Skip to content

Add reporting tests that show NLP results. #6574

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
peterwald merged 6 commits into from
Jul 2, 2025
Merged

Add reporting tests that show NLP results. #6574

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
32e53fe
Add reporting tests that show NLP results.
peterwald Jul 2, 2025
b597474
Cleanup analyzer errors.
peterwald Jul 2, 2025
02d472c
Add global tags for NLP
peterwald Jul 2, 2025
84ecf9b
Add more precision to the evaluator timing
peterwald Jul 2, 2025
f353a5d
More tags
peterwald Jul 2, 2025
4988168
Add another partial match test
peterwald Jul 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions test/Libraries/Microsoft.Extensions.AI.Evaluation.Integration.Tests/NLPEvaluatorTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
#pragma warning disable CA2016 // Forward the 'CancellationToken' parameter to methods that take it.
#pragma warning disable CS8618 // Non-nullable field must contain a non-null value when exiting constructor.

using System;
using System.Diagnostics.CodeAnalysis;
using System.Linq;
using System.Threading.Tasks;
Expand All @@ -24,6 +25,11 @@ static NLPEvaluatorTests()
{
if (Settings.Current.Configured)
{
string version = $"Product Version: {Constants.Version}";
string date = $"Date: {DateTime.UtcNow:dddd, dd MMMM yyyy}";
string projectName = $"Project: Integration Tests";
string testClass = $"Test Class: {nameof(NLPEvaluatorTests)}";
Comment thread
peterwald marked this conversation as resolved.

IEvaluator bleuEvaluator = new BLEUEvaluator();
IEvaluator gleuEvaluator = new GLEUEvaluator();
IEvaluator f1Evaluator = new F1Evaluator();
Expand All @@ -33,7 +39,7 @@ static NLPEvaluatorTests()
storageRootPath: Settings.Current.StorageRootPath,
evaluators: [bleuEvaluator, gleuEvaluator, f1Evaluator],
executionName: Constants.Version,
tags: []);
tags: [version, date, projectName, testClass]);
}
}

Expand All @@ -51,9 +57,7 @@ await _nlpReportingConfiguration.CreateScenarioRunAsync(
var gleuContext = new GLEUEvaluatorContext(referenceText);
var f1Context = new F1EvaluatorContext(referenceText);

var response = new ChatResponse(new ChatMessage(ChatRole.Assistant, "The quick brown fox jumps over the lazy dog."));

EvaluationResult result = await scenarioRun.EvaluateAsync(response, [bleuContext, gleuContext, f1Context]);
EvaluationResult result = await scenarioRun.EvaluateAsync(referenceText, [bleuContext, gleuContext, f1Context]);

Assert.False(
result.ContainsDiagnostics(d => d.Severity >= EvaluationDiagnosticSeverity.Warning),
Expand All @@ -79,9 +83,7 @@ await _nlpReportingConfiguration.CreateScenarioRunAsync(
var gleuContext = new GLEUEvaluatorContext(referenceText);
var f1Context = new F1EvaluatorContext(referenceText);

var response = new ChatResponse(new ChatMessage(ChatRole.Assistant, "What is the meaning of life?"));

EvaluationResult result = await scenarioRun.EvaluateAsync(response, [bleuContext, gleuContext, f1Context]);
EvaluationResult result = await scenarioRun.EvaluateAsync("What is the meaning of life?", [bleuContext, gleuContext, f1Context]);

Assert.False(
result.ContainsDiagnostics(d => d.Severity >= EvaluationDiagnosticSeverity.Warning),
Expand All @@ -102,9 +104,7 @@ public async Task AdditionalContextIsNotPassed()
await _nlpReportingConfiguration.CreateScenarioRunAsync(
scenarioName: $"Microsoft.Extensions.AI.Evaluation.Integration.Tests.{nameof(NLPEvaluatorTests)}.{nameof(AdditionalContextIsNotPassed)}");

var response = new ChatResponse(new ChatMessage(ChatRole.Assistant, "What is the meaning of life?"));

EvaluationResult result = await scenarioRun.EvaluateAsync(response);
EvaluationResult result = await scenarioRun.EvaluateAsync("What is the meaning of life?");

Assert.True(
result.Metrics.Values.All(m => m.ContainsDiagnostics(d => d.Severity is EvaluationDiagnosticSeverity.Error)),
Expand Down
Loading