Enhance citation handling and document chunk structure

- Updated `Ask.razor` to change `PageNumber` to a nullable integer and added `IndexOnPage` to the `Citation` class. Adjusted regex for citation parsing.
- Introduced `PageNumber` and `IndexOnPage` properties in `DocumentChunk.cs`, marking `Content` as required.
- Modified migration files to reflect changes in `DocumentChunk` and `Document` entities.
- Updated citation format in `ChatService.cs` to include `index-on-page` and adjusted document chunk text formatting.
- Changed embedding generation method in `VectorSearchService.cs` and updated document chunk creation to include new properties.

SqlDatabaseVectorSearch/Data/Migrations/00000000000000_Initial.cs

@@ -3,7 +3,7 @@ using Microsoft.EntityFrameworkCore.Migrations;
 
 #nullable disable
 
-namespace SqlDatabaseVectorSearch.Data.Migrations
+namespace SqlDatabaseVectorSearch.Migrations
 {
     /// <inheritdoc />
     public partial class Initial : Migration
@@ -31,6 +31,8 @@ namespace SqlDatabaseVectorSearch.Data.Migrations
                     Id = table.Column<Guid>(type: "uniqueidentifier", nullable: false),
                     DocumentId = table.Column<Guid>(type: "uniqueidentifier", nullable: false),
                     Index = table.Column<int>(type: "int", nullable: false),
+                    PageNumber = table.Column<int>(type: "int", nullable: true),
+                    IndexOnPage = table.Column<int>(type: "int", nullable: false),
                     Content = table.Column<string>(type: "nvarchar(max)", nullable: false),
                     Embedding = table.Column<string>(type: "vector(1536)", nullable: false)
                 },