Home
Configuring
Use this information to configure your network, users, servers (including Web servers), directory services, security, messaging, widgets and live text, and server clusters.
Configuring users and servers
Topics in this section describe how to set up users and servers.
Domino IQ
Domino 14.5 adds support for running an AI inference engine in the Domino backend.
RAG for the Domino IQ server
Retrieval-augmented generation (RAG) is a technique for enhancing the accuracy and reliability of generative AI models with information fetched from relevant data sources like databases. This technique helps in keeping the response from LLMs more grounded, current and domain-specific.

Configuring
Use this information to configure your network, users, servers (including Web servers), directory services, security, messaging, widgets and live text, and server clusters.
- Configuring a network
  This section presents the planning concepts and setup procedures necessary for a successful HCL Domino® deployment over a network. It provides information on network protocols from a Domino perspective but does not attempt to provide general network information.
- Configuring users and servers
  Topics in this section describe how to set up users and servers.
  - Understanding the Server document
    The Server document is set up when you register a server. It contains many of the settings that define how your server operates.
  - Policies
    Use Domino® policy settings to control how users work with Notes®. A policy is a document that identifies a collection of individual policy settings. Policy settings documents define a set of defaults that apply to the users and groups to which the policy is assigned. You can change policy settings and they will be automatically applied to the assigned users and groups.
  - Domino IQ
    Domino 14.5 adds support for running an AI inference engine in the Domino backend.
    - Installing Domino IQ
      The Domino IQ installation is separate from Domino. It involves downloading a .zip file and unzipping it to the Domino program directory. This feature is available only on Windows and Linux 64-bit Domino servers with hardware NVIDIA GPU cards installed. HCL recommends NVIDIA GPU hardware with compute capability of 8.0 or higher for faster AI inferencing response time.
    - Enabling Domino IQ servers
      Use the Domino Directory to set up one or more Domino IQ servers.
    - Understanding LLM guard models
    - Configuring the Domino IQ database
      Specify settings in the Domino IQ database (dominoiq.nsf).
    - RAG for the Domino IQ server
      Retrieval-augmented generation (RAG) is a technique for enhancing the accuracy and reliability of generative AI models with information fetched from relevant data sources like databases. This technique helps in keeping the response from LLMs more grounded, current and domain-specific.
      - Adding an Embedding Model document
        There are several opensource embedding model documents in GGUF format like mxbai-embed-large, bge-me, nomic-embed-text, and snowflake-arctic-embed that are available to load. Choose an embedding model based on language and size needs.
      - Creating an Embedding and Vector database Configuration
        You can either add a new configuration in dominoiq.nsf or edit an existing configuration document for a given Domino IQ server.
      - Configuring the Command document for RAG
        Use the existing Command document in dominoiq.nsf, described in the topic conf_add_llm_command_document.html, to specify the new RAG fields.
      - Launching Domino IQ tasks for RAG support
        RAG-related processes are started by the DominoIQ task in the Domino server process.
      - Enabling or disabling the RAG vector database
    - Downloading an LLM model manually
      Download pre-trained data models in GGUF format.
    - Configuring the Certstore database for TLS
      Specify TLS communication settings in the Certstore database (certstore.nsf).
    - DominoIQ task status and controls
      Use Domino IQ server task status, along with console/tell commands, to help monitor and Domino IQ.
    - Security considerations for Domino IQ
      When you use Domino IQ to integrate any AI solution, you must test that solution for performance, quality, and security (including for Domino's out of the box IQ features). For better security, your model should support paraphrasing capability, which Domino IQ leverages.
    - Troubleshooting tips
      Here is some helpful information if you encounter a problem with Domino IQ.
  - Defining default settings for Notes® user registration
    Before you register new Notes® users, you can specify default settings that apply to all users. Default settings simplify user registration and ensure user settings consistency. You can define many default settings, such as what mail server users have or what certifier ID to use for user registration. You can also specify a default workstation execution control list (ECL) to protect data from unauthorized workstation access.
  - Using groups
    Groups are lists of users, groups, and servers that have common traits. They are useful for mailing lists and access control lists. Using groups can simplify administration tasks.
  - Replicas
    You can make a database available to users in different locations, on different networks, or in different time zones, by creating replicas of the database.
  - Calendars and scheduling
    The calendar and scheduling features allow users to check the free time of other users, schedule meetings with them, and reserve resources, such as conference rooms and equipment.
  - Editing the notes.ini file
    The Domino and Notes notes.ini files contain the settings required for the server and client to operate correctly. If you modify or add settings in a notes.ini file, do so cautiously and never edit the file directly with a text editor.
  - Configuring directory services
    This section describes how to plan, set up, and use HCL Domino® directory services.
  - Configuring messaging
    This section provides an overview of messaging and describes how to set up mail routing, how to set up and customize mail servers, and how to track mail.
  - Configuring Verse
    HCL Verse provides HCL Notes® users with browser-based access to Notes mail and to Notes calendar and scheduling features. Administrators specify mail policy and security policy settings as well as notes.ini file settings to complete the full implementation of HCL Verse.
  - Configuring Web servers
    This section describes how to set up the HCL Domino® Web server, and the Domino Web Navigator.
  - Setting up a cluster
    Setting up a cluster includes the tasks of creating and verifying that it is working correctly, and then setting up user access, mail, replications, size quotas, directory assistance, roaming, web navigation, and use of a private LAN in the cluster.
  - Configuring Widgets and Live Text
    Widgets and Live Text enables end users to see and act on Live Text in supported documents, including HCL Notes® mail, using XML extensions (widgets) created specifically for their use.
  - Domain Search
    Notes® client and Web users can use Domain Search to search an entire Domino® domain for database documents, files, and attachments that match a search query.

RAG for the Domino IQ server

Retrieval-augmented generation (RAG) is a technique for enhancing the accuracy and reliability of generative AI models with information fetched from relevant data sources like databases. This technique helps in keeping the response from LLMs more grounded, current and domain-specific.

Starting in Domino 14.5.1, RAG support in the Domino IQ server enables a command defined in dominoiq.nsf to use a Domino database as a RAG source database. The specified fields in the RAG source database are converted into embeddings and stored in a local Vector database. When a configured AI command gets invoked on the Domino IQ server from an application via the LLMReq method in LotusScript or Java, the user prompt is semantically searched against the Vector database. The returned matches are retrieved from the RAG source data documents and sent as additional context in the prompt sent to the LLM inference engine.

In Domino 14.5.1, RAG support is available only when the Domino IQ server is configured in Local mode, so the the LLM handling RAG source content is running on the Domino IQ servers configured for RAG.

When configured for RAG, the Domino IQ server launches:

A llama-server instance with an LLM inference model if Domino IQ server is enabled for local mode
A llama-server instance with an embedding model
A llama-server instance with a guard model (optional)
A vector database server

All of these processes are launched by the DominoIQ task in the Domino server process.

A database that will be used as a RAG source in a command document must be replicated to the Domino IQ server or servers for which the command is configured in dominoiq.nsf.

Prerequisite

Make sure that the dominoiq.nsf on the Domino IQ Administration server and all Domino IQ servers in the domain are updated with the dominoiq.ntf shipped with 14.5.1.

Set up RAG

To configure RAG and enable a RAG database for Domino IQ, see the procedures that follow.