Agent with Storage

Code

1from kern.agent import Agent
2from kern.db.postgres import PostgresDb
3from kern.models.ibm import WatsonX
4from kern.tools.hackernews import HackerNewsTools
5
6# Setup the database
7db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
8db = PostgresDb(db_url=db_url)
9
10agent = Agent(
11    model=WatsonX(id="mistralai/mistral-small-3-1-24b-instruct-2503"),
12    db=db,
13    tools=[HackerNewsTools()],
14    add_history_to_context=True,
15)
16agent.print_response("How many people live in Canada?")
17agent.print_response("What is their national anthem called?")

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export IBM_WATSONX_API_KEY=xxx
2export IBM_WATSONX_PROJECT_ID=xxx

Install dependencies

1uv pip install -U psycopg sqlalchemy ibm-watsonx-ai kern-ai

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

1python cookbook/11_models/ibm/watsonx/db.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.