From d6b60197e6cf90d4a20c59b96457e7c3fcaad166 Mon Sep 17 00:00:00 2001
From: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>
Date: Tue, 24 Sep 2024 11:08:57 +0100
Subject: [PATCH] .Net: Add filtering support for VectoreStoreTextSearch
 (#8947)

### Motivation and Context

Related to #6725

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
---
 .../Data/VectorSearch/VectorSearchFilter.cs   | 18 +++++++
 .../Data/TextSearch/VectorStoreTextSearch.cs  |  2 +-
 .../Data/VectorStoreTextSearchTests.cs        | 47 +++++++++++++++++++
 3 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/dotnet/src/SemanticKernel.Abstractions/Data/VectorSearch/VectorSearchFilter.cs b/dotnet/src/SemanticKernel.Abstractions/Data/VectorSearch/VectorSearchFilter.cs
index 030261dd8567..bddc6487fc4c 100644
--- a/dotnet/src/SemanticKernel.Abstractions/Data/VectorSearch/VectorSearchFilter.cs
+++ b/dotnet/src/SemanticKernel.Abstractions/Data/VectorSearch/VectorSearchFilter.cs
@@ -28,6 +28,24 @@ public sealed class VectorSearchFilter
     /// </summary>
     public IEnumerable<FilterClause> FilterClauses => this._filterClauses;
 
+    /// <summary>
+    /// Create an instance of <see cref="VectorSearchFilter"/>
+    /// </summary>
+    public VectorSearchFilter()
+    {
+    }
+
+    /// <summary>
+    /// Create an instance of <see cref="VectorSearchFilter"/> with the provided <see cref="FilterClause"/>s.
+    /// <param name="filterClauses">The <see cref="FilterClause"/> instances to use</param>
+    /// </summary>
+    internal VectorSearchFilter(IEnumerable<FilterClause> filterClauses)
+    {
+        Verify.NotNull(filterClauses, nameof(filterClauses));
+
+        this._filterClauses.AddRange(filterClauses);
+    }
+
     /// <summary>
     /// Add an equal to clause to the filter options.
     /// </summary>
diff --git a/dotnet/src/SemanticKernel.Core/Data/TextSearch/VectorStoreTextSearch.cs b/dotnet/src/SemanticKernel.Core/Data/TextSearch/VectorStoreTextSearch.cs
index d720f455eec7..979a7aac3d92 100644
--- a/dotnet/src/SemanticKernel.Core/Data/TextSearch/VectorStoreTextSearch.cs
+++ b/dotnet/src/SemanticKernel.Core/Data/TextSearch/VectorStoreTextSearch.cs
@@ -117,7 +117,7 @@ private async Task<IAsyncEnumerable<VectorSearchResult<TRecord>>> ExecuteVectorS
         searchOptions ??= new TextSearchOptions();
         var vectorSearchOptions = new VectorSearchOptions
         {
-            Filter = null,
+            Filter = searchOptions.Filter?.FilterClauses is not null ? new VectorSearchFilter(searchOptions.Filter.FilterClauses) : null,
             Offset = searchOptions.Offset,
             Limit = searchOptions.Count,
         };
diff --git a/dotnet/src/SemanticKernel.UnitTests/Data/VectorStoreTextSearchTests.cs b/dotnet/src/SemanticKernel.UnitTests/Data/VectorStoreTextSearchTests.cs
index 9f2fd61c6fc7..36f769582811 100644
--- a/dotnet/src/SemanticKernel.UnitTests/Data/VectorStoreTextSearchTests.cs
+++ b/dotnet/src/SemanticKernel.UnitTests/Data/VectorStoreTextSearchTests.cs
@@ -124,6 +124,47 @@ public async Task CanGetSearchResultsWithVectorizableTextSearchAsync()
         Assert.Equal(2, results.Count);
     }
 
+    [Fact]
+    public async Task CanFilterGetSearchResultsWithVectorizedSearchAsync()
+    {
+        // Arrange.
+        var sut = await CreateVectorStoreTextSearchFromVectorizedSearchAsync();
+        TextSearchFilter evenFilter = new();
+        evenFilter.Equality("Tag", "Even");
+        TextSearchFilter oddFilter = new();
+        oddFilter.Equality("Tag", "Odd");
+
+        // Act.
+        KernelSearchResults<object> evenSearchResults = await sut.GetSearchResultsAsync("What is the Semantic Kernel?", new()
+        {
+            Count = 2,
+            Offset = 0,
+            Filter = evenFilter
+        });
+        var evenResults = await ToListAsync(evenSearchResults.Results);
+        KernelSearchResults<object> oddSearchResults = await sut.GetSearchResultsAsync("What is the Semantic Kernel?", new()
+        {
+            Count = 2,
+            Offset = 0,
+            Filter = oddFilter
+        });
+        var oddResults = await ToListAsync(oddSearchResults.Results);
+
+        Assert.Equal(2, evenResults.Count);
+        var result1 = evenResults[0] as DataModel;
+        Assert.Equal("Even", result1?.Tag);
+        var result2 = evenResults[1] as DataModel;
+        Assert.Equal("Even", result2?.Tag);
+
+        Assert.Equal(2, oddResults.Count);
+        result1 = oddResults[0] as DataModel;
+        Assert.Equal("Odd", result1?.Tag);
+        result2 = oddResults[1] as DataModel;
+        Assert.Equal("Odd", result2?.Tag);
+    }
+
+    #region private
+
     /// <summary>
     /// Create a <see cref="VectorStoreTextSearch{TRecord}"/> from a <see cref="IVectorizedSearch{TRecord}"/>.
     /// </summary>
@@ -185,6 +226,7 @@ private static async Task AddRecordsAsync(
             {
                 Key = Guid.NewGuid(),
                 Text = $"Record {i}",
+                Tag = i % 2 == 0 ? "Even" : "Odd",
                 Embedding = await embeddingService.GenerateEmbeddingAsync($"Record {i}")
             };
             await recordCollection.UpsertAsync(dataModel);
@@ -274,7 +316,12 @@ private sealed class DataModel
         [VectorStoreRecordData]
         public required string Text { get; init; }
 
+        [VectorStoreRecordData(IsFilterable = true)]
+        public required string Tag { get; init; }
+
         [VectorStoreRecordVector(1536)]
         public ReadOnlyMemory<float> Embedding { get; init; }
     }
+
+    #endregion
 }