100K embedding: supervisor achieves 67.6/sec (57% faster than single pipeline)

- 4 parallel pipelines on i9 + A4000 via Ollama
- Previous single-pipeline: 43/sec, 39min for 100K
- Supervisor: 67.6/sec, 22min for 100K
- Previous 100K attempt failed at 97K (no retry) — supervisor handles this
- Checkpointing every 1000 chunks for crash recovery
- Round-robin retry on batch failure (3 attempts)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
root
2026-03-27 09:45:59 -05:00
co-authored by Claude Opus 4.6
parent 6f0f92a9e4
commit b2cd54e941
15 changed files with 162 additions and 105 deletions
+1
View File
@@ -0,0 +1 @@
{"job_id":"job-1774622586005","index_name":"resumes_100k_v2","total_chunks":100000,"completed_ranges":[[92500,95000],[95000,97500],[90000,92500],[97500,100000]],"failed_ranges":[],"embedded_count":10000}