Accuracy Evaluation with Graph

import asyncio
from upsonic import Agent, Task, Graph
from upsonic.eval import AccuracyEvaluator

agent = Agent(
    model="anthropic/claude-sonnet-4-5",
    name="GraphAgent",
)

graph = Graph(
    default_agent=agent,
    show_progress=False,
)

task = Task(description="What is the capital of Italy?")
graph.add(task)

judge = Agent(model="anthropic/claude-sonnet-4-5", name="Judge")

evaluator = AccuracyEvaluator(
    judge_agent=judge,
    agent_under_test=graph,
    query="What is the capital of Italy?",
    expected_output="Rome is the capital of Italy.",
    additional_guidelines="Check if the answer correctly identifies Rome.",
    num_iterations=1,
)

result = asyncio.run(evaluator.run(print_results=True))

print(f"Score: {result.average_score}/10")
print(f"Output: {result.generated_output}")

import asyncio
from upsonic import Agent, Task, Graph
from upsonic.eval import AccuracyEvaluator

agent = Agent(
    model="anthropic/claude-sonnet-4-5",
    name="ChainAgent",
)

graph = Graph(
    default_agent=agent,
    show_progress=False,
)

task1 = Task(description="Name a popular programming language.")
task2 = Task(description="Describe one key feature of that programming language.")
graph.add(task1 >> task2)

judge = Agent(model="anthropic/claude-sonnet-4-5", name="Judge")

evaluator = AccuracyEvaluator(
    judge_agent=judge,
    agent_under_test=graph,
    query="Name a popular programming language and describe one key feature.",
    expected_output="Python is a popular language known for its readable syntax.",
    additional_guidelines="Accept any valid programming language with a correct key feature.",
    num_iterations=1,
)

result = asyncio.run(evaluator.run(print_results=True))

print(f"Score: {result.average_score}/10")