Pin the Qwen embedding/reranker models to specific commit revisions (and sentence-transformers to the exact version already in use) so index builds are reproducible instead of floating on each model's main branch. Also move the encoder and reranker instances to module-level singletons shared by every Index, instead of one pair per instance, so a process serving multiple repository roots only loads each model once. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2 lines
29 B
Plaintext
2 lines
29 B
Plaintext
sentence-transformers==5.7.0
|