GeneralBots/botserver
2
1
Fork 0
Code Activity Actions 1

Add comment about batch_size reduction for llama-server stability
All checks were successful
BotServer CI/CD / build (push) Successful in 2m9s
Details

Browse source
This commit is contained in:
Rodrigo Rodriguez (Pragmatismo) 2026-04-12 09:59:49 -03:00
parent d3673e1f34
commit 694fb91efe
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/core/kb/embedding_generator.rs
View file

@ -43,7 +43,7 @@ impl Default for EmbeddingConfig {
embedding_model: "BAAI/bge-multilingual-gemma2".to_string(),
embedding_key: None,
dimensions: 2048,
batch_size: 2,
batch_size: 2, // Reduced from 16 to prevent llama-server crash
timeout_seconds: 60,
max_concurrent_requests: 1,
connect_timeout_seconds: 10,