Deployments

import os
from dotenv import load_dotenv
load_dotenv()

from simplismart import DeploymentCreate, Simplismart

client = Simplismart()
deployment = client.create_deployment(
    DeploymentCreate(
        model_repo=os.getenv("MODEL_REPO_ID", "model-repo-uuid"),
        org=os.getenv("ORG_ID"),
        gpu_id="nvidia-h100",
        name="vision-private-deploy",
        min_pod_replicas=1,
        max_pod_replicas=2,
        autoscale_config={"targets": [{"metric": "gpu", "target": 80}]},
        env_variables={"KEY": "value"},
        healthcheck={"path": "/", "port": 8000},
        ports={"http": {"port": 8000}},
        metrics_path=["/v1/chat/completions"],
        fast_scaleup=True,
        deployment_tag="v1.0",
    )
)

autoscale_config = {
    "targets": [
        {
            "metric": "gpu",      # Required
            "target": 80,          # Required (number)
            "percentile": 95      # Optional, only for latency metric
        }
    ]
}

import os
from dotenv import load_dotenv
load_dotenv()

from simplismart import Simplismart

client = Simplismart()
deployments = client.list_deployments(
    model_repo_id=os.getenv("MODEL_REPO_ID"),  # Optional
    status="DEPLOYED",
    offset=0,
    count=20,
)
print(deployments)

[
  {
    "deployment_id": "deployment-uuid",
    "deployment_name": "speechbrain-v3",
    "model_repo_id": "model-repo-uuid",
    "model_repo_name": "speechbrain",
    "model_type": "unknown",
    "accelerator_type": ["nvidia-l40s"],
    "accelerator_count": 1,
    "status": "DEPLOYED"
  }
]

deployments = client.list_model_deployments(org_id="org-uuid")

deployment = client.get_model_deployment(deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"))

print(deployment)

deployment = client.get_deployment(deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"))

updated = client.update_deployment(
    deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"),
    payload={
        "min_pod_replicas": 1,
        "max_pod_replicas": 2,
        "autoscale_config": {"targets": [{"metric": "gpu", "target": 80}]},
    },
)

result = client.stop_deployment(deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"))

result = client.start_deployment(deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"))

result = client.restart_deployment(
    deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"),
)

health = client.fetch_deployment_health(deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"))

print(health)

{
  "data": "Healthy",
  "messages": [
    {
      "message": "Ready to use, the model is running and available for inference.",
      "severity": "info"
    }
  ],
  "pods": { "ready": 1, "not_ready": 0 }
}

result = client.update_deployment_autoscaling(
    deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"),
    min_replicas=1,
    max_replicas=3,
)

result = client.delete_deployment(
    deployment_id=os.getenv("DEPLOYMENT_ID", "deployment-uuid"),
)

from simplismart import Simplismart, SimplismartError

client = Simplismart()
try:
    deployment = client.get_deployment(deployment_id="00000000-0000-0000-0000-000000000000")
except SimplismartError as e:
    print("Status:", e.status_code)
    print("Message:", e)
    print("Payload:", e.payload)

Caught SimplismartError:
  status_code: 404
  message: No ModelDeployment matches the given query. (status=404)
  payload: {'detail': 'No ModelDeployment matches the given query.'}

import json
from simplismart import Simplismart

client = Simplismart()

with open("byoc-create.json") as f:
    payload = json.load(f)

deployment = client.create_byoc_deployment(payload=payload)