Mirrors/SqlDatabaseVectorSearch
1
0
Fork 0
mirror of https://github.com/marcominerva/SqlDatabaseVectorSearch.git synced 2026-06-20 12:23:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improve docx parsing, chunk ordering, and DB config

Browse Source 
- 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.
This commit is contained in:
Marco Minerva
2026-01-13 14:43:14 +01:00
parent 1ae1db2628
commit 04d777c9d5
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs
+1 -1
View File
@@ -14,7 +14,7 @@ public class DocxContentDecoder(IServiceProvider serviceProvider) : IContentDeco
// Open a Word document for read-only access. // Open a Word document for read-only access.
using var document = WordprocessingDocument.Open(stream, false); using var document = WordprocessingDocument.Open(stream, false);
var body = document.MainDocumentPart?.Document.Body; var body = document.MainDocumentPart?.Document?.Body;
var content = new StringBuilder(); var content = new StringBuilder();
foreach (var p in body?.Descendants<Paragraph>() ?? []) foreach (var p in body?.Descendants<Paragraph>() ?? [])