OpenAI 终于发力了,今天清晨更新了一大波内容,让我们一起来看看:
-
Chat Completions API 中现在支撑函数调用了,也就是说为 API 接口定义了一套标准的插件标准!
-
新增了
gpt-4-0613
和gpt-3.5-turbo-0613
模型 -
新增了支撑 16k 上下文的
gpt-3.5-turbo-16k
模型 -
嵌入模型本钱下降 75%
-
gpt-3.5-turbo
模型 tokens 本钱下降 25% -
gpt-3.5-turbo-0301
和gpt-4-0314
模型行将被抛弃
函数调用
OpenAI API 现在支撑函数调用了,但仅限于 gpt-4-0613
和 gpt-3.5-turbo-0613
模型,其实就是支撑插件了!应用场景:
- 创建聊天机器人,经过调用外部工具(例如 ChatGPT 插件)来回答问题
- 将自然语言转换为 API 调用或数据库查询
- 从文本中提取结构化数据
函数调用举例
1、运用函数和用户的输入调用模型
恳求:
curl https://api.openai.com/v1/chat/completions -u :$OPENAI_API_KEY -H 'Content-Type: application/json' -d '{
"model": "gpt-3.5-turbo-0613",
"messages": [
{"role": "user", "content": "What is the weather like in Boston?"}
],
"functions": [
{
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location"]
}
}
]
}'
呼应:
{
"id": "chatcmpl-123",
...
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": null,
"function_call": {
"name": "get_current_weather",
"arguments": "{ "location": "Boston, MA"}"
}
},
"finish_reason": "function_call"
}]
}
2、调用第三方 API
恳求:
curl https://weatherapi.com/...
呼应:
{ "temperature": 22, "unit": "celsius", "description": "Sunny" }
3、将呼应发送回模型进行汇总
恳求:
curl https://api.openai.com/v1/chat/completions -u :$OPENAI_API_KEY -H 'Content-Type: application/json' -d '{
"model": "gpt-3.5-turbo-0613",
"messages": [
{"role": "user", "content": "What is the weather like in Boston?"},
{"role": "assistant", "content": null, "function_call": {"name": "get_current_weather", "arguments": "{ "location": "Boston, MA"}"}},
{"role": "function", "name": "get_current_weather", "content": "{"temperature": "22", "unit": "celsius", "description": "Sunny"}"}
],
"functions": [
{
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location"]
}
}
]
}'
呼应:
{
"id": "chatcmpl-123",
...
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "The weather in Boston is currently sunny with a temperature of 22 degrees Celsius.",
},
"finish_reason": "stop"
}]
}
新模型
GPT-4
GPT-4 新增了 2 个模型,gpt-4-0613
和 gpt-4-32k-0613
,均支撑函数调用,而且支撑更长的上下文和更好的语义理解。
GPT-3.5 Turbo
GPT-3.5 新增了 2 个模型,gpt-3.5-turbo-0613
和 gpt-3.5-turbo-16k
。
gpt-3.5-turbo-0613
支撑函数调用,而且对 system 类型的音讯具有更好的操控,呼应速度更快!
gpt-3.5-turbo-16k
支撑更长的上下文,单个恳求中支撑约 20 页文本输入。
抛弃模型
gpt-3.5-turbo-0301
,gpt-4-0314
以及 gpt-4-32k-0314
行将抛弃运用。
费用情况
嵌入模型
text-embedding-ada-002
本钱下降 75%,现在费用是 $0.0001/1K tokens
GPT-3.5 Turbo
gpt-3.5-turbo
本钱下降 25%,费用明细:
输入:$0.0015/1K input tokens
输出:$0.002/1K output tokens
gpt-3.5-turbo-16k
费用明细:
输入:$0.003/1K input tokens
输出:$0.004/1K output tokens
总的来说就是新增了函数调用功用,更长的上下文支撑,更低的本钱。
树先生开发的 ChatGPT 镜像网址也在第一时间更新了上述模型,欢迎体会!函数调用功用行将更新,敬请期待~