Getting Started

Option 1: Install using Maven Dependency

Copy and paste the following Maven Dependency into your Mule application pom file.

<dependency>
  <groupId>cloud.anypoint</groupId>
  <artifactId>mule4-vectors-connector</artifactId>
  <version>0.2.50</version>
  <classifier>mule-plugin</classifier>
</dependency>

Option 2: Install Manually using Maven

System Requirements

Before you start, ensure you have the following prerequisites:

• Java Development Kit (JDK) 8, 11, and 17
• Apache Maven
• MuleSoft Anypoint Studio

Download the MAC Vectors Connector

Clone the MAC Vectors Connector repository from GitHub:

git clone https://github.com/MuleSoft-AI-Chain-Project/mac-vectors.git
cd mac-vectors

Install the Connector with Java 8

mvn clean install -Dmaven.test.skip=true -DskipTests

Installing with Java 11, 17, 21, 22, etc.

Step 1

export MAVEN_OPTS="--add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.util.regex=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.xml/javax.xml.namespace=ALL-UNNAMED"

Step 2

 
For Java 11
mvn clean install -Dmaven.test.skip=true -DskipTests -Djdeps.multiRelease=11
 
For Java 17
mvn clean install -Dmaven.test.skip=true -DskipTests -Djdeps.multiRelease=17
 
For Java 21
mvn clean install -Dmaven.test.skip=true -DskipTests -Djdeps.multiRelease=21
 
For Java 22
mvn clean install -Dmaven.test.skip=true -DskipTests -Djdeps.multiRelease=22

Add the Connector to Your Project

Add the following dependency to your pom.xml file:

 
<dependency>
    <groupId>com.mulesoft.connectors</groupId>
    <artifactId>mule4-vectors-connector</artifactId>
    <version>{version}</version>
    <classifier>mule-plugin</classifier>
</dependency>

Configuration

Go to the Global Elements in your MuleSoft project, and create a new configuration. In the Connector Configuration, you will find the MuleSoft Vectors Connector Configuration. Select it and press OK.

In the connector configuration you will be required to configure the Embedding Model Service and Vector Store, while the Storage configuration is optional (you can define/override it at operation level).

Here an example of fully configured connector.

Embedding Model Service Configuration

You can choose one of the available Embedding Model Service.

Based on the selection you will be presented with the related required parameters.

Vector Store Configuration

You can choose one of the available Vector Store.

Based on the selection you will be presented with the related required parameters.

Storage Configuration

This configuration is optional and you can decide to define it or override it at operation level. You can choose one of the available Storage options.

Based on the selection you will be presented with the related required parameters.

Expression (Dataweave)

Is it possible to define the storage configuration using a dataweave expression following some examples.

Local

output application/java
---
{
    workingDirectory: ""
} as Object {
    class : "org.mule.extension.vectors.internal.storage.local.LocalStorageConfiguration"
}

AWS S3

output application/java
---
{
    awsRegion: p('s3.awsDefaultRegion'),
    awsAccessKeyId: p('s3.awsAccessKeyId'),
    awsSecretAccessKey: p('s3.awsDefaultRegion')
} as Object {
    class : "org.mule.extension.vectors.internal.storage.s3.AWSS3StorageConfiguration"
}

Azure Blob

output application/java
---
{
    azureName: p('azureBlob.accountName'),
    azureKey: p('azureBlob.accountKey')
} as Object {
    class : "org.mule.extension.vectors.internal.storage.azureblob.AzureBlobStorageConfiguration"
}