Getting Started

Use the Connector in Your Project

Application Requirements

Java Development Kit (JDK)

The application using the MuleSoft Vectors Connector can use Java Development Kit (JDK) 8, 11 and 17 with following exceptions:

• OpenSearch vector store only support Java Development Kit (JDK) 11 and 17

MuleSoft Runtime

The application using the MuleSoft Vectors Connector requires a Mule Runtime >= 4.5.3.

Option 1: Maven Central Repository

(opens in a new tab)

<dependency>
    <groupId>io.github.mulesoft-ai-chain-project</groupId>
    <artifactId>mule4-vectors-connector</artifactId>
    <version>{version}</version>
    <classifier>mule-plugin</classifier>
</dependency>

Option 2: Local Maven Repository

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

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

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"

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

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

Connector Additional Dependencies

Mule maven plugin allows to configure additional plugin dependencies for a connector, you can learn more here (opens in a new tab).

In order to add a dependency like the following to your application

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-document-loader-azure-storage-blob</artifactId>
    <version>${langchain4jVersion}</version>
</dependency>
 

you need to modify your pom.xml file as follows.

The change is different depending on how you installed the connector..

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="..." >
 
...
 
  <properties>
  	...
  	<mule.maven.plugin.version>4.3.0</mule.maven.plugin.version>
  	<langchain4jVersion>0.35.0</langchain4jVersion>
  </properties>
 
  <build>
  	<plugins>
  		...
  		<plugin>
  			<groupId>org.mule.tools.maven</groupId>
  			<artifactId>mule-maven-plugin</artifactId>
  			<version>${mule.maven.plugin.version}</version>
  			<extensions>true</extensions>
  			<configuration>
  				<additionalPluginDependencies>
  					<plugin>
  						<groupId>io.github.mulesoft-ai-chain-project</groupId>
  						<artifactId>mule4-vectors-connector</artifactId>
  						<additionalDependencies>
 
  							<!-- OPTIONAL DEPENDENCY GOES HERE -->
  							<dependency>
  								<groupId>dev.langchain4j</groupId>
  								<artifactId>langchain4j-document-loader-azure-storage-blob</artifactId>
  								<version>${langchain4jVersion}</version>
  							</dependency>
  							<!-- OPTIONAL DEPENDENCY GOES HERE -->
 
  						</additionalDependencies>
  					</plugin>
  				</additionalPluginDependencies>
  			</configuration>
  		</plugin>
  	</plugins>
  </build>
...
</project>

You'll find in the following sections the instruction to add the dependencies required by each specific service (eg. Amazon S3, Azure OpenAI, ...).

Storage Services

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-document-loader-amazon-s3</artifactId>
    <version>${langchain4jVersion}</version>
</dependency>

Embedding Model Services

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-azure-open-ai</artifactId>
    <version>${langchain4jVersion}</version>
</dependency>

Vector Stores

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-azure-ai-search</artifactId>
    <version>${langchain4jVersion}</version>
</dependency>

Connector Configurations

The MuleSoft Vectors connector is shipped with 3 different categories of operations: Document, Embedding and Store. For each category a dedicated configuration must be defined.

Document Configuration

The document configuration allows to pick-up the right storage service option among the available ones. When configuring the connection to a specific storage service it's also possible to test it.

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 Document config. Select it and press OK.

Depending on the specific storage service selected you'll be presented with different parameter to setup the connection. Following an example.

Embedding Configuration

The embedding configuration allows to pick-up the right embedding model service option among the available ones. When configuring the connection to a specific embedding model service it's also possible to test it.

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 Embedding config. Select it and press OK.

Depending on the specific embedding model service selected you'll be presented with different parameter to setup the connection. Following an example.

Store Configuration

The store configuration allows to pick-up the right vector store option among the available ones. When configuring the connection to a specific vector store it's also possible to test it.

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 Store config. Select it and press OK.

Depending on the specific vector store selected you'll be presented with different parameter to setup the connection. Following an example.