Agent with Storage

Code

cookbook/models/lmstudio/storage.py

from agno.agent import Agent
from agno.models.lmstudio import LMStudio
from agno.storage.postgres import PostgresStorage
from agno.tools.duckduckgo import DuckDuckGoTools

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

agent = Agent(
    model=LMStudio(id="qwen2.5-7b-instruct-1m"),
    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

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

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

2. Install LM Studio

   Install LM Studio from here and download the model you want to use.

3. Install libraries

   pip install -U sqlalchemy psycopg duckduckgo-search agno
   

4. Run PgVector

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql/data/pgdata \
     -v pgvolume:/var/lib/postgresql/data \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:16
   

5. Run Agent

   Mac

   python cookbook/models/lmstudio/storage.py
   

Assistant

Responses are generated using AI and may contain mistakes.