mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
c79f886dc3
* dotnet: refresh Foundry sample guidance Carry forward the still-relevant sample guidance and Foundry-specific documentation fixes from the old stacked sample migration work, adapted to the current repo layout and policy. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * dotnet: rename Foundry sample env vars Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * dotnet: remove persistent provider sample Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * dotnet: drop SAMPLE_GUIDELINES.md from this PR Defer the guidelines doc and its cross-link to a follow-on PR to avoid broken-link failures in CI. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * dotnet: add DefaultAzureCredential warning to remaining samples Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * dotnet: address PR review feedback Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
56 lines
2.4 KiB
C#
56 lines
2.4 KiB
C#
// Copyright (c) Microsoft. All rights reserved.
|
|
|
|
// Simplest possible agent evaluation: create a Foundry agent, run it against
|
|
// test questions, and use Foundry quality evaluators to score the responses.
|
|
// For custom domain-specific checks, see the Evaluation_CustomEvals sample.
|
|
|
|
using Azure.AI.Projects;
|
|
using Azure.Identity;
|
|
using Microsoft.Agents.AI;
|
|
using Microsoft.Extensions.AI.Evaluation;
|
|
using FoundryEvals = Microsoft.Agents.AI.Foundry.FoundryEvals;
|
|
|
|
string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
|
|
string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
|
|
|
|
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
|
|
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
|
|
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
|
|
AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
|
|
|
|
AIAgent agent = projectClient.AsAIAgent(
|
|
model: deploymentName,
|
|
instructions: "You are a helpful assistant. Provide clear, accurate answers.",
|
|
name: "SimpleAgent");
|
|
|
|
// Configure Foundry quality evaluators — runs evaluations server-side via the Foundry Evals API.
|
|
FoundryEvals evaluator = new(projectClient, deploymentName, FoundryEvals.Relevance, FoundryEvals.Coherence);
|
|
|
|
// Run the agent against test queries and evaluate in one call.
|
|
string[] queries = ["What is photosynthesis?", "How do vaccines work?"];
|
|
AgentEvaluationResults results = await agent.EvaluateAsync(queries, evaluator);
|
|
|
|
// Print results.
|
|
Console.WriteLine($"Passed: {results.Passed}/{results.Total}");
|
|
if (results.ReportUrl is not null)
|
|
{
|
|
Console.WriteLine($"Report: {results.ReportUrl}");
|
|
}
|
|
|
|
Console.WriteLine();
|
|
|
|
for (int i = 0; i < results.Items.Count; i++)
|
|
{
|
|
Console.WriteLine($"Query: {queries[i]}");
|
|
Console.WriteLine($"Response: {(results.InputItems?[i].Response is { } resp ? resp.Substring(0, Math.Min(50, resp.Length)) : "N/A")}...");
|
|
foreach (var metric in results.Items[i].Metrics)
|
|
{
|
|
string score = metric.Value is NumericMetric nm && nm.Value.HasValue
|
|
? nm.Value.Value.ToString("F1")
|
|
: "N/A";
|
|
Console.WriteLine($" {metric.Key}: {score}");
|
|
}
|
|
|
|
Console.WriteLine();
|
|
}
|