Installing watsonx Orchestrate

An instance administrator can install watsonx Orchestrate on IBM® Software Hub Version 5.3.

Who needs to complete this task?

Instance administrator To install watsonx Orchestrate, you must be an instance administrator. An instance administrator has permission to install software in the following projects:

The operators project for the instance

The operators for this instance of watsonx Orchestrate are installed in the operators project.

In the installation commands, the ${PROJECT_CPD_INST_OPERATORS} environment variable refers to the operators project.

The operands project for the instance

The custom resources for the control plane and watsonx Orchestrate are installed in the operands project.

In the installation commands, the ${PROJECT_CPD_INST_OPERANDS} environment variable refers to the operands project.

When do you need to complete this task?

Review the following options to determine whether you need to complete this task:

  • If you want to install multiple services at the same time, follow the process in Running a batch installation of solutions and services instead.
  • If you didn't install watsonx Orchestrate as part of a batch installation, complete this task to add watsonx Orchestrate to your environment.

    Repeat as needed If you are responsible for multiple instances of IBM Software Hub, you can repeat this task to install more instances of watsonx Orchestrate on the cluster.

Important: You cannot install watsonx Orchestrate and standalone watsonx Assistant on the same instance of IBM Software Hub. If you want to install these services on the same Red Hat® OpenShift® Container Platform cluster, you must install each service on a different instance of IBM Software Hub. For more information see Multitenancy considerations.

Information you need to complete this task

Review the following information before you install watsonx Orchestrate:

Version requirements

All of the components that are associated with an instance of IBM Software Hub must be installed at the same release. For example, if the IBM Software Hub control plane is installed at Version 5.3.0, you must install watsonx Orchestrate at Version 5.3.0.

Environment variables

The commands in this task use environment variables so that you can run the commands exactly as written.

  • If you don't have the script that defines the environment variables, see Setting up installation environment variables.
  • To use the environment variables from the script, you must source the environment variables before you run the commands in this task. For example, run:
    source ./cpd_vars.sh
Security context constraint

watsonx Orchestrate works with the default Red Hat OpenShift Container Platform security context constraint, restricted-v2.

Storage requirements
You must specify storage classes when you install watsonx Orchestrate. The following storage classes are recommended. However, if you don't use these storage classes on your cluster, ensure that you specify a storage class with an equivalent definition.
Storage Notes Storage classes
OpenShift Data Foundation When you install the service, specify file storage and block storage.
  • File storage: ocs-storagecluster-cephfs
  • Block storage: ocs-storagecluster-ceph-rbd
IBM Fusion Data Foundation When you install the service, specify file storage and block storage.
  • File storage: ocs-storagecluster-cephfs
  • Block storage: ocs-storagecluster-ceph-rbd
IBM Fusion Global Data Platform When you install the service, specify the same storage class for both file storage and block storage.
  • File storage:

    Either of the following storage classes:

    • ibm-spectrum-scale-sc
    • ibm-storage-fusion-cp-sc
  • Block storage:

    Either of the following storage classes:

    • ibm-spectrum-scale-sc
    • ibm-storage-fusion-cp-sc
IBM Storage Scale Container Native Not supported. Not applicable.
Portworx When you install the service, the --storage_vendor=portworx option ensures that the service uses the correct storage classes.
  • File storage: portworx-shared-gp3
  • Block storage: portworx-db-gp3-sc
NFS Not supported. Not applicable.
Amazon Elastic storage Not supported. Not applicable.
NetApp Trident When you install the service, specify the same storage class for both file storage and block storage.
  • File storage: ontap-nas
  • Block storage: ontap-nas
Nutanix Not supported. Not applicable.

Before you begin

This task assumes that the following prerequisites are met:

System requirements
This task assumes that the cluster meets the minimum requirements for watsonx Orchestrate.
Where to find more information
If this task is not complete, see System requirements.
In addition, if you plan to use features that require GPU, ensure that you have the appropriate type and number of GPU for watsonx Orchestrate.
Where to find more information
If this task is not complete, see GPU requirements.
Workstation
This task assumes that the workstation from which you will run the installation is set up as a client workstation and has the following command-line interfaces:
  • IBM Software Hub CLI: cpd-cli
  • OpenShift CLI: oc
  • Helm CLI: helm
Where to find more information
If this task is not complete, see Setting up a client workstation.
Control plane
This task assumes that the IBM Software Hub control plane is installed.
Where to find more information
If this task is not complete, see Installing an instance of IBM Software Hub.
Private container registry
If your environment uses a private container registry (for example, your cluster is air-gapped), this task assumes that the following tasks are complete:
  1. The watsonx Orchestrate software images are mirrored to the private container registry.
    Where to find more information
    If this task is not complete, see Mirroring images to a private container registry.
  2. The cpd-cli is configured to pull the olm-utils-v4 image from the private container registry.
    Where to find more information
    If this task is not complete, see Pulling the olm-utils-v3 image from the private container registry.
Red Hat OpenShift AI
If you plan to use features that require Red Hat OpenShift AI, this task assumes that Red Hat OpenShift AI is installed.
Where to find more information
If this task is not complete, see Installing Red Hat OpenShift AI.
Multicloud Object Gateway
This task assumes that the following tasks are complete:
  1. Multicloud Object Gateway is installed and configured.
    Where to find more information
    If this task is not complete, see Installing Multicloud Object Gateway.
  2. The secrets that enable watsonx Orchestrate to connect to Multicloud Object Gateway exist.
    Where to find more information
    If this task is not complete, see Creating secrets for services that use Multicloud Object Gateway.
Red Hat OpenShift Serverless Knative Eventing
This task assumes that Red Hat OpenShift Serverless Knative Eventing is installed.
Where to find more information
If this task is not complete, see Installing Red Hat OpenShift Serverless Knative Eventing.
Cluster-scoped resources
This task assumes that the cluster-scoped resources, such as custom resource definitions, cluster roles, and cluster role bindings, exist.
Where to find more information
If this task is not complete, see Creating cluster-scoped resources for the IBM Software Hub platform and services.
Image pull secrets
This task assumes that the secrets that contain the image pull credentials for the instance exist.
Where to find more information
If this task is not complete, see Creating image pull secrets for an instance of IBM Software Hub.
Identity Management Service
This task assumes that IBM Software Hub is configured to use the Identity Management Service.
To check whether IBM Software Hub is using the Identity Management Service, run:
oc get zenservice lite-cr \
-n ${PROJECT_CPD_INST_OPERANDS} \
-o jsonpath='{.spec.iamIntegration}'

Procedure

Complete the following tasks to install watsonx Orchestrate:

  1. Specifying installation options
  2. Installing the service
  3. Validating the installation
  4. What to do next

Specifying installation options

If you plan to install watsonx™ Orchestrate configuration, specify the appropriate installation options in a file named install-options.yml in the cpd-cli work directory (For example: cpd-cli-workspace/olm-utils-workspace/work).

The installation options that you specify depend on several factors. The first factor that you must consider is where you want to install the foundation models for watsonx Orchestrate. You can use foundation models on:
The same cluster as watsonx Orchestrate
Choosing a model GPU requirements
You must use one of the models provided by IBM.

The features that you plan to use determine the model or models that you must install.

You must have sufficient GPU on the cluster where you plan to install watsonx Orchestrate.
A remote or external cluster by using AI gateway
Choosing a model GPU requirements
You can choose whether to use:
  • One of the models provided by IBM

    If you use the models provided by IBM, the features that you plan to use determine the models that you must install.

  • A custom model

    If you use a custom model, you must register the external model through AI gateway.

Local GPU is not required.
Remote GPU might be required:
  • If you plan to host models on a remote cluster, you must have sufficient GPU on the cluster where you plan to install the foundation models.

    For more information on GPU requirements, consult the documentation from the model provider.

  • If you plan to use models hosted by a third-party, you don't need GPU.
After you decide where you will install the foundation models, you can decide which features you want to install. You can install:
  • Only the agentic AI features
  • The agentic AI features and Assistant Builder features.
  • The agentic AI features, Assistant Builder features, and legacy features, such as conversational search and conversational skills.
Models provided by IBM

Review the following table to determine which model or models provide the features that you need:

Model
Agentic AI

Domain agents
Agentic AI

Tool and API orchestration
Conversational search

Answer generation
Conversational search

Query rewrite
Conversational skills

Custom actions information gathering
granite-3-8b-instruct No No Yes No No
ibm-granite-8b-unified-api-model-v2 No No No Yes Yes
llama-3-1-70b-instruct No Yes Yes Yes Yes
llama-3-2-90b-vision-instruct Yes Yes Yes Yes Yes
Important: The llama-3-2-90b-vision-instruct model is recommended over the llama-3-1-70b-instruct model. The llama-3-2-90b-vision-instruct model offers:
  • Better performance
  • More accurate results
Private container registry users: You must mirror the images for the models that you plan to use to the private container registry. For more information, see Determining which models to mirror to your private container registry.

Choose the appropriate YAML based on where you plan to install the foundation models:

Install foundation models on the same cluster as watsonx Orchestrate
# ............................................................................
# watsonx Orchestrate parameters
# ............................................................................
  watsonxOrchestrate:
    installMode: "agentic"  
    watsonxAI:
      watsonxaiifm: true
      syomModels: []
      ootbModels: []
Use foundation models on a remote or external cluster by using AI gateway
# ............................................................................
# watsonx Orchestrate parameters
# ............................................................................
  watsonxOrchestrate:
    installMode: "agentic"  
    watsonxAI:
      watsonxaiifm: false
      syomModels: []
      ootbModels: []
Property Description
installMode

Specify the features that you plan to install.

Default value
agentic

If you omit this option, the default value is used.

Valid values
agentic
Install only the agentic AI features.
agentic_assistant
Install the agentic AI features and Assistant Builder features.
agentic_skills_assistant
Install the agentic AI features, Assistant Builder features, and legacy features, such as conversational search and conversational skills.
watsonxaiifm

Specify whether to install Inference foundation models (watsonx_ai_ifm) based on where you plan to install the foundation models.

Default value
false

If you omit this option, the default value is used.

Valid values
false
Do not install Inference foundation models.

Specify this option if you plan to install the foundation models on a remote cluster or use foundation models hosted by a third-party.

After you install watsonx Orchestrate, you must use the AI gateway to connect to the foundation models.

true
Install the Inference foundation models.

Specify this option if you plan to install the foundation models on the cluster the same cluster as watsonx Orchestrate.

Remember: You must have sufficient GPU for the models that you plan to install.
ootbModels

Specify whether to install one or more general models.

This option is valid only if you install the foundation models on the same cluster as watsonx Orchestrate (watsonxaiifm: true).

Install models based on the features that you want to enable.

Default value
[]
Valid values
[]
Do not install a general model.
ibm-slate-30m-english-rtrvr

This model is required.

Install the slate-30m-english-rtrvr model by specifying the model ID:
ootbModels: [ibm-slate-30m-english-rtrvr]
granite-3-8b-instruct
Install the granite-3-8b-instruct model by specifying the model ID:
ootbModels: [granite-3-8b-instruct]
llama-3-1-70b-instruct
Install the llama-3-1-70b-instruct model by specifying the model ID:
ootbModels: [llama-3-1-70b-instruct]
llama-3-2-90b-vision-instruct
Install the llama-3-2-90b-vision-instruct model by specifying the model ID:
ootbModels: [llama-3-2-90b-vision-instruct]
Installing multiple general models
To install multiple general models, specify a comma-separated list of model IDs. For example:
ootbModels: [ibm-slate-30m-english-rtrvr,llama-3-2-90b-vision-instruct]
syomModels

Specify whether to install a specialized model that is specifically tuned for use with watsonx Orchestrate.

This option is valid only if:

  • You install the foundation models on the same cluster as watsonx Orchestrate (watsonxaiifm: true).
  • You install the Assistant Builder (installMode: agentic_assistant) or legacy features (install Mode: agentic_skills_assistant).
Default value
[]
Valid values
[]
Do not install a specialized model.
ibm-granite-8b-unified-api-model-v2
Install the ibm-granite-8b-unified-api-model-v2 model by specifying the model ID:
syomModels: [ibm-granite-8b-unified-api-model-v2]

Installing the service

To install watsonx Orchestrate:

  1. Log the cpd-cli in to the Red Hat OpenShift Container Platform cluster:
    ${CPDM_OC_LOGIN}
    Remember: CPDM_OC_LOGIN is an alias for the cpd-cli manage login-to-ocp command.
  2. Install the operator and custom resource for watsonx Orchestrate.

    The command that you run depends on the storage on your cluster.


    Red Hat OpenShift Data Foundation storage

    Run the appropriate command for your environment:

    Default installation (without installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --block_storage_class=${STG_CLASS_BLOCK} \
    --file_storage_class=${STG_CLASS_FILE} \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET}
    Custom installation (with installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --block_storage_class=${STG_CLASS_BLOCK} \
    --file_storage_class=${STG_CLASS_FILE} \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET}\
    --param-file=/tmp/work/install-options.yml

    IBM Fusion Data Foundation storage

    Run the appropriate command for your environment:

    Default installation (without installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --block_storage_class=${STG_CLASS_BLOCK} \
    --file_storage_class=${STG_CLASS_FILE} \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET}
    Custom installation (with installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --block_storage_class=${STG_CLASS_BLOCK} \
    --file_storage_class=${STG_CLASS_FILE} \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET} \
    --param-file=/tmp/work/install-options.yml

    Portworx storage

    Run the appropriate command for your environment:

    Default installation (without installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --storage_vendor=portworx \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET}
    Custom installation (with installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --storage_vendor=portworx \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET} \
    --param-file=/tmp/work/install-options.yml

    NetApp Trident
    Remember: When you use NetApp Trident storage, both ${STG_CLASS_BLOCK} and ${STG_CLASS_FILE} point to the same storage class, typically ontap-nas.

    Run the appropriate command for your environment:

    Default installation (without installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --block_storage_class=${STG_CLASS_BLOCK} \
    --file_storage_class=${STG_CLASS_FILE} \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET}
    Custom installation (with installation options)
    cpd-cli manage install-components \
    --license_acceptance=true \
    --components=watsonx_orchestrate \
    --release=${VERSION} \
    --operator_ns=${PROJECT_CPD_INST_OPERATORS} \
    --instance_ns=${PROJECT_CPD_INST_OPERANDS} \
    --block_storage_class=${STG_CLASS_BLOCK} \
    --file_storage_class=${STG_CLASS_FILE} \
    --image_pull_prefix=${IMAGE_PULL_PREFIX} \
    --image_pull_secret=${IMAGE_PULL_SECRET} \
    --param-file=/tmp/work/install-options.yml

Validating the installation

watsonx Orchestrate is installed when the install-components command returns:
[SUCCESS]... The install-components command ran successfully

If you want to confirm that the custom resource status is Completed, you can run the cpd-cli manage get-cr-status command:

cpd-cli manage get-cr-status \
--cpd_instance_ns=${PROJECT_CPD_INST_OPERANDS} \
--components=watsonx_orchestrate

What to do next

  1. When you face any issue with watsonx Orchestrate installation, see Troubleshooting issues in watsonx Orchestrate.
  2. Complete the mandatory post-installation setup tasks. For more information, see Post-installation setup for watsonx Orchestrate.
  3. To enable the users to access watsonx Orchestrate, see Giving users access to a watsonx Orchestrate instance.