Accuracy with Database Logging

Before running the code, provide a PostgreSQL database named ai on localhost:5432 with username and password ai, matching the example URL. For a local disposable database, run:

docker run --name agno-eval-db -e POSTGRES_DB=ai -e POSTGRES_USER=ai -e POSTGRES_PASSWORD=ai -p 5432:5432 -d postgres:18

Wait for the database to accept connections. If you already have PostgreSQL, adjust the example’s db_url to match it. Reuse the same local container across examples; do not run this creation command again with the same name.

Create a Python file

accuracy_db_logging.py

"""Example showing how to store evaluation results in the database."""

from typing import Optional

from agno.agent import Agent
from agno.db.postgres.postgres import PostgresDb
from agno.eval.accuracy import AccuracyEval, AccuracyResult
from agno.models.openai import OpenAIResponses
from agno.tools.calculator import CalculatorTools

# Setup the database
db_url = "postgresql+psycopg://ai:ai@localhost:5432/ai"
db = PostgresDb(db_url=db_url, eval_table="eval_runs_cookbook")


evaluation = AccuracyEval(
    db=db,  # Pass the database to the evaluation. Results will be stored in the database.
    name="Calculator Evaluation",
    model=OpenAIResponses(id="gpt-5.2"),
    agent=Agent(
        model=OpenAIResponses(id="gpt-5.2"),
        tools=[CalculatorTools()],
    ),
    input="What is 10*5 then to the power of 2? do it step by step",
    expected_output="2500",
    additional_guidelines="Agent output should include the steps and the final answer.",
    num_iterations=1,
)

result: Optional[AccuracyResult] = evaluation.run(print_results=True)
assert result is not None and result.avg_score >= 8

Set up your virtual environment

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

Install dependencies

uv pip install -U openai agno sqlalchemy psycopg

Export your OpenAI API key

  export OPENAI_API_KEY="your_openai_api_key_here"

Run Agent

python accuracy_db_logging.py