Skip to content

Commit ada1fb7

Browse files
Tune default embedding max batch size to 1024
- Lower EmbeddingRetryOptions.MaxEmbeddingBatchSize default from 2048 to 1024 - Align appsettings default (AIOptions:EmbeddingRetry:MaxEmbeddingBatchSize) to 1024
1 parent 920c021 commit ada1fb7

2 files changed

Lines changed: 2 additions & 2 deletions

File tree

EssentialCSharp.Chat.Shared/Models/EmbeddingRetryOptions.cs

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -39,7 +39,7 @@ public sealed class EmbeddingRetryOptions
3939
/// The service may adaptively downshift below this value when throttled.
4040
/// </summary>
4141
[Range(1, 2048)]
42-
public int MaxEmbeddingBatchSize { get; set; } = 2048;
42+
public int MaxEmbeddingBatchSize { get; set; } = 1024;
4343

4444
/// <summary>
4545
/// Minimum delay between embedding API requests in milliseconds.

EssentialCSharp.Web/appsettings.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
"MaxRetries": 5,
2626
"BaseDelayMs": 1000,
2727
"MaxDelayMs": 60000,
28-
"MaxEmbeddingBatchSize": 2048,
28+
"MaxEmbeddingBatchSize": 1024,
2929
"MinInterRequestDelayMs": 250,
3030
"BackoffMultiplier": 2.0,
3131
"MaxJitterFraction": 0.2

0 commit comments

Comments
 (0)