Skip to main content
A Python toolkit groups one or more Python tools so you can import them into watsonx Orchestrate as a single unit. To create a toolkit, place all related Python tools in one folder. Each Python tool includes one or more Python files. In those files, you define functions and annotate them with the @tool decorator so watsonx Orchestrate exposes each function as a usable tool. For more information about Python tools, see Authoring Python-Based Tools. After you package your tools in a folder, you can add the toolkit to watsonx Orchestrate directly from the ADK CLI or import it from a file.

​
Add Python toolkits using the ADK CLI

Use the orchestrate toolkits add command to add a Python toolkit.
BASH
orchestrate toolkits add \
  --kind python \
  --name <toolkit-name> \
  --description <toolkit-description> \
  --language python \
  --package <python-package-name> \
  --package-root <path-to-package-root> \
  --tools <tools> \
  --tier <deployment-tier>

​
Import Python toolkits from a file

You can also import a Python toolkit from a YAML file. This file defines the same configuration options as the add command and fits well into import scripts and CI/CD pipelines. Use the orchestrate toolkits import command to import a toolkit from a file.
BASH
orchestrate toolkits import -f <path to spec> --app-id <connection>
For the YAML file, configure the following:
​
spec_version
string
required
The version of the YAML specification.
​
kind
string
required
The type of toolkit. For Python toolkits, use python.
​
name
string
required
The name of the toolkit.
​
description
string
The description of the toolkit.
​
package-root
string
The path to the folder that contains the Python tools.
​
environment
object
Key-value pairs for the toolkit.
Example:
toolkit_name.yaml
spec_version: v1
kind: python
name: toolkit_name
description: A toolkit sample
package-root: path_to_folder
environment:
    key1: value1