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

Add support for DOCX and TXT files, update error handling

Browse Source 
Updated README.md to reflect support for PDF, DOCX, and TXT files.
Removed commented-out code in DocxContentDecoder.cs.
Added TextContentDecoder service in Program.cs and updated exception handling middleware.
Updated document upload endpoint description in Program.cs.
Modified VectorSearchService to throw NotSupportedException for unsupported content types.
Added TextContentDecoder class in TextContentDecoder.cs.
This commit is contained in:
Marco Minerva
2025-01-29 09:58:22 +01:00
parent 110e21e1e0
commit af9158873f
5 changed files with 26 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SqlDatabaseVectorSearch/ContentDecoders/DocxContentDecoder.cs
-36
View File
@@ -21,41 +21,5 @@ public class DocxContentDecoder : IContentDecoder
}
return Task.FromResult(content.ToString());
//foreach (var paragraph in body!.Elements<Paragraph>())
//{
// foreach (var element in paragraph.Elements())
// {
// if (element is Run run)
// {
// DecodeTextFromRun(run);
// }
// else if (element is Hyperlink hyperlink)
// {
// foreach (var hyperlinkRun in hyperlink.Elements<Run>())
// {
// DecodeTextFromRun(hyperlinkRun);
// }
// //var hyperlinkUri = doc.MainDocumentPart.HyperlinkRelationships.FirstOrDefault(r => r.Id == hyperlink.Id)?.Uri;
// //if (hyperlinkUri is not null)
// //{
// // content.Append($" ({hyperlinkUri})");
// //}
// }
// }
// content.AppendLine(); // Preserve whitespace and blank lines.
//}
//return Task.FromResult(content.ToString());
//void DecodeTextFromRun(Run run)
//{
// foreach (var text in run.Elements<Text>())
// {
// content.Append(text.Text);
// }
//}
}
}
SqlDatabaseVectorSearch/ContentDecoders/TextContentDecoder.cs
+12
View File
@@ -0,0 +1,12 @@
namespace SqlDatabaseVectorSearch.ContentDecoders;
public class TextContentDecoder : IContentDecoder
{
public async Task<string> DecodeAsync(Stream stream, string contentType)
{
using var readStream = new StreamReader(stream);
var content = await readStream.ReadToEndAsync();
return content;
}
}
SqlDatabaseVectorSearch/Program.cs
+11 -2
View File
@@ -54,6 +54,7 @@ builder.Services.AddScoped<VectorSearchService>();
builder.Services.AddKeyedSingleton<IContentDecoder, PdfContentDecoder>(MediaTypeNames.Application.Pdf);
builder.Services.AddKeyedSingleton<IContentDecoder, DocxContentDecoder>("application/vnd.openxmlformats-officedocument.wordprocessingml.document");
builder.Services.AddKeyedSingleton<IContentDecoder, TextContentDecoder>(MediaTypeNames.Text.Plain);
builder.Services.ConfigureHttpJsonOptions(options =>
{
@@ -74,7 +75,15 @@ var app = builder.Build();
// Configure the HTTP request pipeline.
app.UseHttpsRedirection();
app.UseExceptionHandler();
app.UseExceptionHandler(new ExceptionHandlerOptions
{
StatusCodeSelector = exception => exception switch
{
NotSupportedException => StatusCodes.Status501NotImplemented,
_ => StatusCodes.Status500InternalServerError
}
});
app.UseStatusCodePages();
app.MapOpenApi();
@@ -125,7 +134,7 @@ documentsApiGroup.MapPost(string.Empty, async (IFormFile file, VectorSearchServi
.DisableAntiforgery()
.ProducesProblem(StatusCodes.Status400BadRequest)
.WithSummary("Uploads a document")
.WithDescription("Uploads a document to SQL Database and saves its embedding using the native VECTOR type. The document will be indexed and used to answer questions. Currently, only PDF files are supported.");
.WithDescription("Uploads a document to SQL Database and saves its embedding using the native VECTOR type. The document will be indexed and used to answer questions. Currently, PDF, DOCX and TXT files are supported.");
documentsApiGroup.MapDelete("{documentId:guid}", async (Guid documentId, VectorSearchService vectorSearchService) =>
{
SqlDatabaseVectorSearch/Services/VectorSearchService.cs
+1 -1
View File
@@ -18,7 +18,7 @@ public class VectorSearchService(IServiceProvider serviceProvider, ApplicationDb
public async Task<Guid> ImportAsync(Stream stream, string name, string contentType, Guid? documentId)
{
// Extract the contents of the file.
var decoder = serviceProvider.GetRequiredKeyedService<IContentDecoder>(contentType);
var decoder = serviceProvider.GetKeyedService<IContentDecoder>(contentType) ?? throw new NotSupportedException($"Content type '{contentType}' is not supported.");
var content = await decoder.DecodeAsync(stream, contentType);
await dbContext.Database.BeginTransactionAsync();