SageMaker Qwen을 AgentCore에 연결하는 법

region = "us-west-2"
model_id = "Qwen/Qwen3.5-9B"
instance_type = "ml.g6e.2xlarge" # 1x L40S (48GB VRAM)
num_gpu = 1 # vLLM 0.22.1, Python 3.12, CUDA 13.0, Ubuntu 22.04
inference_image = f"763104351884.dkr.ecr.{region}.amazonaws.com/vllm:0.22.1-gpu-py312-cu130-ubuntu22.04-sagemaker"
env = {
    "SM_VLLM_MODEL": model_id,
    "SM_VLLM_TENSOR_PARALLEL_SIZE": "1",
    "SM_VLLM_MAX_MODEL_LEN": "32768",
}
# Create Model
sm.create_model(
    ModelName=model_name,
    ExecutionRoleArn=role,
    PrimaryContainer={"Image": inference_image, "Environment": env},
)
# Create Endpoint Config + Endpoint
sm.create_endpoint_config(
    EndpointConfigName=endpoint_config_name,
    ProductionVariants=[{
        "VariantName": "v1",
        "ModelName": model_name,
        "InstanceType": instance_type,
        "InitialInstanceCount": 1,
        "ContainerStartupHealthCheckTimeoutInSeconds": 1200,
        "InferenceAmiVersion": inference_ami_version,
    }],
)
sm.create_endpoint(EndpointName=endpoint_name, EndpointConfigName=endpoint_config_name)

import httpx
from openai import AsyncOpenAI
from sagemaker.core.token_generator import generate_token

class SageMakerAuth(httpx.Auth):
    def __init__(self, region):
        self.region = region
    def auth_flow(self, request):
        request.headers["Authorization"] = f"Bearer {generate_token(region=self.region)}"
        yield request

strands_client = AsyncOpenAI(
    base_url=f"https://runtime.sagemaker.{REGION}.amazonaws.com/endpoints/{ENDPOINT_NAME}/openai/v1",
    api_key="sagemaker",
    http_client=httpx.AsyncClient(auth=SageMakerAuth(region=REGION)),
)

qwen_model = OpenAIModel(
    client=strands_client,
    model_id="",
    params={"temperature": 0.7, "max_tokens": 4096, "stream_options": {"include_usage": True}},
)

with tracer.start_as_current_span("gen_ai.chat", attributes={
    "gen_ai.system": "openai",
    "gen_ai.request.model": f"qwen3.5-9b ({SAGEMAKER_ENDPOINT_NAME})",
    "gen_ai.operation.name": "chat",
}) as span:
    fa_agent = Agent(
        model=OpenAIModel(
            client=strands_client,
            model_id="",
            params={"temperature": 0.7, "max_tokens": 4096, "stream_options": {"include_usage": True}},
        ),
        system_prompt=FINANCIAL_ANALYSIS_PROMPT,
        tools=[get_stock_analysis, create_diversified_portfolio, compare_stock_performance],
        callback_handler=None,
    )
    result = fa_agent(query)
    # Extract token usage from Strands agent metrics
    usage = result.metrics.accumulated_usage
    span.set_attribute("gen_ai.usage.input_tokens", usage.get("inputTokens", 0))
    span.set_attribute("gen_ai.usage.output_tokens", usage.get("outputTokens", 0))
    span.set_attribute("gen_ai.usage.total_tokens", usage.get("totalTokens", 0))
    return str(result)