Initialize and configure the AI Content Assistant via Properties files

This guide walks you through the process of setting up and configuring the BrXM AI Content Assistant using your project’s properties files.

Installation

The following dependencies need to be added to your project's cms-dependencies pom file:

<dependency>
    <groupId>com.bloomreach.xm.ai</groupId>
    <artifactId>content-ai-service-impl-incubating</artifactId>
</dependency>

<dependency>
    <groupId>com.bloomreach.xm.ai</groupId>
    <artifactId>content-ai-service-rest-incubating</artifactId>
</dependency>

<dependency>
    <groupId>com.bloomreach.xm.ai</groupId>
    <artifactId>content-ai-service-client-bootstrap</artifactId>
</dependency>

<dependency>
    <groupId>com.bloomreach.xm.ai</groupId>
    <artifactId>content-ai-service-client-assistant-angular</artifactId>
</dependency>

Configure via properties files

To configure the Content Assistant in a production ready way, use properties files in any of the locations listed below. The order of this list is important: we look for properties files in all these locations but if a property is found in more than one files, the property from the location higher in this list takes precedence.

1. System properties passed on the command line

2. A properties file named xm-ai-service.properties, visible in the classpath

3. The project's platform.properties file

Multiplicity of configurations

Configuring via properties allows configuring multiple different model providers and vector stores, with only one however being active. 

Global Configuration options

The brxm.ai.provider property is used to specify the name of the active model provider. Possible values are:

• OpenAI 
• VertexAIGemini
• Ollama
• LiteLLM

The brxm.ai.chat.max-messages property is used to set the maximum number of messages allowed in a single conversation. An integer number is expected. If not specified, the default value is 100.

The brxm.ai.chat.pdf.max-size-bytes can be used to specify the maximum number, in bytes, over which a pdf will not be allowed to be added as a reference to a conversation. An integer number is expected. If not specified, it defaults to 1MB (1048576 bytes).

Model Provider options

Next you need to provide required configuration parameters for your specific provider. Given below are the names of each model provider, and the lists of required and optional properties for each.

OpenAI

VertexAIGemini

Ollama

LiteLLM

Vector Store and Ingestion options

Please see Initialize and configure the Vector Store and Ingestion.

Maintenance Scripts

The AI module installs tooling for maintenance of your Vector Store, in the form of Groovy scripts. See more details in Maintenance Groovy Scripts.