edwin-onyxandcubic-dev-ai[bot] 67bd14e801 fix(infra): lazy import litellm and some more pkgs and add layer to connector instantiation for lazy loading (#5488) ...

Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>

2025-10-01 15:05:27 -07:00

..

__init__.py

Model Server (#695)

2023-11-06 16:36:09 -08:00

constants.py

refactor(model): move api-based embeddings/reranking calls out of model server (#5216)

2025-08-20 21:50:21 +00:00

custom_models.py

refactor to use stricter typing (#4513)

2025-04-14 17:23:07 +00:00

encoders.py

fix(infra): lazy import litellm and some more pkgs and add layer to connector instantiation for lazy loading (#5488)

2025-10-01 15:05:27 -07:00

main.py

feat: add non-root user to backend and model-server images (#5134)

2025-08-20 13:49:50 -07:00

management_endpoints.py

improve gpu detection functions and logging in model server

2025-02-07 16:59:02 -08:00

onyx_torch_model.py

refactor to use stricter typing (#4513)

2025-04-14 17:23:07 +00:00

utils.py

refactor(model): move api-based embeddings/reranking calls out of model server (#5216)

2025-08-20 21:50:21 +00:00