Agent with Storage

Store WatsonX agent sessions and history in Postgres.

Code

db.py

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.ibm import WatsonX
from agno.tools.websearch import WebSearchTools

# Setup the database
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url)

agent = Agent(
    model=WatsonX(id="mistralai/mistral-small-3-1-24b-instruct-2503"),
    db=db,
    tools=[WebSearchTools()],
    add_history_to_context=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")

Usage

1. Set up your virtual environment

   Mac

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

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Set your API key

   export IBM_WATSONX_API_KEY=xxx
   export IBM_WATSONX_PROJECT_ID=xxx
   
3. Install dependencies

   uv pip install -U ddgs psycopg sqlalchemy ibm-watsonx-ai agno
   
4. Run PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run Agent

   Save the code above as db.py, then run:

   python db.py
   

PostgreSQL storage maintains conversation state across multiple interactions. The example creates an IBM WatsonX agent with a PostgreSQL storage backend and sends multiple messages, preserving the conversation history between them.