Mirrors/SqlDatabaseVectorSearch
1
0
Fork 0
mirror of https://github.com/marcominerva/SqlDatabaseVectorSearch.git synced 2026-08-04 09:48:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Clarify SQL Server support, improve docs and UI text

Browse Source 
Updated documentation and UI to clarify support for both Azure SQL Database and SQL Server 2025+ for native VECTOR type storage and search. Improved README with accurate prerequisites, setup instructions, and detailed ModelId usage guidance. Clarified streaming response availability in both Blazor and API. Fixed typos and improved wording in UI messages. Enhanced code comments for clarity and accuracy, including ModelId guidance in appsettings.json.
This commit is contained in:
Marco Minerva
2026-07-28 15:14:17 +02:00
parent dc26a3d2e9
commit f9f75cdf7c
6 changed files with 36 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SqlDatabaseVectorSearch/Workflows/GenerateEmbeddingExecutor.cs
+1 -1
View File
@@ -19,7 +19,7 @@ public partial class GenerateEmbeddingExecutor(IServiceProvider serviceProvider,
var chunks = await decoder.DecodeAsync(request.Content, request.ContentType, cancellationToken);
var chunkContents = chunks.Select(p => p.Content).ToList();
// We get the token count of the whole document because it is the total number of token used by embedding (it may be necessary, for example, for cost analysis).
// We get the token count of the whole document because it is the total number of tokens used by the embedding (it may be necessary, for example, for cost analysis).
var tokenCount = tokenizerService.CountEmbeddingTokens(string.Join(" ", chunkContents));
// Process paragraphs in batches.