Import the agents you create in your active environment. You can import agents in two different ways: by importing an agent configuration file or by creating the agent directly using the ADK CLI command.

​
Importing agents using a agent file

The orchestrate agents import command allows you to import agents into the watsonx Orchestrate platform using a YAML, JSON, or Python file.

To specify the path for the agent file, use the --file or -f flag:

[BASH]
orchestrate agents import -f <path to .yaml/.json/.py file>

To use this command, you must have a file with the agent configuration. These configurations are parameters that describe the agent for watsonx Orchestrate. For more information about these agent parameters, see Creating Agents.

​
Importing Agents direct in the CLI

The orchestrate agents create command can be used to quickly create and import an agent into the watsonx Orchestrate platform without first having a file to import.

Native Agent

Flags:

ArgumentDescription
--name / -nThe name of the agent you want to create.
--kind / -kThe kind of agent you wish to create. For native agents, the value should be native.
--descriptionThe description of the agent.
--llmThe large language model the agent will use, in the format of provider/developer/model_id, for example watsonx/ibm/granite-3-8b-instruct, or watsonx/meta-llama/llama-3-3-70b-instruct, where watsonx/ refers to the models supported by watsonx Orchestrate.
--styleThe style of agent you want to create. Either default or react.
--collaboratorsA list of agents that the agent should be able to call out to. Multiple collaborators can be specified (e.g., --collaborators agent_1 --collaborators agent_2).
--toolsA list of tools that the agent should be able to use. Multiple tools can be specified (e.g., --tools tool_1 --tools tool_2).
--outputAllows you to specify an output file to write the agent definition to (either .yaml or .json are supported) for future modification post import.
[BASH]
orchestrate agents create \
--name agent_name \
--kind native \
--description "Sample agent description" \
--llm watsonx/ibm/granite-3-8b-instruct \
--style default \
--collaborators agent_1
--collaborators agent_2
--tools tool_1
--output "agent_name.agent.yaml

External Agent

Allows you to call out to an external agent that is hosted on a different platform, such as Salesforce. For more information, see External Agent.

Flags:

ArgumentDescription
--name / -nThe name of the agent you want to create.
--kind / -kThe kind of agent you wish to create. For external agents, the value should be external.
--title / -tThe title of the agent you wish to create.
--descriptionThe description of the agent.
--api / -aThe external API URL your agent use.
--tagsThe list of tags for the agent. Format: --tags tag1 --tags tag2 .... Only needed for external and assistant agents.
--chat-paramsThe chat parameters in JSON format (e.g., {"stream": true}). Only needed for external and assistant agents.
--configThe agent configuration in JSON format (e.g., {"hidden": false, "enable_cot": false}).
--nicknameThe agent’s nickname.
--app-idThe application connection name used by the agent.
--outputAllows you to specify an output file to write the agent definition to (either .yaml or .json are supported) for future modification post import.
[BASH]
orchestrate agents create \
--name news_agent \
--title "News Agent" \
--description "Sample agent description" \
--api "http://some_url.com" \
--kind external \
--tags "test,other" \
--chat-params '{"stream": true}' \
--config '{"hidden": false, "enable_cot": false}' \
--nickname "news_agent" \
--app-id "my-basic-app"

WX.AI External Agent

To call out to agents on the WX.AI platform, set the provider to wx.ai.

Flags:

ArgumentDescription
--name / -nThe name of the agent you want to create.
--kind / -kThe kind of agent you wish to create. For external agents, the value should be external.
--title / -tThe title of the agent you wish to create.
--descriptionThe description of the agent.
--api / -aThe external API URL your agent will use.
--auth-configThe external API auth config in JSON format (e.g., {"token": "sometoken"}).
--auth-schemeThe external API auth scheme (e.g., API_KEY for WX.AI).
--tagsThe list of tags for the agent. Format: --tags tag1 --tags tag2 .... Only needed for external and assistant agents.
--chat-paramsThe chat parameters in JSON format (e.g., {"stream": true}). Only needed for external and assistant agents.
--configThe agent configuration in JSON format (e.g., {"hidden": false, "enable_cot": false}).
`—nicknameThe agent’s nickname.
--app-idThe application connection name used by the agent.
--providerThe external agent provider. It will be wx.ai for WX.AI agents.
--outputAllows you to specify an output file to write the agent definition to (either .yaml or .json are supported) for future modification post import.
[BASH]
orchestrate agents create \
--name science_agent \
--title "Sciene Agent" \
--description "This external agent answers questions about Space" \
--api "http://some_url.com" \
--auth-config '{"token": "sometoken"}' \
--auth-scheme 'API_KEY' \
--kind external \
--tags "wx.ai" \
--chat-params '{"stream": true}' \
--config '{"hidden": false, "enable_cot": false}' \
--nickname "Science Agent" \
--provider "wx.ai"
--output "science_agent.agent.yaml