​
Code

cookbook/models/ibm/watsonx/basic.py
from agno.agent import Agent, RunResponse
from agno.models.ibm import WatsonX

agent = Agent(model=WatsonX(id="ibm/granite-20b-code-instruct"), markdown=True)

# Get the response in a variable
# run: RunResponse = agent.run("Share a 2 sentence horror story")
# print(run.content)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story")

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.

python3 -m venv .venv
source .venv/bin/activate
2

Set your API key

export IBM_WATSONX_API_KEY=xxx
export IBM_WATSONX_PROJECT_ID=xxx
3

Install libraries

pip install -U ibm-watsonx-ai agno
4

Run Agent

python cookbook/models/ibm/watsonx/basic.py

This example creates an agent using the IBM WatsonX model and prints a response directly to the terminal. The markdown=True parameter tells the agent to format the output as markdown, which can be useful for displaying rich text content.

Agent with ToolsStreaming Basic Agent