Agent with Storage

Code

cookbook/models/ibm/watsonx/storage.py

from agno.agent import Agent
from agno.models.ibm import WatsonX
from agno.storage.postgres import PostgresStorage
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=PostgresStorage(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

Create a virtual environment

Open the Terminal and create a python virtual environment.

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

python3 -m venv .venv
.venv/scripts/activate

Set your API key

export IBM_WATSONX_API_KEY=xxx
export IBM_WATSONX_PROJECT_ID=xxx

Install libraries

pip install -U ibm-watsonx-ai sqlalchemy psycopg duckduckgo-search agno

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.

Run Agent

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

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 Output RAG Agent

Examples

Agent Concepts

Models

Agent with Storage

Code

Usage

​Code

​Usage

Code

Usage