From 04d777c9d5adfd6f321b5a7891a691bd44a69b04 Mon Sep 17 00:00:00 2001
From: Marco Minerva <marco.minerva@gmail.com>
Date: Tue, 13 Jan 2026 14:43:14 +0100
Subject: [PATCH] Improve docx parsing, chunk ordering, and DB config

- Add null check for Document in DocxContentDecoder to prevent exceptions.
- Set DocumentChunk.Id to auto-generate in ApplicationDbContext.
- Order vector search results by cosine similarity for relevance.
---
 SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs | 2 +-
 SqlDatabaseVectorSearch/Data/ApplicationDbContext.cs          | 2 +-
 SqlDatabaseVectorSearch/Services/VectorSearchService.cs       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs b/SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs
index 00579c4..7b0bac1 100644
--- a/SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs
+++ b/SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs
@@ -14,7 +14,7 @@ public class DocxContentDecoder(IServiceProvider serviceProvider) : IContentDeco
         // Open a Word document for read-only access.
         using var document = WordprocessingDocument.Open(stream, false);
 
-        var body = document.MainDocumentPart?.Document.Body;
+        var body = document.MainDocumentPart?.Document?.Body;
         var content = new StringBuilder();
 
         foreach (var p in body?.Descendants<Paragraph>() ?? [])
diff --git a/SqlDatabaseVectorSearch/Data/ApplicationDbContext.cs b/SqlDatabaseVectorSearch/Data/ApplicationDbContext.cs
index e9e41a3..a595973 100644
--- a/SqlDatabaseVectorSearch/Data/ApplicationDbContext.cs
+++ b/SqlDatabaseVectorSearch/Data/ApplicationDbContext.cs
@@ -34,7 +34,7 @@ public class ApplicationDbContext(DbContextOptions<ApplicationDbContext> options
         modelBuilder.Entity<DocumentChunk>(entity =>
         {
             entity.ToTable("DocumentChunks");
-            entity.HasKey(e => e.Id);
+            entity.HasKey(e => e.Id);            
 
             entity.Property(e => e.Id).ValueGeneratedOnAdd();
             entity.Property(e => e.Content).IsRequired();
diff --git a/SqlDatabaseVectorSearch/Services/VectorSearchService.cs b/SqlDatabaseVectorSearch/Services/VectorSearchService.cs
index 113af4b..f18d39e 100644
--- a/SqlDatabaseVectorSearch/Services/VectorSearchService.cs
+++ b/SqlDatabaseVectorSearch/Services/VectorSearchService.cs
@@ -152,7 +152,7 @@ public partial class VectorSearchService(IServiceProvider serviceProvider, Appli
         var questionEmbedding = await embeddingGenerator.GenerateVectorAsync(reformulatedQuestion.Text!, cancellationToken: cancellationToken);
         var embeddingVector = new SqlVector<float>(questionEmbedding);
 
-        var chunks = await dbContext.DocumentChunks.Include(c => c.Document)                    
+        var chunks = await dbContext.DocumentChunks.Include(c => c.Document)
                     .OrderBy(c => EF.Functions.VectorDistance("cosine", c.Embedding, embeddingVector))
                     .Take(appSettings.MaxRelevantChunks)
                     .ToListAsync(cancellationToken);