mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
alliscode
45527eed29
Merged and refactored eval module per Eduard's PR review: - Merge _eval.py + _local_eval.py into single _evaluation.py - Convert EvalItem from dataclass to regular class - Rename to_dict() to to_eval_data() - Convert _AgentEvalData to TypedDict - Simplify check system: unified async pattern with isawaitable - Parallelize checks and evaluators with asyncio.gather - Add all/any mode to tool_called_check - Fix bool(passed) truthy bug in _coerce_result - Remove deprecated function_evaluator/async_function_evaluator aliases - Remove _MinimalAgent, tighten evaluate_agent signature - Set self.name in __init__ (LocalEvaluator, FoundryEvals) - Limit FoundryEvals to AsyncOpenAI only - Type project_client as AIProjectClient - Remove NotImplementedError continuous eval code - Add evaluation samples in 02-agents/ and 03-workflows/ - Update all imports and tests (167 passing) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
65 lines
1.7 KiB
Python
65 lines
1.7 KiB
Python
# Copyright (c) Microsoft. All rights reserved.
|
|
|
|
"""Evaluate an agent with expected outputs and tool call checks.
|
|
|
|
Demonstrates ground-truth comparison and tool usage evaluation:
|
|
1. Provide expected outputs alongside queries
|
|
2. Use built-in tool_calls_present for tool verification
|
|
3. Combine multiple evaluation criteria
|
|
|
|
Usage:
|
|
uv run python samples/02-agents/evaluation/evaluate_with_expected.py
|
|
"""
|
|
|
|
import asyncio
|
|
|
|
from agent_framework import (
|
|
Agent,
|
|
LocalEvaluator,
|
|
evaluate_agent,
|
|
evaluator,
|
|
tool_calls_present,
|
|
)
|
|
|
|
|
|
@evaluator
|
|
def response_matches_expected(response: str, expected_output: str) -> float:
|
|
"""Score based on word overlap with expected output."""
|
|
if not expected_output:
|
|
return 1.0
|
|
response_words = set(response.lower().split())
|
|
expected_words = set(expected_output.lower().split())
|
|
return len(response_words & expected_words) / max(len(expected_words), 1)
|
|
|
|
|
|
async def main():
|
|
agent = Agent(
|
|
model="gpt-4o-mini",
|
|
instructions="You are a math tutor. Answer concisely.",
|
|
)
|
|
|
|
local = LocalEvaluator(
|
|
response_matches_expected,
|
|
tool_calls_present, # verifies expected tools were called
|
|
)
|
|
|
|
results = await evaluate_agent(
|
|
agent=agent,
|
|
queries=["What is 2 + 2?", "What is the square root of 144?"],
|
|
expected_output=["4", "12"],
|
|
expected_tool_calls=[
|
|
[], # no tools expected for simple math
|
|
[],
|
|
],
|
|
evaluators=local,
|
|
)
|
|
|
|
for r in results:
|
|
print(f"{r.provider}: {r.passed}/{r.total} passed")
|
|
for item in r.items:
|
|
print(f" [{item.status}] {item.input_text} → {item.output_text[:80]}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|