Overview

pip install simplismart-sdk

export SIMPLISMART_PG_TOKEN="your_pg_token_here"
export ORG_ID="your_org_uuid"
export SIMPLISMART_BASE_URL="https://api.app.simplismart.ai"  # Optional, default: https://api.app.simplismart.ai
export SIMPLISMART_TIMEOUT="300"  # Optional, default: 300 seconds

import os
from dotenv import load_dotenv
load_dotenv()

from simplismart import Simplismart

# Token and optional settings from env: SIMPLISMART_PG_TOKEN, SIMPLISMART_BASE_URL, SIMPLISMART_TIMEOUT
client = Simplismart(
    pg_token=os.getenv("SIMPLISMART_PG_TOKEN"),
    base_url=os.getenv("SIMPLISMART_BASE_URL", "https://api.app.simplismart.ai"),
    timeout=int(os.getenv("SIMPLISMART_TIMEOUT", "300")),
)

import os
from dotenv import load_dotenv
from simplismart import Simplismart, ModelRepoCompileCreate, ModelRepoListParams, DeploymentCreate
load_dotenv()
from time import sleep

client = Simplismart(pg_token=os.getenv("SIMPLISMART_PG_TOKEN"))
org_id = os.getenv("ORG_ID")
MODEL_REPO_NAME = "llama-3.2-1b-instruct-SDK"

# model compile
payload = ModelRepoCompileCreate(
    name=MODEL_REPO_NAME,
    description="llama-model - A model deployed using Simplismart",    
    source_type="huggingface",
    source_url="meta-llama/Llama-3.2-1B-Instruct",
    model_class="LlamaForCausalLM",
    accelerator_type="nvidia-h100",
    use_simplismart_infrastructure=True,
)

data = client.create_model_repo_private_compile(payload)
print(
    f"Model compilation initiated: {data['name']} | "
    f"uuid={data['uuid']} | status={data['status']} | source={data['source_url']}"
)

# Fetch the compiled model repo and wait until it's ready
list_params = ModelRepoListParams(org_id=org_id, offset=0, count=1, name=MODEL_REPO_NAME)
model_repo_id = None
prev_status = None

while True:
    repos = client.list_model_repos(list_params)
    result = repos["results"][0]
    model_repo_id = result["uuid"]
    status = result["status"]

    if status != prev_status:
        print(f"Model Repo {model_repo_id}: {status}")
        prev_status = status

    if status == "SUCCESS":
        break
    sleep(10)

# create deployment
deployment = client.create_deployment(
    DeploymentCreate(
        org=org_id,
        model_repo=model_repo_id,
        gpu_id="nvidia-h100",
        name="llama-3.2-1b-instruct-SDK",  # should be unique
        min_pod_replicas=1,
        max_pod_replicas=2,
        autoscale_config={"targets": [{"metric": "gpu", "target": 80}]},
    )
)

deployment_id = deployment["deployment_id"]
model_endpoint = deployment.get("model_endpoint", "")
print(
    f"Deployment created: id={deployment_id} \n Name={deployment.get('name')} \n "
    f"Model Endpoint=https://{model_endpoint}"
)

deployment_detail = client.get_model_deployment(
    deployment_id=os.getenv("DEPLOYMENT_ID", deployment_id)
)
print(f"Status: {deployment_detail.get('status', 'unknown')}")

health = client.fetch_deployment_health(deployment_id=deployment_id)
health_status = health.get("data", "unknown")
if health.get("messages"):
    msg = health["messages"][0].get("message", "")
    print(f"Health: {health_status} — {msg}")
else:
    print(f"Health: {health_status}")

if health_status == "Healthy":
    print("Deployment is ready.")
else:
    print("Deployment is still in progress.")

Model compilation initiated: llama-3.2-1b-instruct-SDK | uuid=e079d5f9-9fa9-4664-82ce-0218b7d1c220 | status=PENDING | source=meta-llama/Llama-3.2-1B-Instruct
Model Repo e079d5f9-9fa9-4664-82ce-0218b7d1c220: PENDING
Model Repo e079d5f9-9fa9-4664-82ce-0218b7d1c220: LAUNCHING_RAY_CLUSTER
Model Repo e079d5f9-9fa9-4664-82ce-0218b7d1c220: OPTIMISING
Model Repo e079d5f9-9fa9-4664-82ce-0218b7d1c220: SUCCESS
Deployment created: id=0ee77f95-a49a-4965-9aa9-311fa9318c47 
 Name=llama-3.2-1b-instruct-SDK 
 Model Endpoint=https://YOUR-ENDPOINT.HERE
Status: DEPLOYING
Health: Progressing — The deployment is progressing. Please wait for the application to be healthy.
Deployment is still in progress.

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.'}