Azure AI Foundry Agents

Azure AI Foundry Agents

Azure AI Foundry Agents를 OpenAI Request/Response 포맷으로 호출하는 방법을 알려드릴게요. LiteLLM을 쓰면 에이전트를 표준 completion 인터페이스로 사용할 수 있어요.

출처: 문서

본문

인증

옵션 1: Service Principal (프로덕션에 권장)

export AZURE_TENANT_ID="your-tenant-id"
export AZURE_CLIENT_ID="your-client-id"
export AZURE_CLIENT_SECRET="your-client-secret"

옵션 2: Azure AD 토큰 (수동)

# Get token via Azure CLI
az account get-access-token --resource "https://ai.azure.com" --query accessToken -o tsv

필요한 Azure 역할

az role assignment create \
  --assignee-object-id "<service-principal-object-id>" \
  --assignee-principal-type "ServicePrincipal" \
  --role "Azure AI Developer" \
  --scope "/subscriptions/<sub>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<resource>"

빠른 시작

LiteLLM 모델 포맷

azure_ai/agents/{AGENT_ID}
  • azure_ai/agents/asst_abc123

LiteLLM Python SDK

import litellm

# Make a completion request to your Azure AI Foundry Agent
# Uses AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET env vars for auth
response = litellm.completion(
    model="azure_ai/agents/asst_abc123",
    messages=[
        {
            "role": "user", 
            "content": "Explain machine learning in simple terms"
        }
    ],
    api_base="https://your-resource.services.ai.azure.com/api/projects/your-project",
)

print(response.choices[0].message.content)
print(f"Usage: {response.usage}")

import litellm

# Stream responses from your Azure AI Foundry Agent
response = await litellm.acompletion(
    model="azure_ai/agents/asst_abc123",
    messages=[
        {
            "role": "user",
            "content": "What are the key principles of software architecture?"
        }
    ],
    api_base="https://your-resource.services.ai.azure.com/api/projects/your-project",
    stream=True,
)

async for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

LiteLLM Proxy

1. config.yaml에 모델 설정

model_list:
  - model_name: azure-agent-1
    litellm_params:
      model: azure_ai/agents/asst_abc123
      api_base: https://your-resource.services.ai.azure.com/api/projects/your-project
      # Service Principal auth (recommended)
      tenant_id: os.environ/AZURE_TENANT_ID
      client_id: os.environ/AZURE_CLIENT_ID
      client_secret: os.environ/AZURE_CLIENT_SECRET

  - model_name: azure-agent-math-tutor
    litellm_params:
      model: azure_ai/agents/asst_def456
      api_base: https://your-resource.services.ai.azure.com/api/projects/your-project
      # Or pass Azure AD token directly
      api_key: os.environ/AZURE_AD_TOKEN

2. LiteLLM Proxy 시작

litellm --config config.yaml

3. Azure AI Foundry Agents로 요청 보내기

curl http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ***" \
  -d '{
    "model": "azure-agent-1",
    "messages": [
      {
        "role": "user", 
        "content": "Summarize the main benefits of cloud computing"
      }
    ]
  }'

curl http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ***" \
  -d '{
    "model": "azure-agent-math-tutor",
    "messages": [
      {
        "role": "user",
        "content": "What is 25 * 4?"
      }
    ],
    "stream": true
  }'

from openai import OpenAI

# Initialize client with your LiteLLM proxy URL
client = OpenAI(
    base_url="http://localhost:4000",
    api_key="your-litellm-api-key"
)

# Make a completion request to your Azure AI Foundry Agent
response = client.chat.completions.create(
    model="azure-agent-1",
    messages=[
      {
        "role": "user",
        "content": "What are best practices for API design?"
      }
    ]
)

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

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:4000", 
    api_key="your-litellm-api-key"
)

# Stream Agent responses
stream = client.chat.completions.create(
    model="azure-agent-math-tutor",
    messages=[
      {
        "role": "user",
        "content": "Explain the Pythagorean theorem"
      }
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

환경 변수

export AZURE_TENANT_ID="your-tenant-id"
export AZURE_CLIENT_ID="your-client-id"
export AZURE_CLIENT_SECRET="your-client-secret"

대화 연속성 (스레드 관리)

import litellm

# First message creates a new thread
response1 = await litellm.acompletion(
    model="azure_ai/agents/asst_abc123",
    messages=[{"role": "user", "content": "My name is Alice"}],
    api_base="https://your-resource.services.ai.azure.com/api/projects/your-project",
)

# Get the thread_id from the response
thread_id = response1._hidden_params.get("thread_id")

# Continue the conversation using the same thread
response2 = await litellm.acompletion(
    model="azure_ai/agents/asst_abc123",
    messages=[{"role": "user", "content": "What's my name?"}],
    api_base="https://your-resource.services.ai.azure.com/api/projects/your-project",
    thread_id=thread_id,  # Pass the thread_id to continue conversation
)

print(response2.choices[0].message.content)  # Should mention "Alice"

공급업체별 파라미터

from litellm import completion

response = litellm.completion(
    model="azure_ai/agents/asst_abc123",
    messages=[
        {
            "role": "user",
            "content": "Analyze this data and provide insights",
        }
    ],
    api_base="https://your-resource.services.ai.azure.com/api/projects/your-project",
    thread_id="thread_abc123",  # Optional: Continue existing conversation
    instructions="Be concise and focus on key insights",  # Optional: Override agent instructions
)

model_list:
  - model_name: azure-agent-analyst
    litellm_params:
      model: azure_ai/agents/asst_abc123
      api_base: https://your-resource.services.ai.azure.com/api/projects/your-project
      tenant_id: os.environ/AZURE_TENANT_ID
      client_id: os.environ/AZURE_CLIENT_ID
      client_secret: os.environ/AZURE_CLIENT_SECRET
      instructions: "Be concise and focus on key insights"

사용 가능한 파라미터

thread_id와 instructions를 선택적으로 전달할 수 있어요.

LiteLLM A2A Gateway

1. Agents로 이동하기

2. Azure AI Foundry Agent 유형 선택하기

3. 에이전트 설정하기

에이전트 이름 (Agent Name)

에이전트 ID (Agent ID)

  • https://ai.azure.com/ 에 접속해 "Agents"를 클릭해요
  • 추가하려는 에이전트의 "ID"를 복사해요 (예: asst_hbnoK9BOCcHhC3lC4MDroVGG)
  • LiteLLM에 Agent ID를 붙여 넣어요 - LiteLLM이 Azure Foundry에서 어떤 에이전트를 호출할지 알게 돼요

Azure AI API Base

  • https://ai.azure.com/ 에 접속해 "Overview"를 클릭해요
  • 라이브러리에서 Microsoft Foundry를 선택해요
  • 엔드포인트를 얻으면 https://<domain>.services.ai.azure.com/api/projects/<project-name> 형태예요
  • LiteLLM에 URL을 붙여 넣어요

인증

  • Azure Tenant ID
  • Azure Client ID
  • Azure Client Secret

4. Playground에서 테스트하기

5. 에이전트를 선택하고 메시지 보내기

추가 자료

  • Azure AI Foundry Agents Documentation
  • Create Thread and Run API Reference
  • A2A Agent Gateway
  • A2A Cost Tracking

A2A를 통한 Foundry 에이전트

agents:
  - agent_name: foundry-agent
    agent_card_params:
      name: "Foundry Agent"
      url: "https://<account>.services.ai.azure.com/api/projects/<project>/agents/<agent>/endpoint/protocols/a2a"
      protocolVersion: "1.0"
      capabilities:
        streaming: false
    litellm_params:
      agent_card_path: agentCard/v1.0
      tenant_id: os.environ/AZURE_TENANT_ID
      client_id: os.environ/AZURE_CLIENT_ID
      client_secret: os.environ/AZURE_CLIENT_SECRET

curl http://localhost:4000/a2a/foundry-agent \
  -H "Authorization: Bearer $LITEL..._KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": "1",
    "method": "message/send",
    "params": {
      "message": {
        "kind": "message",
        "role": "user",
        "messageId": "m1",
        "parts": [{"kind": "text", "text": "What is 2 + 2?"}]
      },
      "configuration": {"blocking": true}
    }
  }'

curl http://localhost:4000/v1/chat/completions \
  -H "Authorization: Bearer $LITEL..._KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "a2a/foundry-agent", "messages": [{"role": "user", "content": "What is 2 + 2?"}]}'

더 알아보기 (Learn more)