CZL文档

接口文档 ​

CZLOapi的接口通用此方式，即OPENAI的接口方式。
调用不同接口，只需要更换model参数即可。

发出请求 ​

您可以将以下命令粘贴到终端中以运行您的第一个 API 请求。确保替换$OPENAI_API_KEY为您的秘密 API 密钥。

bash
curl https://oapi.czl.net/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'

此请求查询模型以完成以“ Say this is a test gpt-3.5-turbo ”提示开始的文本。您应该收到类似于以下内容的响应：

json
{
   "id":"chatcmpl-abc123",
   "object":"chat.completion",
   "created":1677858242,
   "model":"gpt-3.5-turbo-0301",
   "usage":{
      "prompt_tokens":13,
      "completion_tokens":7,
      "total_tokens":20
   },
   "choices":[
      {
         "message":{
            "role":"assistant",
            "content":"\n\nThis is a test!"
         },
         "finish_reason":"stop",
         "index":0
      }
   ]
}

现在您已经生成了第一个聊天完成。我们可以看到finish_reasonisstop这意味着 API 返回了模型生成的完整完成。在上面的请求中，我们只生成了一条消息，但您可以设置参数n来生成多条消息选择。

模型 ​

列出并描述 API 中可用的各种模型。 您可以参考模型文档来了解可用的模型以及它们之间的差异。

模型列表 ​

GET https://oapi.czl.net/v1/models/

列出当前可用的型号，并提供每个型号的基本信息，例如所有者和可用性。

Example request

bash
curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer $OPENAI_API_KEY"

Response

json
{
	"data": [{
		"id": "gpt-3.5-turbo",
		"object": "model",
		"created": 1677649963,
		"owned_by": "openai",
		"permission": [{
			"id": "modelperm-LwHkVFn8AcMItP432fKKDIKJ",
			"object": "model_permission",
			"created": 1626777600,
			"allow_create_engine": true,
			"allow_sampling": true,
			"allow_logprobs": true,
			"allow_search_indices": false,
			"allow_view": true,
			"allow_fine_tuning": false,
			"organization": "*",
			"group": null,
			"is_blocking": false
		}],
		"root": "gpt-3.5-turbo",
		"parent": null
	}, {
		"id": "gpt-3.5-turbo-16k",
			...
		}],
		"root": "gpt-3.5-turbo-16k",
		"parent": null
	}, {
		"id": "gpt-3.5-turbo-16k-0613",
			...
		}],
		"root": "gpt-3.5-turbo-16k-0613",
		"parent": null
	}, {
		"id": "gpt-4",
			...
		}],
		"root": "gpt-4",
		"parent": null
	}, {
		"id": "gpt-4-0613",
		"object": "model",
		"created": 1677649963,
		"owned_by": "openai",
		"permission": [{
			"id": "modelperm-LwHkVFn8AcMItP432fKKDIKJ",
			"object": "model_permission",
			...
		}],
		"root": "gpt-4-0613",
		"parent": null
        }, 
......
	{
		"id": "code-davinci-edit-001",
		......
		"root": "code-davinci-edit-001",
		"parent": null
	}],
	"object": "list"
}

1688396070096.png

检索模型 ​

GET https://oapi.czl.net/v1/models/{model}

检索模型实例，提供有关模型的基本信息，例如所有者和权限。

路径参数 ​

model string Required ​

The ID of the model to use for this request

Example request

bash
curl https://oapi.czl.net/v1/models/gpt-4 \
  -H "Authorization: Bearer $OPENAI_API_KEY"

Response

json
{
	"id": "gpt-4",
	"object": "model",
	"created": 1677649963,
	"owned_by": "openai",
	"permission": [...],
	"root": "gpt-4",
	"parent": null
}

聊天 ​

给定包含对话的消息列表，模型将返回响应。

Create chat completion ​

POST https://api.openai.com/v1/chat/completions

Creates a model response for the given chat conversation.

Request body ​

model string Required ​

ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

messages array Required ​

A list of messages comprising the conversation so far. Example Python code.

参数类型是否必需描述
role字符串是消息作者的角色。可选值为system、user、assistant或function。
content字符串否消息的内容。除了带有函数调用的assistant消息外，其他消息都需要提供内容。
name字符串否作者的名称。如果角色为function，则需要提供名称，且应该是内容中包含的函数的名称。名称只能包含a-z、A-Z、0-9和下划线，最大长度为64个字符。
function_call对象否应该调用的函数的名称和参数，由模型生成。
functions array Optional ​

A list of functions the model may generate JSON inputs for.

参数类型是否必需描述
name字符串是要调用的函数的名称。名称只能包含a-z、A-Z、0-9，或包含下划线和连字符，最大长度为64个字符。
description字符串否函数的描述信息。
parameters对象否函数接受的参数，以JSON Schema对象描述。参考指南中的示例，以及JSON Schema参考文档了解格式的详细信息。

Example request

bash
curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"}]
  }'

Parameters

json
{
  "model": "gpt-3.5-turbo",
  "messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"}]
}

Response

json
{
  "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
  }
}

其他参数 ​

function_call

  • Type: string or object
  • Optional
  • Controls how the model responds to function calls.
  • Options:
    • "none": The model does not call a function and responds to the end-user.
    • "auto": The model can choose between responding to the end-user or calling a function.
    • {"name": "my_function"}: The model is forced to call the specified function.
  • Default behavior:
    • "none" if there are no functions present.
    • "auto" if functions are present.

temperature

  • Type: number
  • Optional
  • Defaults to 1
  • Determines the sampling temperature, ranging from 0 to 2.
  • Higher values like 0.8 make the output more random.
  • Lower values like 0.2 make the output more focused and deterministic.
  • We generally recommend adjusting this or top_p but not both.

top_p

  • Type: number
  • Optional
  • Defaults to 1
  • An alternative to sampling with temperature.
  • Determines the threshold probability mass.
  • Only the tokens comprising the top_p probability mass are considered.
  • For example, a value of 0.1 means only the tokens with the top 10% probability mass are considered.
  • We generally recommend adjusting this or temperature but not both.

n

  • Type: integer
  • Optional
  • Defaults to 1
  • Determines how many chat completion choices to generate for each input message.

stream

  • Type: boolean
  • Optional
  • Defaults to false
  • If set to true, partial message deltas will be sent (like in ChatGPT).
  • Tokens will be sent as data-only server-sent events as they become available.
  • The stream is terminated by a data: [DONE] message.

stop

  • Type: string or array
  • Optional
  • Defaults to null
  • Specifies up to 4 sequences where the API will stop generating further tokens.

max_tokens

  • Type: integer
  • Optional
  • Defaults to inf
  • Specifies the maximum number of tokens to generate in the chat completion.
  • The total length of input tokens and generated tokens is limited by the model's context length.

presence_penalty

  • Type: number
  • Optional
  • Defaults to 0
  • Number between -2.0 and 2.0.
  • Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

frequency_penalty

  • Type: number
  • Optional
  • Defaults to 0
  • Number between -2.0 and 2.0.
  • Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

logit_bias

  • Type: map
  • Optional
  • Defaults to null
  • Modifies the likelihood of specified tokens appearing in the completion.
  • Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100.
  • Mathematically, the bias is added to the logits generated by the model prior to sampling.

user

  • Type: string
  • Optional
  • A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

其他API介绍 ​

OPENAI链接