from litellm import completion

# OpenAI调用
response = completion(
    model="openai/gpt-4", 
    messages=[{"role": "user", "content": "写一个python快速排序"}]
)

# 换成Anthropic
response = completion(
    model="anthropic/claude-3-sonnet",
    messages=[{"role": "user", "content": "写一个python快速排序"}]
)

# 换成Google
response = completion(
    model="google/gemini-pro",
    messages=[{"role": "user", "content": "写一个python快速排序"}]
)

from litellm import Router

# 配置模型列表
model_list = [
    {
        "model_name": "gpt-4",
        "litellm_params": {"model": "openai/gpt-4"},
    },
    {
        "model_name": "gpt-4",
        "litellm_params": {"model": "anthropic/claude-3-sonnet"},
    }
]

# 创建路由器
router = Router(model_list=model_list)

# 自动选择可用模型
response = router.completion(
    model="gpt-4",
    messages=[{"role": "user", "content": "你好"}]
)

from litellm import completion
import os

# 设置回调
os.environ["HELICONE_API_KEY"] = "your-key"
litellm.success_callback = ["helicone"]

# 调用时会自动记录用量
response = completion(
    model="openai/gpt-4",
    messages=[{"role": "user", "content": "Hi"}],
    metadata={"project": "chatbot", "user": "user_123"}
)

response = completion(
    model="openai/gpt-4",
    messages=[{"role": "user", "content": "讲个故事"}],
    stream=True
)

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

litellm --model huggingface/bigcode/starcoder

import openai
client = openai.OpenAI(
    api_key="anything",
    base_url="http://localhost:4000"
)

response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "你好"}]
)