Agent with Storage

Code

1from kern.agent import Agent
2from kern.models.aws import AwsBedrock
3from kern.db.postgres import PostgresDb
4from kern.tools.hackernews import HackerNewsTools
5
6db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
7
8agent = Agent(
9    model=AwsBedrock(id="mistral.mistral-large-2402-v1:0"),
10    db=PostgresDb(session_table="agent_sessions", db_url=db_url),
11    tools=[HackerNewsTools()],
12    add_history_to_context=True,
13)
14agent.print_response("How many people live in Canada?")
15agent.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 AWS Credentials

1export AWS_ACCESS_KEY_ID=***
2export AWS_SECRET_ACCESS_KEY=***
3export AWS_REGION=***

Install dependencies

1uv pip install -U boto3 sqlalchemy psycopg kern-ai

Run PgVector

1docker run -d \
2  -e POSTGRES_DB=ai \
3  -e POSTGRES_USER=ai \
4  -e POSTGRES_PASSWORD=ai \
5  -e PGDATA=/var/lib/postgresql/data/pgdata \
6  -v pgvolume:/var/lib/postgresql/data \
7  -p 5532:5432 \
8  --name pgvector \
9  agnohq/pgvector:16

Run Agent

1python storage.py