​
Code

cookbook/models/ibm/watsonx/storage.py
from agno.agent import Agent
from agno.models.ibm import WatsonX
from agno.storage.agent.postgres import PostgresAgentStorage
from agno.tools.duckduckgo import DuckDuckGoTools

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

agent = Agent(
    model=WatsonX(id="ibm/granite-20b-code-instruct"),
    storage=PostgresAgentStorage(table_name="agent_sessions", db_url=db_url),
    tools=[DuckDuckGoTools()],
    add_history_to_messages=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")

​
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 sqlalchemy psycopg duckduckgo-search agno
4

Set up PostgreSQL

Make sure you have a PostgreSQL database running. You can adjust the db_url in the code to match your database configuration.

5

Run Agent

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

This example shows how to use PostgreSQL storage with IBM WatsonX to maintain conversation state across multiple interactions. It creates an agent with a PostgreSQL storage backend and sends multiple messages, with the conversation history being preserved between them.

Note: You need to install the sqlalchemy package and have a PostgreSQL database available.

Agent with Structured OutputRAG Agent