Run a KubeAI Text Function
Call function.run(action="serve", ...) to deploy the KubeAI text model. Configure the function and service with the following parameters.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
| action | str | ✓ | Action to execute. Must be serve |
| envs | list[dict] | Environment variables. | |
| secrets | list[str] | List of secret names. | |
| profile | str | Profile template. | |
| env | dict | Environment variables for the serving function. | |
| args | list[str] | Arguments. | |
| cache_profile | str | Cache profile. | |
| files | list[KubeaiFile] | Files to make available to the model. | |
| scaling | Scaling | Scaling parameters. | |
| processors | int | Number of processors. |
Files
Files are a list of dictionaries with path and content keys:
Scaling
scaling configures replica counts, autoscaling and load balancing:
scaling = {
"replicas": int,
"min_replicas": int,
"max_replicas": int,
"autoscaling_disabled": bool,
"target_request": int,
"scale_down_delay_seconds": int,
"load_balancing": {
"strategy": str, # "LeastLoad" or "PrefixHash"
"prefix_hash": {
"mean_load_factor": int,
"replication": int,
"prefix_char_length": int
}
}
}