Penilaian

Dalam .NET, kerangka kerja evaluasi dibangun pada Microsoft. Extensions.AI.Evaluation. Para evaluator mengimplementasikan IAgentEvaluator antarmuka, dan penyelarasan disediakan melalui metode ekstensi pada AIAgent dan Run.

Jenis inti hidup di namespace Microsoft.Agents.AI:

using Microsoft.Agents.AI;

Dalam Python, kerangka kerja evaluasi adalah bagian dari paket inti agent_framework. Para evaluator menerapkan protokol Evaluator, dan orkestrasi disediakan melalui fungsi evaluate_agent() dan evaluate_workflow().

from agent_framework import (
    evaluate_agent,
    evaluate_workflow,
    EvalItem,
    EvalResults,
    LocalEvaluator,
)

Pemeriksaan bawaan

Rangka Kerja Agen dilengkapi dengan pemeriksaan bawaan untuk skenario umum.

using Microsoft.Agents.AI;

var local = new LocalEvaluator(
    EvalChecks.KeywordCheck("weather", "temperature"),  // Response must contain these keywords
    EvalChecks.ToolCalledCheck("get_weather")            // Agent must have called this tool
);

Evaluator fungsi kustom

Gunakan FunctionEvaluator.Create() untuk membungkus fungsi apa pun sebagai pemeriksaan evaluasi. Beberapa kelebihan beban tersedia tergantung pada data apa yang Anda butuhkan:

using Microsoft.Agents.AI;

var local = new LocalEvaluator(
    // Simple: check only the response text
    FunctionEvaluator.Create("is_concise",
        (string response) => response.Split(' ').Length < 500),

    // With expected output: compare against ground truth
    FunctionEvaluator.Create("mentions_city",
        (string response, string? expectedOutput) =>
            expectedOutput != null && response.Contains(expectedOutput, StringComparison.OrdinalIgnoreCase)),

    // Full context: access the complete EvalItem
    FunctionEvaluator.Create("used_search",
        (EvalItem item) => item.Conversation.Any(m =>
            m.Text?.Contains("search", StringComparison.OrdinalIgnoreCase) == true))
);

Pemeriksaan bawaan

Rangka Kerja Agen dilengkapi dengan pemeriksaan bawaan untuk skenario umum.

from agent_framework import (
    LocalEvaluator,
    keyword_check,
    tool_called_check,
    tool_calls_present,
    tool_call_args_match,
)

local = LocalEvaluator(
    keyword_check("weather", "temperature"),  # Response must contain these keywords
    tool_called_check("get_weather"),          # Agent must have called this tool
    tool_calls_present,                        # All expected tool call names were made
    tool_call_args_match,                      # Expected tool calls match on name + args
)

Evaluator fungsi kustom

@evaluator Gunakan dekorator untuk membungkus fungsi apa pun sebagai pemeriksaan evaluator. Nama parameter fungsi menentukan data apa yang diterimanya dari EvalItem:

from agent_framework import evaluator, LocalEvaluator

@evaluator
def is_concise(response: str) -> bool:
    """Check response is under 500 words."""
    return len(response.split()) < 500

@evaluator
def mentions_city(response: str, expected_output: str) -> bool:
    """Check response contains the expected city name."""
    return expected_output.lower() in response.lower()

@evaluator
def used_tools(conversation: list, tools: list) -> float:
    """Score based on tool usage. Returns 0.0–1.0 (>= 0.5 passes)."""
    tool_calls = [c for m in conversation for c in (m.contents or []) if c.type == "function_call"]
    return min(len(tool_calls) / max(len(tools), 1), 1.0)

local = LocalEvaluator(is_concise, mentions_city, used_tools)

Nama parameter yang didukung: query, , responseexpected_output, expected_tool_calls, conversation, tools, context.

Jenis pengembalian: bool, float (≥ 0,5 = pass), dict dengan score atau passed kunci, atau CheckResult. Fungsi asinkron ditangani secara otomatis.

using Microsoft.Agents.AI.AzureAI;

var foundry = new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence);

from agent_framework.foundry import FoundryEvals

evals = FoundryEvals(
    project_client=project_client,
    model="gpt-4o",
    evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)

using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Foundry;

var foundry = new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence);

AgentEvaluationResults results = await agent.EvaluateAsync(
    new[]
    {
        "What's the weather in Seattle?",
        "Plan a weekend trip to Portland",
        "What restaurants are near Pike Place?",
    },
    foundry);

results.AssertAllPassed();  // Throws if any item failed

EvaluateAsync adalah metode ekstensi pada AIAgent. Ini menjalankan agen sekali per kueri, mengonversi setiap interaksi menjadi EvalItem, dan meneruskan batch ke evaluator.

from agent_framework import evaluate_agent
from agent_framework.foundry import FoundryEvals

evals = FoundryEvals(
    project_client=project_client,
    model="gpt-4o",
    evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)

results = await evaluate_agent(
    agent=my_agent,
    queries=[
        "What's the weather in Seattle?",
        "Plan a weekend trip to Portland",
        "What restaurants are near Pike Place?",
    ],
    evaluators=evals,
)

for r in results:
    print(f"{r.provider}: {r.passed}/{r.total}")
    r.raise_for_status()  # Raises EvalNotPassedError if any item failed

evaluate_agent menjalankan agen sekali per kueri, mengonversi setiap interaksi menjadi EvalItem, dan meneruskan batch ke evaluator. Ini mengembalikan satu EvalResults untuk setiap penyedia evaluator.

AgentEvaluationResults results = await agent.EvaluateAsync(
    new[] { "What's the weather in Seattle?" },
    foundry,
    numRepetitions: 3);  // Each query runs 3 times independently
// Results contain 3 items (1 query × 3 repetitions)

results = await evaluate_agent(
    agent=my_agent,
    queries=["What's the weather in Seattle?"],
    evaluators=evals,
    num_repetitions=3,  # Each query runs 3 times independently
)
# Results contain 3 items (1 query × 3 repetitions)

AgentEvaluationResults results = await agent.EvaluateAsync(
    new[] { "What's 2+2?", "Capital of France?" },
    foundry,
    expectedOutput: new[] { "4", "Paris" });

Anda juga dapat menentukan panggilan alat yang diharapkan:

AgentEvaluationResults results = await agent.EvaluateAsync(
    new[] { "What's the weather in NYC?" },
    new LocalEvaluator(EvalChecks.ToolCalledCheck("get_weather")),
    expectedToolCalls: new[]
    {
        new[] { new ExpectedToolCall("get_weather") },
    });

from agent_framework import evaluate_agent, ExpectedToolCall

results = await evaluate_agent(
    agent=my_agent,
    queries=["What's 2+2?", "Capital of France?"],
    expected_output=["4", "Paris"],
    evaluators=evals,
)

Anda juga dapat menentukan panggilan alat yang diharapkan:

results = await evaluate_agent(
    agent=my_agent,
    queries=["What's the weather in NYC?"],
    expected_tool_calls=[ExpectedToolCall("get_weather", {"location": "NYC"})],
    evaluators=local,
)

var response = await agent.RunAsync(new[] { new ChatMessage(ChatRole.User, "What's the weather?") });

AgentEvaluationResults results = await agent.EvaluateAsync(
    new[] { response },
    new[] { "What's the weather?" },
    foundry);

from agent_framework import Message, evaluate_agent

response = await agent.run([Message("user", ["What's the weather?"])])

results = await evaluate_agent(
    agent=agent,
    responses=response,
    queries="What's the weather?",
    evaluators=evals,
)

// Full conversation as context
AgentEvaluationResults results = await agent.EvaluateAsync(
    new[] { "Plan a 3-day trip to Paris" },
    foundry,
    splitter: ConversationSplitters.Full);

// Per-turn: each exchange scored independently
var items = EvalItem.PerTurnItems(conversation);
var perTurnResults = await evaluator.EvaluateAsync(items);

Anda juga dapat menerapkan pemisah kustom dengan menerapkan IConversationSplitter:

public class SplitBeforeToolCall : IConversationSplitter
{
    public (IReadOnlyList<ChatMessage> QueryMessages, IReadOnlyList<ChatMessage> ResponseMessages) Split(
        IReadOnlyList<ChatMessage> conversation)
    {
        // Custom split logic
        for (int i = 0; i < conversation.Count; i++)
        {
            if (conversation[i].Text?.Contains("tool_call") == true)
                return (conversation.Take(i).ToList(), conversation.Skip(i).ToList());
        }
        return ConversationSplitters.LastTurn.Split(conversation);
    }
}

from agent_framework import evaluate_agent, ConversationSplit

# Full conversation as context
results = await evaluate_agent(
    agent=agent,
    queries=["Plan a 3-day trip to Paris"],
    evaluators=evals,
    conversation_split=ConversationSplit.FULL,
)

# Per-turn: each exchange scored independently
from agent_framework import EvalItem

items = EvalItem.per_turn_items(conversation)
# Pass items directly to an evaluator
per_turn_results = await evaluator.evaluate(items)

Anda juga dapat menyediakan pemisah kustom — pemanggil apa pun yang mengambil percakapan dan mengembalikan (query_messages, response_messages):

def split_before_memory(conversation):
    """Split just before a memory-retrieval tool call."""
    for i, msg in enumerate(conversation):
        for c in msg.contents or []:
            if c.type == "function_call" and c.name == "retrieve_memory":
                return conversation[:i], conversation[i:]
    # Fallback to default
    return EvalItem._split_last_turn_static(conversation)

results = await evaluate_agent(
    agent=agent,
    queries=queries,
    evaluators=evals,
    conversation_split=split_before_memory,
)

using Microsoft.Agents.AI;
using Microsoft.Agents.AI.AzureAI;

Run run = await workflowRunner.RunAsync(workflow, "Plan a trip to Paris");

AgentEvaluationResults results = await run.EvaluateAsync(
    new FoundryEvals(chatConfiguration, FoundryEvals.Relevance));

Console.WriteLine($"Overall: {results.Passed}/{results.Total}");

// Per-agent breakdown
if (results.SubResults != null)
{
    foreach (var (name, sub) in results.SubResults)
    {
        Console.WriteLine($"  {name}: {sub.Passed}/{sub.Total}");
    }
}

results.AssertAllPassed();

from agent_framework import evaluate_workflow
from agent_framework.foundry import FoundryEvals

evals = FoundryEvals(project_client=project_client, model="gpt-4o")
result = await workflow.run("Plan a trip to Paris")

eval_results = await evaluate_workflow(
    workflow=workflow,
    workflow_result=result,
    evaluators=evals,
)

for r in eval_results:
    print(f"{r.provider}: {r.passed}/{r.total}")
    for name, sub in r.sub_results.items():
        print(f"  {name}: {sub.passed}/{sub.total}")

Anda juga dapat meneruskan queries secara langsung dan kerangka kerja akan menjalankan alur kerja untuk Anda:

eval_results = await evaluate_workflow(
    workflow=workflow,
    queries=["Plan a trip to Paris", "Book a flight to London"],
    evaluators=evals,
)

using Microsoft.Agents.AI;
using Microsoft.Agents.AI.AzureAI;

IReadOnlyList<AgentEvaluationResults> results = await agent.EvaluateAsync(
    new[] { "What's the weather in Seattle?" },
    evaluators: new IAgentEvaluator[]
    {
        new LocalEvaluator(
            EvalChecks.KeywordCheck("weather"),
            FunctionEvaluator.Create("is_helpful", (string r) => r.Split(' ').Length > 10)),
        new FoundryEvals(chatConfiguration, FoundryEvals.Relevance, FoundryEvals.Coherence),
    });

// results[0] = local evaluator results
// results[1] = Foundry evaluator results
foreach (var r in results)
{
    Console.WriteLine($"{r.Provider}: {r.Passed}/{r.Total}");
}

from agent_framework import evaluate_agent, evaluator, LocalEvaluator, keyword_check
from agent_framework.foundry import FoundryEvals

@evaluator
def is_helpful(response: str) -> bool:
    return len(response.split()) > 10

foundry = FoundryEvals(
    project_client=project_client,
    model="gpt-4o",
    evaluators=[FoundryEvals.RELEVANCE, FoundryEvals.COHERENCE],
)

results = await evaluate_agent(
    agent=agent,
    queries=["What's the weather in Seattle?"],
    evaluators=[
        LocalEvaluator(is_helpful, keyword_check("weather")),
        foundry,
    ],
)

# results[0] = local evaluator results
# results[1] = Foundry evaluator results
for r in results:
    print(f"{r.provider}: {r.passed}/{r.total}")

Evaluator MEAI

Kerangka kerja evaluasi .NET terintegrasi langsung dengan Microsoft. Extensions.AI.Evaluation evaluator. Evaluator kualitas dan keamanan dari MEAI berfungsi tanpa adaptor apa pun:

using Microsoft.Extensions.AI.Evaluation;
using Microsoft.Extensions.AI.Evaluation.Quality;
using Microsoft.Extensions.AI.Evaluation.Safety;

// Quality evaluators
AgentEvaluationResults results = await agent.EvaluateAsync(
    new[] { "What's the weather?" },
    new CompositeEvaluator(
        new RelevanceEvaluator(),
        new CoherenceEvaluator(),
        new GroundednessEvaluator()),
    chatConfiguration: new ChatConfiguration(evalClient));

// Safety evaluators
AgentEvaluationResults safetyResults = await agent.EvaluateAsync(
    new[] { "What's the weather?" },
    new ContentHarmEvaluator(),
    chatConfiguration: new ChatConfiguration(evalClient));