Accuracy Evaluation with Database Logging

"""
Accuracy Evaluation with Database Logging
=========================================

Demonstrates storing accuracy evaluation results in PostgreSQL.
"""

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 OpenAIChat
from agno.tools.calculator import CalculatorTools

# ---------------------------------------------------------------------------
# Create Database
# ---------------------------------------------------------------------------
db_url = "postgresql+psycopg://ai:ai@localhost:5432/ai"
db = PostgresDb(db_url=db_url, eval_table="eval_runs_cookbook")

# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
evaluation = AccuracyEval(
    db=db,
    name="Calculator Evaluation",
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-4o"),
        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,
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    result: Optional[AccuracyResult] = evaluation.run(print_results=True)
    assert result is not None and result.avg_score >= 8