# 本地请求

## huggingface 请求

curl -X POST https://sanbo1200-planrun.hf.space/chat1 \
  -H 'Accept: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-xx",
    "messages": [{"role": "user", "content": "Say this is a test!"}],
    "temperature": 0.7,
    "max_tokens": 150,
    "top_p": 1.0,
    "frequency_penalty": 0.0,
    "presence_penalty": 0.0
  }'





## 启动服务

* 设置环境变量

``` 
# 优先级1: 替换
export REPLACE_CHAT="/chat"
# 优先级2: 前缀
export PREFIX_CHAT="/api,/hf"
# 优先级3: 追加
export APPEND_CHAT="/hh/v1/go,/xxx/sxxx"
# 默认端口设置
export PORT=7860
# 默认默认授权token
export TOKEN="sk_token"
```
* 启动服务
```
uvicorn main:app --reload

uvicorn main:app --reload --port 7860

```

## 调用服务

```

curl -X POST http://localhost:7860/api/v1/chat/completions \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say this is a test!"}],
    "temperature": 0.7,
    "max_tokens": 150,
    "top_p": 1.0,
    "frequency_penalty": 0.0,
    "presence_penalty": 0.0,
    "stop": ["\n"]
  }'

## 精简
curl -X POST http://localhost:7860/api/v1/chat/completions \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say this is a test!"}],
    "temperature": 0.7,
    "max_tokens": 150,
    "top_p": 1.0,
    "frequency_penalty": 0.0,
    "presence_penalty": 0.0
  }'

curl -X POST http://localhost:7860/v1/chat/completions \
  -H 'Accept: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say this is a test!"}],
    "temperature": 0.7,
    "max_tokens": 150,
    "top_p": 1.0,
    "frequency_penalty": 0.0,
    "presence_penalty": 0.0
  }'

curl -X POST https://sanbo1200-planrun.hf.space/chat \
  -H 'Accept: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say this is a test!"}],
    "temperature": 0.7,
    "max_tokens": 150,
    "top_p": 1.0,
    "frequency_penalty": 0.0,
    "presence_penalty": 0.0
  }'



```