CLIML
ML
7 `hanzo` commands for ML, each calling one operation on api.hanzo.ai.
Package ml is model serving: deploy a model behind an endpoint and call it.
7 commands · API reference →
| Command | Calls | What it does |
|---|---|---|
hanzo ml health | GET /v1/ml/health | Whether model serving can actually work right now |
hanzo ml models predict <name> | POST /v1/ml/models/{name}/predict | Run inference against one of your deployed models |
hanzo ml models get <name> | GET /v1/ml/models/{name} | Returns one deployed inference model. |
hanzo ml models update <name> | PATCH /v1/ml/models/{name} | Change a deployed model in place |
hanzo ml models rm <name> | DELETE /v1/ml/models/{name} | Deletes a deployed inference model. |
hanzo ml models list | GET /v1/ml/models | Lists the inference models deployed in the caller's org. |
hanzo ml models create | POST /v1/ml/models | Deploys one inference model for the caller's org, and answers 201 with the model as Kubernetes admitted it. |
How is this guide?