部署经过微调的模型进行推理

若要部署自定义模型，请选择要部署的自定义模型，然后选择“ 部署”。

此时会打开“部署模型”对话框。 在该对话框中，输入部署名称，然后选择“创建”，开始部署自定义模型。

可在 Azure AI Foundry 门户的“部署”窗格中监视部署进度。

UI 不支持跨区域部署，而 Python SDK 或 REST 支持。

import json
import os
import requests

token = os.getenv("<TOKEN>") 
subscription = "<YOUR_SUBSCRIPTION_ID>"  
resource_group = "<YOUR_RESOURCE_GROUP_NAME>"
resource_name = "<YOUR_AZURE_OPENAI_RESOURCE_NAME>"
model_deployment_name = "gpt-35-turbo-ft" # custom deployment name that you will use to reference the model when making inference calls.

deploy_params = {'api-version': "2024-10-21"} 
deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}

deploy_data = {
    "sku": {"name": "standard", "capacity": 1}, 
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": <"fine_tuned_model">, #retrieve this value from the previous call, it will look like gpt-35-turbo-0125.ft-b044a9d3cf9c4228b5d393567f693b83
            "version": "1"
        }
    }
}
deploy_data = json.dumps(deploy_data)

request_url = f'https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}'

print('Creating a new deployment...')

r = requests.put(request_url, params=deploy_params, headers=deploy_headers, data=deploy_data)

print(r)
print(r.reason)
print(r.json())

跨区域部署

微调支持将微调后的模型部署到与模型最初进行微调时所在的区域不同的区域。 还可以部署到其他订阅/区域。

唯一的限制是新区域还必须支持微调，并且在部署交叉订阅时为部署生成授权令牌的帐户必须有权访问源订阅和目标订阅。

下面是一个示例，说明了如何将已在一个订阅/区域中微调的模型部署到另一个订阅/区域。

import json
import os
import requests

token= os.getenv("<TOKEN>") 

subscription = "<DESTINATION_SUBSCRIPTION_ID>"  
resource_group = "<DESTINATION_RESOURCE_GROUP_NAME>"
resource_name = "<DESTINATION_AZURE_OPENAI_RESOURCE_NAME>"

source_subscription = "<SOURCE_SUBSCRIPTION_ID>"
source_resource_group = "<SOURCE_RESOURCE_GROUP>"
source_resource = "<SOURCE_RESOURCE>"


source = f'/subscriptions/{source_subscription}/resourceGroups/{source_resource_group}/providers/Microsoft.CognitiveServices/accounts/{source_resource}'

model_deployment_name = "gpt-35-turbo-ft" # custom deployment name that you will use to reference the model when making inference calls.

deploy_params = {'api-version': "2024-10-21"} 
deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}



deploy_data = {
    "sku": {"name": "standard", "capacity": 1}, 
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": <"FINE_TUNED_MODEL_NAME">, # This value will look like gpt-35-turbo-0125.ft-0ab3f80e4f2242929258fff45b56a9ce 
            "version": "1",
            "source": source
        }
    }
}
deploy_data = json.dumps(deploy_data)

request_url = f'https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}'

print('Creating a new deployment...')

r = requests.put(request_url, params=deploy_params, headers=deploy_headers, data=deploy_data)

print(r)
print(r.reason)
print(r.json())

若要在同一订阅但不同区域之间进行部署，只需让源变量和目标变量的订阅和资源组相同，并且仅源资源名称和目标资源名称需要独一无二。

跨租户部署

用 az account get-access-token --tenant 生成访问令牌的帐户应具有对源和目标 Azure OpenAI 资源的认知服务 OpenAI 参与者权限。 需要生成两个不同的令牌，一个用于源租户，一个用于目标租户。

import requests

subscription = "DESTINATION-SUBSCRIPTION-ID"
resource_group = "DESTINATION-RESOURCE-GROUP"
resource_name = "DESTINATION-AZURE-OPENAI-RESOURCE-NAME"
model_deployment_name = "DESTINATION-MODEL-DEPLOYMENT-NAME"
fine_tuned_model = "gpt-4o-mini-2024-07-18.ft-f8838e7c6d4a4cbe882a002815758510" #source fine-tuned model id example id provided
source_subscription_id = "SOURCE-SUBSCRIPTION-ID"
source_resource_group = "SOURCE-RESOURCE-GROUP" 
source_account = "SOURCE-AZURE-OPENAI-RESOURCE-NAME"

dest_token = "DESTINATION-ACCESS-TOKEN" # az account get-access-token --tenant DESTINATION-TENANT-ID
source_token = "SOURCE-ACCESS-TOKEN"  # az account get-access-token --tenant SOURCE-TENANT-ID

headers = {
    "Authorization": f"Bearer {dest_token}", 
    "x-ms-authorization-auxiliary": f"Bearer {source_token}", 
    "Content-Type": "application/json"
}

url = f"https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}?api-version=2024-10-01"

payload = {
    "sku": {
        "name": "standard",
        "capacity": 1
    },
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": fine_tuned_model,
            "version": "1",
            "sourceAccount": f"/subscriptions/{source_subscription_id}/resourceGroups/{source_resource_group}/providers/Microsoft.CognitiveServices/accounts/{source_account}"
        }
    }
}

response = requests.put(url, headers=headers, json=payload)

# Check response
print(f"Status Code: {response.status_code}")
print(f"Response: {response.json()}")

以下示例演示如何使用 REST API 为自定义模型创建模型部署。 REST API 为自定义模型的部署生成名称。

curl -X POST "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>?api-version=2024-10-21" \
  -H "Authorization: Bearer <TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{
    "sku": {"name": "standard", "capacity": 1},
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": "<FINE_TUNED_MODEL>",
            "version": "1"
        }
    }
}'

跨区域部署

微调支持将微调后的模型部署到与模型最初进行微调时所在的区域不同的区域。 还可以部署到其他订阅/区域。

唯一的限制是新区域还必须支持微调，并且在部署交叉订阅时为部署生成授权令牌的帐户必须有权访问源订阅和目标订阅。

下面是一个示例，说明了如何将已在一个订阅/区域中微调的模型部署到另一个订阅/区域。

curl -X PUT "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>?api-version=2024-10-21" \
  -H "Authorization: Bearer <TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{
    "sku": {"name": "standard", "capacity": 1},
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": "<FINE_TUNED_MODEL>", 
            "version": "1",
            "source": "/subscriptions/{sourceSubscriptionID}/resourceGroups/{sourceResourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{sourceAccount}" 
        }
    }
}'

若要在同一订阅但不同区域之间进行部署，只需让源变量和目标变量的订阅和资源组相同，并且仅源资源名称和目标资源名称需要独一无二。

跨租户部署

用 az account get-access-token --tenant 生成访问令牌的帐户应具有对源和目标 Azure OpenAI 资源的认知服务 OpenAI 参与者权限。 需要生成两个不同的令牌，一个用于源租户，一个用于目标租户。

curl -X PUT "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>?api-version=2024-10-01" \
  -H "Authorization: Bearer <DESTINATION TOKEN>" \
  -H "x-ms-authorization-auxiliary: Bearer <SOURCE TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{
    "sku": {"name": "standard", "capacity": 1},
    "properties": {
        "model": {
            "format": "OpenAI",
            "name": "<FINE_TUNED_MODEL>", 
            "version": "1",
            "sourceAccount": "/subscriptions/{sourceSubscriptionID}/resourceGroups/{sourceResourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{sourceAccount}" 
        }
    }
}'

以下示例演示如何使用 Azure CLI 部署自定义模型。 使用 Azure CLI 时，必须为自定义模型的部署指定名称。 有关使用 Azure CLI 部署自定义模型的详细信息，请参阅 az cognitiveservices account deployment。

若要在控制台窗口中运行此 Azure CLI 命令，必须将以下 <>占位符 替换为自定义模型的相应值：

az cognitiveservices account deployment create 
    --resource-group <YOUR_RESOURCE_GROUP>
    --name <YOUR_RESOURCE_NAME>  
    --deployment-name <YOUR_DEPLOYMENT_NAME>
    --model-name <YOUR_FINE_TUNED_MODEL_ID>
    --model-version "1" 
    --model-format OpenAI 
    --sku-capacity "1" 
    --sku-name "Standard"

部署自定义模型后，可像使用任何其他已部署的模型一样使用它。 可以使用 Azure AI Foundry 门户中的 Playgrounds 来试验新部署。 可以继续对自定义模型使用相同的参数，例如 temperature 和 max_tokens，就像对其他已部署的模型一样。

import os
from openai import AzureOpenAI

client = AzureOpenAI(
  azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
  api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
  api_version="2024-02-01"
)

response = client.chat.completions.create(
    model="gpt-35-turbo-ft", # model = "Custom deployment name you chose for your fine-tuning model"
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},
        {"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},
        {"role": "user", "content": "Do other Azure services support this too?"}
    ]
)

print(response.choices[0].message.content)

curl $AZURE_OPENAI_ENDPOINT/openai/deployments/<deployment_name>/chat/completions?api-version=2024-10-21 \
  -H "Content-Type: application/json" \
  -H "api-key: $AZURE_OPENAI_API_KEY" \
  -d '{"messages":[{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},{"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},{"role": "user", "content": "Do other Azure services support this too?"}]}'

Azure CLI 仅适用于控制平面作，例如资源创建和 模型部署。 对于推理操作，请使用 REST API 或 语言 SDK。