Agent with Storage
Persist an LMStudio agent's chat history to PostgreSQL and give it web search tools with add_history_to_context enabled.
Code
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.lmstudio import LMStudio
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=LMStudio(id="qwen2.5-7b-instruct-1m"),
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?")Load a model that supports tool calling in LM Studio.
Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateStart the LM Studio API server
Install LM Studio, download and load a model, then open Developer and start the API server on port 1234. Keep the server running while you run Python in a terminal.
Check the model list:
curl http://127.0.0.1:1234/v1/modelsSet LMStudio(id=...) in the example to the exact model id returned by your server. If you change the server port, set the matching base_url on LMStudio.
Install dependencies
uv pip install -U ddgs sqlalchemy "psycopg[binary]" openai agnoRun PgVector
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:18Run Agent
Save the code above as db.py, then run:
python db.py