OpenAI Agents SDK
透過 LiteLLM Proxy 使用 OpenAI Agents SDK 搭配任何 LLM 提供者。
OpenAI Agents SDK 是一個用於建置多代理程式工作流程的輕量型框架。它包含官方的 LiteLLM 擴充功能，讓您可以使用 100+ 個受支援的提供者。
快速開始
1. 安裝相依套件
uv add "openai-agents[litellm]"
2. 將模型加入設定檔
config.yaml
model_list:
- model_name: gpt-4o
litellm_params:
model: "openai/gpt-4o"
api_key: "os.environ/OPENAI_API_KEY"
- model_name: claude-sonnet
litellm_params:
model: "anthropic/claude-3-5-sonnet-20241022"
api_key: "os.environ/ANTHROPIC_API_KEY"
- model_name: gemini-pro
litellm_params:
model: "gemini/gemini-2.0-flash-exp"
api_key: "os.environ/GEMINI_API_KEY"
3. 啟動 LiteLLM Proxy
litellm --config config.yaml
4. 搭配 Proxy 使用
- 透過 Proxy
- 直接使用（不透過 Proxy）
from agents import Agent, Runner
from agents.extensions.models.litellm_model import LitellmModel
# Point to LiteLLM proxy
agent = Agent(
name="Assistant",
instructions="You are a helpful assistant.",
model=LitellmModel(
model="claude-sonnet", # Model from config.yaml
api_key="sk-1234", # LiteLLM API key
base_url="http://localhost:4000"
)
)
result = await Runner.run(agent, "What is LiteLLM?")
print(result.final_output)
from agents import Agent, Runner
from agents.extensions.models.litellm_model import LitellmModel
# Use any provider directly
agent = Agent(
name="Assistant",
instructions="You are a helpful assistant.",
model=LitellmModel(
model="anthropic/claude-3-5-sonnet-20241022",
api_key="your-anthropic-key"
)
)
result = await Runner.run(agent, "What is LiteLLM?")
print(result.final_output)
追蹤用量
啟用用量追蹤以監控 token 消耗：
from agents import Agent, ModelSettings
from agents.extensions.models.litellm_model import LitellmModel
agent = Agent(
name="Assistant",
model=LitellmModel(model="claude-sonnet", api_key="sk-1234"),
model_settings=ModelSettings(include_usage=True)
)
result = await Runner.run(agent, "Hello")
print(result.context_wrapper.usage) # Token counts
環境變數
| 變數 | 值 | 說明 |
|---|---|---|
LITELLM_BASE_URL | http://localhost:4000 | LiteLLM proxy URL |
LITELLM_API_KEY | sk-1234 | 您的 LiteLLM API 金鑰 |