Memulai

Panduan ini menunjukkan cara menerapkan model Amazon Nova yang disesuaikan pada titik akhir SageMaker waktu nyata, mengonfigurasi parameter inferensi, dan memanggil model Anda untuk pengujian.

Prasyarat

Berikut ini adalah prasyarat untuk menerapkan model Amazon Nova pada inferensi: SageMaker

Langkah 1: Konfigurasikan AWS kredensil

Konfigurasikan AWS kredensyal Anda menggunakan salah satu metode berikut:

Opsi 1: AWS CLI (Direkomendasikan)

aws configure

Masukkan kunci AWS akses, kunci rahasia, dan wilayah default Anda saat diminta.

Opsi 2: file AWS kredensial

Buat atau edit~/.aws/credentials:

[default]
aws_access_key_id = YOUR_ACCESS_KEY
aws_secret_access_key = YOUR_SECRET_KEY

Opsi 3: Variabel lingkungan

export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key

Inisialisasi klien AWS

Buat skrip atau buku catatan Python dengan kode berikut untuk menginisialisasi AWS SDK dan memverifikasi kredensil Anda:

import boto3

# AWS Configuration - Update these for your environment
REGION = "us-east-1"  # Supported regions: us-east-1, us-west-2
AWS_ACCOUNT_ID = "YOUR_ACCOUNT_ID"  # Replace with your AWS account ID

# Initialize AWS clients using default credential chain
sagemaker = boto3.client('sagemaker', region_name=REGION)
sts = boto3.client('sts')

# Verify credentials
try:
    identity = sts.get_caller_identity()
    print(f"Successfully authenticated to AWS Account: {identity['Account']}")
    
    if identity['Account'] != AWS_ACCOUNT_ID:
        print(f"Warning: Connected to account {identity['Account']}, expected {AWS_ACCOUNT_ID}")

except Exception as e:
    print(f"Failed to authenticate: {e}")
    print("Please verify your credentials are configured correctly.")

Jika otentikasi berhasil, Anda akan melihat output yang mengonfirmasi ID AWS akun Anda.

Langkah 2: Buat peran SageMaker eksekusi

Peran SageMaker eksekusi adalah peran IAM yang memberikan SageMaker izin untuk mengakses AWS sumber daya atas nama Anda, seperti bucket Amazon S3 untuk artefak model dan untuk pencatatan. CloudWatch

Menciptakan peran eksekusi

Kode berikut membuat peran IAM dengan izin yang diperlukan untuk menerapkan model khusus Amazon Nova:

import json

# Create SageMaker Execution Role
role_name = f"SageMakerInference-ExecutionRole-{AWS_ACCOUNT_ID}"

trust_policy = {
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Principal": {"Service": "sagemaker.amazonaws.com"},
            "Action": "sts:AssumeRole"
        }
    ]
}

iam = boto3.client('iam', region_name=REGION)

# Create the role
role_response = iam.create_role(
    RoleName=role_name,
    AssumeRolePolicyDocument=json.dumps(trust_policy),
    Description='SageMaker execution role with S3 and SageMaker access'
)

# Attach required policies
iam.attach_role_policy(
    RoleName=role_name,
    PolicyArn='arn:aws:iam::aws:policy/AmazonSageMakerFullAccess'
)

iam.attach_role_policy(
    RoleName=role_name,
    PolicyArn='arn:aws:iam::aws:policy/AmazonS3FullAccess'
)

SAGEMAKER_EXECUTION_ROLE_ARN = role_response['Role']['Arn']
print(f"Created SageMaker execution role: {SAGEMAKER_EXECUTION_ROLE_ARN}")

Menggunakan peran eksekusi yang ada (Opsional)

Jika Anda sudah memiliki peran SageMaker eksekusi, Anda dapat menggunakannya sebagai gantinya:

# Replace with your existing role ARN
SAGEMAKER_EXECUTION_ROLE_ARN = "arn:aws:iam::YOUR_ACCOUNT_ID:role/YOUR_EXISTING_ROLE_NAME"

Untuk menemukan SageMaker peran yang ada di akun Anda:

iam = boto3.client('iam', region_name=REGION)
response = iam.list_roles()
sagemaker_roles = [role for role in response['Roles'] if 'SageMaker' in role['RoleName']]
for role in sagemaker_roles:
    print(f"{role['RoleName']}: {role['Arn']}")

Untuk informasi selengkapnya tentang peran SageMaker eksekusi, lihat SageMaker Peran.

Langkah 3: Konfigurasikan parameter model

Konfigurasikan parameter penerapan untuk model Amazon Nova Anda. Pengaturan ini mengontrol perilaku model, alokasi sumber daya, dan karakteristik inferensi. Untuk daftar jenis instance yang didukung dan nilai CONTEXT_LENGTH dan MAX_CONCURRENCY yang didukung untuk masing-masing, lihat. Model dan instance yang didukung Untuk daftar lengkap fitur kontainer tambahan seperti default pengambilan sampel, decoding spekulatif, dan kuantisasi, lihat. Fitur Kontainer Inferensi

Parameter yang diperlukan

Konfigurasikan penerapan Anda

# AWS Configuration
REGION = "us-east-1"  # Must match region from Step 1

# ECR Account mapping by region
ECR_ACCOUNT_MAP = {
    "us-east-1": "708977205387",
    "us-west-2": "176779409107"
}

# Container Image
IMAGE = f"{ECR_ACCOUNT_MAP[REGION]}.dkr.ecr.{REGION}.amazonaws.com/nova-inference-repo:SM-Inference-latest"
print(f"IMAGE = {IMAGE}")

# Required parameters
CONTEXT_LENGTH = "8000"        # Maximum total context length
MAX_CONCURRENCY = "8"          # Maximum concurrent sequences

# Build environment variables for the container
environment = {
    'CONTEXT_LENGTH': CONTEXT_LENGTH,
    'MAX_CONCURRENCY': MAX_CONCURRENCY,
    # Optional: add container feature environment variables here.
    # See "Inference Container Features" for the full list.
    # Examples:
    # 'DEFAULT_TEMPERATURE': '0.7',
    # 'DEFAULT_MAX_NEW_TOKENS': '512',
    # 'QUANTIZATION_DTYPE': 'fp8',
}

print("Environment configuration:")
for key, value in environment.items():
    print(f"  {key}: {value}")

Konfigurasikan parameter khusus penerapan

Sekarang konfigurasikan parameter spesifik untuk penerapan model Amazon Nova Anda, termasuk lokasi artefak model dan pemilihan jenis instans.

Tetapkan pengenal penerapan

# Deployment identifier - use a descriptive name for your use case
JOB_NAME = "my-nova-deployment"

Tentukan lokasi artefak model

Sediakan URI Amazon S3 tempat artefak model Amazon Nova terlatih Anda disimpan. Ini harus menjadi lokasi keluaran dari pelatihan model atau pekerjaan fine-tuning Anda.

# S3 location of your trained Nova model artifacts
# Replace with your model's S3 URI - must end with /
MODEL_S3_LOCATION = "s3://your-bucket-name/path/to/model/artifacts/"

Pilih varian model dan tipe instance

# Configure model variant and instance type
TESTCASE = {
    "model": "micro",              # Options: micro, lite, lite2
    "instance": "ml.g5.12xlarge"   # Refer to "Supported models and instances" section
}

# Generate resource names
INSTANCE_TYPE = TESTCASE["instance"]
MODEL_NAME = JOB_NAME + "-" + TESTCASE["model"] + "-" + INSTANCE_TYPE.replace(".", "-")
ENDPOINT_CONFIG_NAME = MODEL_NAME + "-Config"
ENDPOINT_NAME = MODEL_NAME + "-Endpoint"

print(f"Model Name: {MODEL_NAME}")
print(f"Endpoint Config: {ENDPOINT_CONFIG_NAME}")
print(f"Endpoint Name: {ENDPOINT_NAME}")

Konvensi penamaan

Kode secara otomatis menghasilkan nama yang konsisten untuk AWS sumber daya:

Langkah 4: Buat SageMaker sumber daya dan gunakan titik akhir

SageMaker menawarkan dua pendekatan untuk menerapkan model ke titik akhir waktu nyata. Pilih pendekatan yang sesuai dengan kasus penggunaan Anda:

Opsi A: Membuat dengan komponen inferensi

Dengan komponen inferensi, pertama-tama Anda membuat titik akhir, lalu menerapkan model Anda sebagai komponen inferensi pada titik akhir tersebut. Ini memisahkan model dari infrastruktur titik akhir, memberi Anda lebih banyak fleksibilitas.

Buat konfigurasi titik akhir

Buat konfigurasi endpoint yang mendefinisikan infrastruktur tanpa menentukan model. Jenis dan hitungan instans dikelola pada tingkat titik akhir:

# Create Endpoint Configuration for inference components
INFERENCE_COMPONENT_NAME = MODEL_NAME + "-IC"

try:
    config_response = sagemaker.create_endpoint_config(
        EndpointConfigName=ENDPOINT_CONFIG_NAME,
        ProductionVariants=[
            {
                'VariantName': 'primary',
                'InstanceType': INSTANCE_TYPE,
                'InitialInstanceCount': 1,
                'RoutingConfig': {
                    'RoutingStrategy': 'LEAST_OUTSTANDING_REQUESTS'
                }
            }
        ],
        Tags=[
            {
                'Key': 'sagemaker:nova-inference-component',
                'Value': 'true'
            }
        ]
    )
    print("Endpoint configuration created successfully!")
    print(f"Config ARN: {config_response['EndpointConfigArn']}")

except sagemaker.exceptions.ClientError as e:
    print(f"Error creating endpoint configuration: {e}")

Buat dan terapkan titik akhir

import time

try:
    endpoint_response = sagemaker.create_endpoint(
        EndpointName=ENDPOINT_NAME,
        EndpointConfigName=ENDPOINT_CONFIG_NAME
    )
    print("Endpoint creation initiated successfully!")
    print(f"Endpoint ARN: {endpoint_response['EndpointArn']}")
except Exception as e:
    print(f"Error creating endpoint: {e}")

# Wait for endpoint to be InService
print("Waiting for endpoint to be InService...")
print("This typically takes 5-10 minutes...\n")

while True:
    try:
        response = sagemaker.describe_endpoint(EndpointName=ENDPOINT_NAME)
        status = response['EndpointStatus']
        
        if status == 'Creating':
            print(f"⏳ Status: {status} - Provisioning infrastructure...")
        elif status == 'InService':
            print(f"✅ Status: {status}")
            print(f"\nEndpoint '{ENDPOINT_NAME}' is ready.")
            break
        elif status == 'Failed':
            print(f"❌ Status: {status}")
            print(f"Failure Reason: {response.get('FailureReason', 'Unknown')}")
            break
        else:
            print(f"Status: {status}")
    except Exception as e:
        print(f"Error checking endpoint status: {e}")
        break
    
    time.sleep(30)

Buat komponen inferensi

Setelah titik akhir InService, terapkan model Amazon Nova Anda sebagai komponen inferensi:

try:
    ic_response = sagemaker.create_inference_component(
        InferenceComponentName=INFERENCE_COMPONENT_NAME,
        EndpointName=ENDPOINT_NAME,
        VariantName='primary',
        Specification={
            'Container': {
                'Image': IMAGE,
                'ArtifactUrl': MODEL_S3_LOCATION,
                'Environment': environment
            },
            'ComputeResourceRequirements': {
                'NumberOfCpuCoresRequired': 15,
                'NumberOfAcceleratorDevicesRequired': 4,
                'MinMemoryRequiredInMb': 25000
            }
        },
        RuntimeConfig={
            'CopyCount': 1
        }
    )
    print("Inference component creation initiated!")
    print(f"Inference Component ARN: {ic_response['InferenceComponentArn']}")

except sagemaker.exceptions.ClientError as e:
    print(f"Error creating inference component: {e}")

Parameter kunci:

Memantau penyebaran komponen inferensi

# Wait for inference component to be InService
print("Waiting for inference component deployment...")
print("This typically takes 10-20 minutes as the model is loaded...\n")

while True:
    try:
        ic_desc = sagemaker.describe_inference_component(
            InferenceComponentName=INFERENCE_COMPONENT_NAME
        )
        ic_status = ic_desc['InferenceComponentStatus']
        
        if ic_status == 'Creating':
            print(f"⏳ Status: {ic_status} - Loading model artifacts...")
        elif ic_status == 'InService':
            print(f"✅ Status: {ic_status}")
            print(f"\nInference component '{INFERENCE_COMPONENT_NAME}' is ready!")
            break
        elif ic_status == 'Failed':
            print(f"❌ Status: {ic_status}")
            print(f"Failure Reason: {ic_desc.get('FailureReason', 'Unknown')}")
            break
        else:
            print(f"Status: {ic_status}")
    except Exception as e:
        print(f"Error checking inference component status: {e}")
        break
    
    time.sleep(30)

Opsi B: Membuat dengan titik akhir model tunggal

Dengan titik akhir model tunggal, Anda membuat objek SageMaker model, konfigurasi titik akhir, dan kemudian menerapkan titik akhir. Pendekatan ini mengemas model langsung ke konfigurasi titik akhir.

Buat SageMaker model

Kode berikut membuat SageMaker model yang mereferensikan artefak model Amazon Nova Anda:

try:
    model_response = sagemaker.create_model(
        ModelName=MODEL_NAME,
        PrimaryContainer={
            'Image': IMAGE,
            'ModelDataSource': {
                'S3DataSource': {
                    'S3Uri': MODEL_S3_LOCATION,
                    'S3DataType': 'S3Prefix',
                    'CompressionType': 'None'
                }
            },
            'Environment': environment
        },
        ExecutionRoleArn=SAGEMAKER_EXECUTION_ROLE_ARN,
        EnableNetworkIsolation=True
    )
    print("Model created successfully!")
    print(f"Model ARN: {model_response['ModelArn']}")
    
except sagemaker.exceptions.ClientError as e:
    print(f"Error creating model: {e}")

Parameter kunci:

Buat konfigurasi titik akhir

Selanjutnya, buat konfigurasi titik akhir yang mendefinisikan infrastruktur penerapan Anda:

# Create Endpoint Configuration
try:
    production_variant = {
        'VariantName': 'primary',
        'ModelName': MODEL_NAME,
        'InitialInstanceCount': 1,
        'InstanceType': INSTANCE_TYPE,
    }
    
    config_response = sagemaker.create_endpoint_config(
        EndpointConfigName=ENDPOINT_CONFIG_NAME,
        ProductionVariants=[production_variant]
    )
    print("Endpoint configuration created successfully!")
    print(f"Config ARN: {config_response['EndpointConfigArn']}")
    
except sagemaker.exceptions.ClientError as e:
    print(f"Error creating endpoint configuration: {e}")

Parameter kunci:

Terapkan titik akhir

import time

try:
    endpoint_response = sagemaker.create_endpoint(
        EndpointName=ENDPOINT_NAME,
        EndpointConfigName=ENDPOINT_CONFIG_NAME
    )
    print("Endpoint creation initiated successfully!")
    print(f"Endpoint ARN: {endpoint_response['EndpointArn']}")
except Exception as e:
    print(f"Error creating endpoint: {e}")

Pantau pembuatan titik akhir

Kode berikut akan melakukan polling status endpoint hingga penerapan selesai:

# Monitor endpoint creation progress
print("Waiting for endpoint creation to complete...")
print("This typically takes 15-30 minutes...\n")

while True:
    try:
        response = sagemaker.describe_endpoint(EndpointName=ENDPOINT_NAME)
        status = response['EndpointStatus']
        
        if status == 'Creating':
            print(f"⏳ Status: {status} - Provisioning infrastructure and loading model...")
        elif status == 'InService':
            print(f"✅ Status: {status}")
            print("\nEndpoint creation completed successfully!")
            print(f"Endpoint Name: {ENDPOINT_NAME}")
            print(f"Endpoint ARN: {response['EndpointArn']}")
            break
        elif status == 'Failed':
            print(f"❌ Status: {status}")
            print(f"Failure Reason: {response.get('FailureReason', 'Unknown')}")
            print("\nFull response:")
            print(response)
            break
        else:
            print(f"Status: {status}")
        
    except Exception as e:
        print(f"Error checking endpoint status: {e}")
        break
    
    time.sleep(30)  # Check every 30 seconds

Verifikasi pembuatan sumber daya

Anda dapat memverifikasi bahwa sumber daya Anda berhasil dibuat:

# Describe the model
model_info = sagemaker.describe_model(ModelName=MODEL_NAME)
print(f"Model Status: {model_info['ModelName']} created")

# Describe the endpoint configuration
config_info = sagemaker.describe_endpoint_config(EndpointConfigName=ENDPOINT_CONFIG_NAME)
print(f"Endpoint Config Status: {config_info['EndpointConfigName']} created")

Verifikasi titik akhir sudah siap

Terlepas dari pendekatan mana yang Anda pilih, Anda dapat memverifikasi konfigurasi titik akhir:

# Get detailed endpoint information
endpoint_info = sagemaker.describe_endpoint(EndpointName=ENDPOINT_NAME)

print("\n=== Endpoint Details ===")
print(f"Endpoint Name: {endpoint_info['EndpointName']}")
print(f"Endpoint ARN: {endpoint_info['EndpointArn']}")
print(f"Status: {endpoint_info['EndpointStatus']}")
print(f"Creation Time: {endpoint_info['CreationTime']}")
print(f"Last Modified: {endpoint_info['LastModifiedTime']}")

# Get endpoint config for instance type details
endpoint_config_name = endpoint_info['EndpointConfigName']
endpoint_config = sagemaker.describe_endpoint_config(EndpointConfigName=endpoint_config_name)

# Display production variant details
for variant in endpoint_info['ProductionVariants']:
    print(f"\nProduction Variant: {variant['VariantName']}")
    print(f"  Current Instance Count: {variant['CurrentInstanceCount']}")
    print(f"  Desired Instance Count: {variant['DesiredInstanceCount']}")
    # Get instance type from endpoint config
    for config_variant in endpoint_config['ProductionVariants']:
        if config_variant['VariantName'] == variant['VariantName']:
            print(f"  Instance Type: {config_variant['InstanceType']}")
            break

Memecahkan masalah kegagalan pembuatan titik akhir

Alasan kegagalan umum:

sagemaker.delete_endpoint(EndpointName=ENDPOINT_NAME)

Langkah 5: Panggil titik akhir

Setelah titik akhir Anda InService, Anda dapat mengirim permintaan inferensi untuk menghasilkan prediksi dari model Amazon Nova Anda. SageMaker mendukung titik akhir sinkron (real-time dengan mode streaming/non -streaming) dan titik akhir asinkron (Amazon untuk pemrosesan batch). S3-based

Siapkan klien runtime

Buat klien SageMaker Runtime dengan pengaturan batas waktu yang sesuai:

import json
import boto3
import botocore
from botocore.exceptions import ClientError

# Configure client with appropriate timeouts
config = botocore.config.Config(
    read_timeout=120,      # Maximum time to wait for response
    connect_timeout=10,    # Maximum time to establish connection
    retries={'max_attempts': 3}  # Number of retry attempts
)

# Create SageMaker Runtime client
runtime_client = boto3.client('sagemaker-runtime', config=config, region_name=REGION)

Buat fungsi inferensi universal

Fungsi berikut menangani permintaan streaming dan non-streaming. Ini menggunakan INFERENCE_COMPONENT_NAME variabel yang didefinisikan dalam Langkah 4. Jika Anda menerapkan menggunakan komponen inferensi (Opsi A), ini disetel ke. MODEL_NAME + "-IC" Jika Anda menerapkan menggunakan titik akhir model tunggal (Opsi B), ini tidak ditentukan, jadi setel ke None sebelum menjalankan langkah ini:

# Only needed if you followed Option B (single model endpoints) in Step 4:
# INFERENCE_COMPONENT_NAME = None

def invoke_nova_endpoint(request_body):
    """
    Invoke Nova endpoint with automatic streaming detection.
    Supports both inference component and single model endpoint deployments.
    
    Args:
        request_body (dict): Request payload containing prompt and parameters
    
    Returns:
        dict: Response from the model (for non-streaming requests)
        None: For streaming requests (prints output directly)
    """
    body = json.dumps(request_body)
    is_streaming = request_body.get("stream", False)
    
    # Build invoke parameters
    invoke_params = {
        'EndpointName': ENDPOINT_NAME,
        'ContentType': 'application/json',
        'Body': body
    }
    
    # Add InferenceComponentName if using inference components
    if INFERENCE_COMPONENT_NAME:
        invoke_params['InferenceComponentName'] = INFERENCE_COMPONENT_NAME
    
    try:
        print(f"Invoking endpoint ({'streaming' if is_streaming else 'non-streaming'})...")
        
        if is_streaming:
            response = runtime_client.invoke_endpoint_with_response_stream(**invoke_params)
            
            event_stream = response['Body']
            for event in event_stream:
                if 'PayloadPart' in event:
                    chunk = event['PayloadPart']
                    if 'Bytes' in chunk:
                        data = chunk['Bytes'].decode()
                        print("Chunk:", data)
        else:
            # Non-streaming inference
            invoke_params['Accept'] = 'application/json'
            response = runtime_client.invoke_endpoint(**invoke_params)
            
            response_body = response['Body'].read().decode('utf-8')
            result = json.loads(response_body)
            print("✅ Response received successfully")
            return result
    
    except ClientError as e:
        error_code = e.response['Error']['Code']
        error_message = e.response['Error']['Message']
        print(f"❌ AWS Error: {error_code} - {error_message}")
    except Exception as e:
        print(f"❌ Unexpected error: {str(e)}")

Contoh 1: penyelesaian Non-streaming obrolan

Gunakan format obrolan untuk interaksi percakapan:

# Non-streaming chat request
chat_request = {
    "messages": [
        {"role": "user", "content": "Hello! How are you?"}
    ],
    "max_tokens": 100,
    "max_completion_tokens": 100,  # Alternative to max_tokens
    "stream": False,
    "temperature": 0.7,
    "top_p": 0.9,
    "top_k": 50,
    "logprobs": True,
    "top_logprobs": 3,
    "allowed_token_ids": None,  # List of allowed token IDs
    "truncate_prompt_tokens": None,  # Truncate prompt to this many tokens
    "stream_options": None
}

response = invoke_nova_endpoint(chat_request)

Sampel respon:

{
    "id": "chatcmpl-123456",
    "object": "chat.completion",
    "created": 1234567890,
    "model": "default",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello! I'm doing well, thank you for asking. I'm here and ready to help you with any questions or tasks you might have. How can I assist you today?"
            },
            "logprobs": {
                "content": [
                    {
                        "token": "Hello",
                        "logprob": -0.123,
                        "top_logprobs": [
                            {"token": "Hello", "logprob": -0.123},
                            {"token": "Hi", "logprob": -2.456},
                            {"token": "Hey", "logprob": -3.789}
                        ]
                    }
                    # Additional tokens...
                ]
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 12,
        "completion_tokens": 28,
        "total_tokens": 40
    }
}

Contoh 2: Penyelesaian teks sederhana

Gunakan format penyelesaian untuk pembuatan teks sederhana:

# Simple completion request
completion_request = {
    "prompt": "The capital of France is",
    "max_tokens": 50,
    "stream": False,
    "temperature": 0.0,
    "top_p": 1.0,
    "top_k": -1,  # -1 means no limit
    "logprobs": 3,  # Number of log probabilities to return
    "allowed_token_ids": None,  # List of allowed token IDs
    "truncate_prompt_tokens": None,  # Truncate prompt to this many tokens
    "stream_options": None
}

response = invoke_nova_endpoint(completion_request)

Sampel respon:

{
    "id": "cmpl-789012",
    "object": "text_completion",
    "created": 1234567890,
    "model": "default",
    "choices": [
        {
            "text": " Paris.",
            "index": 0,
            "logprobs": {
                "tokens": [" Paris", "."],
                "token_logprobs": [-0.001, -0.002],
                "top_logprobs": [
                    {" Paris": -0.001, " London": -5.234, " Rome": -6.789},
                    {".": -0.002, ",": -4.567, "!": -7.890}
                ]
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 6,
        "completion_tokens": 2,
        "total_tokens": 8
    }
}

Contoh 3: Penyelesaian obrolan streaming

# Streaming chat request
streaming_request = {
    "messages": [
        {"role": "user", "content": "Tell me a short story about a robot"}
    ],
    "max_tokens": 200,
    "stream": True,
    "temperature": 0.7,
    "top_p": 0.95,
    "top_k": 40,
    "logprobs": True,
    "top_logprobs": 2,
    "stream_options": {"include_usage": True}
}

invoke_nova_endpoint(streaming_request)

Output streaming sampel:

Chunk: data: {"id":"chatcmpl-029ca032-fa01-4868-80b7-c4cb1af90fb9","object":"chat.completion.chunk","created":1772060532,"model":"default","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}],"prompt_token_ids":null}
Chunk: data: {"id":"chatcmpl-029ca032-fa01-4868-80b7-c4cb1af90fb9","object":"chat.completion.chunk","created":1772060532,"model":"default","choices":[{"index":0,"delta":{"content":" Once"},"logprobs":{"content":[{"token":"\u2581Once","logprob":-0.6078429222106934,"bytes":[226,150,129,79,110,99,101],"top_logprobs":[{"token":"\u2581Once","logprob":-0.6078429222106934,"bytes":[226,150,129,79,110,99,101]},{"token":"\u2581In","logprob":-0.7864127159118652,"bytes":[226,150,129,73,110]}]}]},"finish_reason":null,"token_ids":null}]}
Chunk: data: {"id":"chatcmpl-029ca032-fa01-4868-80b7-c4cb1af90fb9","object":"chat.completion.chunk","created":1772060532,"model":"default","choices":[{"index":0,"delta":{"content":" upon"},"logprobs":{"content":[{"token":"\u2581upon","logprob":-0.0012345,"bytes":[226,150,129,117,112,111,110],"top_logprobs":[{"token":"\u2581upon","logprob":-0.0012345,"bytes":[226,150,129,117,112,111,110]},{"token":"\u2581a","logprob":-6.789,"bytes":[226,150,129,97]}]}]},"finish_reason":null,"token_ids":null}]}
Chunk: data: {"id":"chatcmpl-029ca032-fa01-4868-80b7-c4cb1af90fb9","object":"chat.completion.chunk","created":1772060532,"model":"default","choices":[{"index":0,"delta":{"content":" a"},"logprobs":{"content":[{"token":"\u2581a","logprob":-0.0001234,"bytes":[226,150,129,97],"top_logprobs":[{"token":"\u2581a","logprob":-0.0001234,"bytes":[226,150,129,97]},{"token":"\u2581time","logprob":-9.123,"bytes":[226,150,129,116,105,109,101]}]}]},"finish_reason":null,"token_ids":null}]}
Chunk: data: {"id":"chatcmpl-029ca032-fa01-4868-80b7-c4cb1af90fb9","object":"chat.completion.chunk","created":1772060532,"model":"default","choices":[{"index":0,"delta":{"content":" time"},"logprobs":{"content":[{"token":"\u2581time","logprob":-0.0023456,"bytes":[226,150,129,116,105,109,101],"top_logprobs":[{"token":"\u2581time","logprob":-0.0023456,"bytes":[226,150,129,116,105,109,101]},{"token":",","logprob":-6.012,"bytes":[44]}]}]},"finish_reason":null,"token_ids":null}]}

# Additional chunks...

Chunk: data: {"id":"chatcmpl-029ca032-fa01-4868-80b7-c4cb1af90fb9","object":"chat.completion.chunk","created":1772060532,"model":"default","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":{"prompt_tokens":15,"completion_tokens":87,"total_tokens":102}}
Chunk: data: [DONE]

Contoh 4: Penyelesaian obrolan multimodal

Gunakan format multimodal untuk input gambar dan teks:

# Multimodal chat request (if supported by your model)
multimodal_request = {
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}}
            ]
        }
    ],
    "max_tokens": 150,
    "temperature": 0.3,
    "top_p": 0.8,
    "stream": False
}

response = invoke_nova_endpoint(multimodal_request)

Sampel respon:

{
    "id": "chatcmpl-345678",
    "object": "chat.completion",
    "created": 1234567890,
    "model": "default",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "The image shows..."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 1250,
        "completion_tokens": 45,
        "total_tokens": 1295
    }
}

Langkah 6: Bersihkan sumber daya (Opsional)

Untuk menghindari biaya yang tidak perlu, hapus AWS sumber daya yang Anda buat selama tutorial ini. SageMaker endpoint dikenakan biaya saat sedang berjalan, bahkan jika Anda tidak secara aktif membuat permintaan inferensi.

Inisialisasi klien pembersihan

import boto3
import time

# Initialize SageMaker client
sagemaker = boto3.client('sagemaker', region_name=REGION)

Hapus komponen inferensi (jika menggunakan Opsi A)

Jika Anda menerapkan menggunakan komponen inferensi, hapus komponen inferensi terlebih dahulu sebelum menghapus titik akhir:

# Delete inference component (Option A only)
try:
    print("Deleting inference component...")
    sagemaker.delete_inference_component(InferenceComponentName=INFERENCE_COMPONENT_NAME)
    print(f"✅ Inference component '{INFERENCE_COMPONENT_NAME}' deletion initiated")
except Exception as e:
    print(f"❌ Error deleting inference component: {e}")

# Wait for inference component to be deleted before proceeding
print("Waiting for inference component deletion...")
while True:
    try:
        sagemaker.describe_inference_component(InferenceComponentName=INFERENCE_COMPONENT_NAME)
        time.sleep(10)
    except sagemaker.exceptions.ClientError as e:
        if e.response['Error']['Code'] == 'ValidationException':
            print("✅ Inference component successfully deleted")
            break
        else:
            print(f"Error: {e}")
            break

Hapus titik akhir

try:
    print("Deleting endpoint...")
    sagemaker.delete_endpoint(EndpointName=ENDPOINT_NAME)
    print(f"✅ Endpoint '{ENDPOINT_NAME}' deletion initiated")
    print("Charges will stop once deletion completes (typically 2-5 minutes)")
except Exception as e:
    print(f"❌ Error deleting endpoint: {e}")

import time

print("Monitoring endpoint deletion...")
while True:
    try:
        response = sagemaker.describe_endpoint(EndpointName=ENDPOINT_NAME)
        status = response['EndpointStatus']
        print(f"Status: {status}")
        time.sleep(10)
    except sagemaker.exceptions.ClientError as e:
        if e.response['Error']['Code'] == 'ValidationException':
            print("✅ Endpoint successfully deleted")
            break
        else:
            print(f"Error: {e}")
            break

Hapus konfigurasi titik akhir

Setelah titik akhir dihapus, hapus konfigurasi titik akhir:

try:
    print("Deleting endpoint configuration...")
    sagemaker.delete_endpoint_config(EndpointConfigName=ENDPOINT_CONFIG_NAME)
    print(f"✅ Endpoint configuration '{ENDPOINT_CONFIG_NAME}' deleted")
except Exception as e:
    print(f"❌ Error deleting endpoint configuration: {e}")

Hapus model (Opsi B saja)

Jika Anda menggunakan titik akhir model tunggal, hapus objek SageMaker model:

try:
    print("Deleting model...")
    sagemaker.delete_model(ModelName=MODEL_NAME)
    print(f"✅ Model '{MODEL_NAME}' deleted")
except Exception as e:
    print(f"❌ Error deleting model: {e}")