You can think of the Milvus integration as having two parts to it. The first is authorization with your Milvus cluster. This part is re-usable across pipelines and allows you to connect to this same application in different pipelines without providing the credentials every time.
The second part is the configuration that's specific to your RAG Pipeline. This is where you specify the name of the collection in your Milvus cluster. If the collection does not already exist, Vectorize will create it for you.
If you haven't yet built a connector to your source database, go to configure a source connector and select your source data platform.
OR
If you're ready to start creating pipelines for vectorizing data, head to Pipeline Basics.
