Overview 

Before configuring the extension in the Service Desk application, you need to define the knowledge sources for the AI chatbot, configure the look and feel of the chat, adjust the position of the chat on the screen and the chatbot name, and adjust how the user names and live agent names will be shown in the chat. All this is done through the Conversational AI administration portal.

For recommendations on how to write or improve source materials for Retrieval-Augmented Generation (RAG) AI systems, refer to Knowledge Discovery: Best practices for knowledge sources.

Further configuration implies that Conversational AI (CAI) and AiCore components for Knowledge Discovery for End Users are up and running. For more details, see Conversational AI (CAI) and AiCore Installation and Configuration. For more details about the Conversational AI administration portal, see the Efecte Chat for Service Management guide.

Knowledge Sources Configuration 

The processed data sources are specified in the Conversational AI administrator portal → Projects → AI Chatbot → Knowledge sources:

For more details about the portal configuration, visit How to set up your Chatbot page.

Adding sources 

Add and Test a Demo RAG Source

After configuring the Pass Through connection and API key, add a Demo Source to verify that the AICore RAG/KD4EU pipeline is working correctly.

The Demo Source provides built-in sample content and does not require an external URL, credentials, or uploaded files.

Prerequisites

Before configuring the Demo Source, make sure that:

• An LLM backend is configured;
• Pass-through requests are working;
• A chat model is available;
• An embedding model is configured.

Enable RAG

In the AICore portal, navigate to:

CONFIG → RAG Chat Settings

Configure the following settings:

• Enable RAG: enabled;
• Multiple Databases: disabled for the initial setup;
• Auto Refresh: disabled for the initial test;
• Backend: select the configured LLM backend;
• Model: select a chat model;
• System Template: keep the default value.

The following values can be used for an initial test:

Click Save to apply the configuration.

These settings activate RAG and define the chat model used to generate answers based on retrieved document content.

Configure Embeddings

In the AICore portal, navigate to:

CONFIG → EMBEDDINGS

Configure the following settings:

• Embeddings: enabled;
• Backend: select the configured provider or backend;
• Model: select an embedding-capable model, for example text-embedding-3-small;
• Vector Size: enter the vector dimension supported by the selected embedding model;
• Indexing Threads: keep the default value of 4 for the initial test.

Click Save to apply the configuration.

Incorrect embedding configuration can result in the following issues:

• reindexing fails;
• no documents are returned by search;
• RAG Chat generates an answer without using indexed documents.

Add the Demo Source

In the AICore portal, navigate to:

RAG INDEX → Sources Configuration

Click Add New Source, and then select Demo Source.

Configure the following fields:

• Source Name: enter a descriptive name, for example animal-facts;
• Category Name Source: keep the default value source-name.

Alternatively, select custom and enter a custom category name.

Click Save.

The Demo Source creates built-in sample content about ten animals. No additional connection details or authentication credentials are required.

Index the Demo Source

In the AICore portal, navigate to:

RAG INDEX → Reindex

Click Start Reindexing and wait until the indexing process is completed.

A successful indexing run for the Demo Source should create ten documents.

The indexing result can be verified in the following areas:

• RAG INDEX → Sources Summary;
• RAG INDEX → Search.

Verify the Indexed Documents

In the AICore portal, navigate to:

RAG INDEX → Search

Search for a term included in the Demo Source, for example:

• cheetah;
• penguin;
• platypus.

The search results should contain indexed chunks from the configured Demo Source.

If the search returns results, document indexing and retrieval are working correctly.

If no results are returned:

1. Check whether the reindexing process completed successfully.
2. Verify the embedding backend, model, and vector size.
3. Check the document count in RAG INDEX → Sources Summary.
4. Check Failed Documents, if available, for indexing errors.

Test RAG Chat

In the AICore portal, navigate to:

Chat & Test → RAG

Enter a question related to the Demo Source, for example:

• What is the fastest land animal?
• Tell me about penguins.
• What makes the platypus unique?

The generated answer should be based on the indexed Demo Source content.

The RAG Chat page also displays the API endpoint used for RAG requests:

/rag/v1/chat/completions

For more details on various knowledge sources configuration, see:

• M42 Intelligence: AI Knowledge Discovery
• Data Sources section in the AI Core portal Docs.

Connecting portals 

To process the data from the specified knowledge sources, the AICore should be connected to Conversational AI administrator portal by adjusting the settings in Integrations → Gen AI.

Agent Console Users

The Agent Console URL is a portal where the Agents can browse active chats and chat history. The data from this portal is shown in the Agent Console of the Service Desk → Notifications area. To access the Agent Console, additional credentials are required.

Agent Console users are managed in the Conversational AI administrator portal:

1. In the Conversational AI administrator portal, open Users → Users list
2. Use + Create an agent action
3. Fill out the Name and E-mail address of the new agent user. One Agent user can be created per e-mail address.

The login credentials are sent to the specified email.

The name of the user specified in the Conversational AI portal will be shown as an Agent name in the live chat:

For more details, see also Chat User Management.

Adjusting Look & Feel

Showing the user name in live chat 

By default, the chat Agents do not see the name of the person they are chatting with. Each new conversation is entitled by a generated and automatically assigned user number:

The Agent can see the End User name in the live chat when the M42 Enterprise authentication is enabled:

To enable the M42 Enterprise authentication, apply the following configuration:

1. In the Conversational AI administrator portal, open Projects → AI Chatbot → Advanced → M42 Enterprise authentication
2. Select the Enable authentication checkbox
3. In Authentication URL, adjust the following URL by changing the placeholder to your Matrix42 Enterprise instance:
   https://{my_Martix42Enterprise_URL}/m42Services/api/userinfo

The configuration for https://m42.imagoverum.com/m42Services/api/userinfo might look as follows:

Styling the chat for the Self Service Portal 

To make the chat widget blend more naturally with the New Look of the Matrix42 Self Service Portal, you can adjust its appearance through the Conversational AI administrator portal → Projects → AI Chatbot → Look and CSS Settings sections. Change the default values in these sections to the values from the ESM, which can be found via the following paths:

• Theme: in the ESM Administration application → User Interface → Theme → Select default for New Look Theme and click Edit → all colors are listed here. See also Themes.
• CSS var could be found in the following way: in the ESM, open DEV-tools on UUX page in Web-browser (right button click on the page → Inspect) → Select the very first root <html> element in Elements-tab → Find in Styles-tab the full list of CSS variables.

Look

In the Look configuration, adjust the Base Color and Font name as follows:

• Base color: could be the same as value in the ESM Administration application → User Interface → Theme → Accent Colors → Primary Color
  
• Font name: Roboto,"Helvetica Neue",sans-serif

  

CSS settings

Adjust the following default values with the custom values from ESM Theme or CSS var:

The configuration below is customized for the default New Look Theme from the ESM Administration application → User Interface → Theme.

Install Extension 

The Matrix42 Enterprise Administrator can install Knowledge Discovery for End Users from the Extension Gallery.

Activate 

After installation, the Knowledge Discovery for End Users should be activated and configured via Service Desk → Settings → Knowledge Discovery for End Users.

In Enabled, select the checkbox to activate the extension and fill out the following fields:

• Conversational AI URL
• Agent Console URL
• Installation ID
• Space ID

To get Conversational AI URL, Installation ID, Space ID:

• Log in to the Conversational AI administrator portal → https://<cai-admin.FQDN. For on-premises installations, the address can be fetched from environmental variables (admin must set it up during installation). For RFS / demo it would be https://cai-admin.efectecloud.com.
• Navigate to Projects → AI Chatbot → Get Code
• Copy highlighted values:

For Agent Console URL:

• Exchange "static" with "rail" in Conversational AI URL, e.g., based on the screenshot above https://cai-static.efectecloud.com → https://cai-rail.efectecloud.com

Click Save & Close to proceed.