chatgpt-web 官方模型参数的设置

Hi,非常棒的项目。然而是否提供了一些调整模型的参数设置，官方的API接口提供了tokens以及temperature、还有penalty等参数的设置。项目里似乎没有可以简单进行配置的文件。

Mar 02 '23 17:03 williamlorder

还有聊天机器人初始语气，以及身份等。下面是一个官方的示例

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "\n\nHello there, how may I assist you today?",
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Mar 02 '23 17:03 williamlorder

除此之外，gpt-3.5-turbo 模型支持的 role 其实有三种：user、assistant、system，system 的指令可以设置 chat 的行为，相当于一个顶层约束，比如让 chat 倾向于做一个 ai 全能助手或是翻译官，感觉也是很有必要增加一个设置入口。

# Note: you need to be using OpenAI Python v0.27.0 for the code below to work
import openai

openai.ChatCompletion.create(
  model="gpt-3.5-turbo",
  messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"},
        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
        {"role": "user", "content": "Where was it played?"}
    ]
)

[
  {“role”: “system”, “content”: “You are a helpful assistant that translates English to French.”},
  {“role”: “user”, “content”: ‘Translate the following English text to French: “{text}”’}
]

相关文档见：https://platform.openai.com/docs/guides/chat/introduction