Add PII redaction POC for secure LLM prompting.
Implements detect-redact-sanitize pipeline with regex, domain rules, and ONNX NER before the LLM boundary, plus NUnit tests and Xenovex push documentation. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
@@ -0,0 +1,53 @@
|
||||
using FluentAssertions;
|
||||
using Microsoft.Extensions.Logging.Abstractions;
|
||||
using Microsoft.Extensions.Options;
|
||||
using PiiRedaction.Core.Configuration;
|
||||
using PiiRedaction.Core.Models;
|
||||
using PiiRedaction.Infrastructure.Onnx;
|
||||
|
||||
namespace PiiRedaction.Infrastructure.Tests.Onnx;
|
||||
|
||||
[TestFixture]
|
||||
public sealed class OnnxNerModelRunnerTests
|
||||
{
|
||||
[Test]
|
||||
public void Constructor_MissingModel_IsModelUnavailable()
|
||||
{
|
||||
var path = Path.Combine(Path.GetTempPath(), $"missing-ner-{Guid.NewGuid():N}.onnx");
|
||||
using var runner = CreateRunner(path);
|
||||
|
||||
runner.IsModelAvailable.Should().BeFalse();
|
||||
}
|
||||
|
||||
[Test]
|
||||
public void PredictEntities_WhenModelUnavailable_ReturnsEmpty()
|
||||
{
|
||||
var path = Path.Combine(Path.GetTempPath(), $"missing-ner-{Guid.NewGuid():N}.onnx");
|
||||
using var runner = CreateRunner(path);
|
||||
|
||||
runner.PredictEntities("Customer Ravi Kumar").Should().BeEmpty();
|
||||
}
|
||||
|
||||
[Test]
|
||||
public void Constructor_InvalidModelFile_IsModelUnavailable()
|
||||
{
|
||||
var path = Path.Combine(Path.GetTempPath(), $"invalid-ner-{Guid.NewGuid():N}.onnx");
|
||||
File.WriteAllText(path, "not-a-valid-onnx-model");
|
||||
|
||||
try
|
||||
{
|
||||
using var runner = CreateRunner(path);
|
||||
runner.IsModelAvailable.Should().BeFalse();
|
||||
}
|
||||
finally
|
||||
{
|
||||
File.Delete(path);
|
||||
}
|
||||
}
|
||||
|
||||
private static OnnxNerModelRunner CreateRunner(string modelPath)
|
||||
{
|
||||
var options = Options.Create(new PiiRedactionOptions { OnnxModelPath = modelPath });
|
||||
return new OnnxNerModelRunner(options, NullLogger<OnnxNerModelRunner>.Instance);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,51 @@
|
||||
using FluentAssertions;
|
||||
|
||||
using PiiRedaction.Core.Models;
|
||||
|
||||
using PiiRedaction.Tests.Shared;
|
||||
|
||||
|
||||
|
||||
namespace PiiRedaction.Infrastructure.Tests.Onnx;
|
||||
|
||||
|
||||
|
||||
[TestFixture]
|
||||
|
||||
[Category("RealModel")]
|
||||
|
||||
public sealed class RealNerModelRunnerTests : RealNerModelFixture
|
||||
|
||||
{
|
||||
|
||||
[TestCase("Customer Ravi Kumar called about billing.", "Ravi", "Ravi Kumar")]
|
||||
|
||||
[TestCase("Mr. John Smith called about a duplicate debit.", "John", "John Smith")]
|
||||
|
||||
public void PredictEntities_DetectsPersonWithCorrectSpan(string prompt, string expectedNamePart, string expectedValue)
|
||||
|
||||
{
|
||||
|
||||
var entities = Runner.PredictEntities(prompt);
|
||||
|
||||
|
||||
|
||||
entities.Should().Contain(entity =>
|
||||
|
||||
entity.Type == PiiEntityType.Person &&
|
||||
|
||||
entity.Source == PiiDetectionSource.Ner &&
|
||||
|
||||
entity.Value.Contains(expectedNamePart, StringComparison.Ordinal) &&
|
||||
|
||||
prompt.AsSpan(entity.StartIndex, entity.Length).ToString() == entity.Value);
|
||||
|
||||
|
||||
|
||||
entities.Should().Contain(entity => entity.Value == expectedValue);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user