Add --speed fast/medium/slow profiles for embed operations

Speed profiles control timeout, retries, batch size, and delays:
  fast:   30s timeout, 7 retries, batch 10, 1s delay (~5x faster)
  medium: 60s timeout, 5 retries, batch 5, 2s delay (default)
  slow:   300s timeout, 3 retries, batch 5, 5s delay (safe)

Analysis showed 54% of batches hit 300s timeout on Olla bad routes,
wasting 7.7h on 155 batches. Fast mode reduces timeout waste from
300s to 30s per bad route — real embeds take ~18s on average.

Also reduced default batch delay from 5s to 2s in config.yaml.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
salvacybersec
2026-04-07 10:30:50 +03:00
parent be0a333134
commit 0a07045e17
2 changed files with 61 additions and 9 deletions

View File

@@ -26,7 +26,7 @@ embedding:
# Batch processing — avoid API rate limits
processing:
batch_size: 50 # files per batch
delay_between_batches: 5 # seconds
delay_between_batches: 2 # seconds
max_concurrent: 3 # parallel uploads
skip_extensions: # don't process these
- ".bin"