用net frame 4.7 写的.
基于ChatGPT 3.0 开放API
软件很简单, 控制台程序, 需要用户自己修改Console_ChatGPT.exe.config
文件, 在里面填写api_key
api_key可以从网上找一些免费分享的, 也可以自己注册申请.
这个程序的优点就是不用梯子, 直接就能服务国内用户.
API 3.0跟3.5相比差一些, 不过一些简单的内容还是可以满足的.
如图, 一本正经的胡说八道. 很显然3.0的模型没有完整的读过水浒传.
用net frame 4.7 写的.
基于ChatGPT 3.0 开放API
软件很简单, 控制台程序, 需要用户自己修改Console_ChatGPT.exe.config
文件, 在里面填写api_key
api_key可以从网上找一些免费分享的, 也可以自己注册申请.
这个程序的优点就是不用梯子, 直接就能服务国内用户.
API 3.0跟3.5相比差一些, 不过一些简单的内容还是可以满足的.
如图, 一本正经的胡说八道. 很显然3.0的模型没有完整的读过水浒传.
赞一个。
3.5 现在官方应该不舍得拿出来啊
我叫它帮我将 API 整合到 Synology Chat,弄了几天了。今天终于弄到回复到的,但是每次只能回复很少一段,后续的没有。
果然,自己不会的情况下叫它干活还是不行的。
今日已放出3.5 api。
$0.002 per 1k tokens
100万tokens两美元,的确不贵。
看你们讨论火热,然而有人还卡在第一步 ( OpenAI 的服务在您所在的国家/地区不可用。
还好还有个new bing,可惜不能长对话
chatgpt api 长对话有什么限制吗?可以一直聊下去??forever??
蹲守 3.5 版
有长度限制。好像3万字。中文算两个。中文支持一般。
有个telegram机器人或者网页版API多好。
求大佬更新3.5 的api
统一回复, 我这里北京联通, chatgpt 的官网已经被墙了. API也不能正常访问.
这样话, 用这个意义不大了. 不如直接访问chatgpt , 没梯子的, 都去用 new bing 吧. 太糟心了.
有梯子的话,大佬你这个就很方便了,不用打开浏览器了
这个需要API, 收费的.
官网的免费.
之前还有个国内直接使用的优势. 现在都没了. 何必选收费的.
这个世界充满了遗憾。我这个住在欧洲的用户日常被中美忽略 好不公平
这个东西关键就是model,回答区别大了。求升级到3.5-turbo
大佬,我把你写的这个和autohotkey进行了整合,很好用。
求升级个3.5版本~
api比new bing 或者 官网 给出回答的速度要快很多,偏实用~
如果你是ahk, 我推荐这个方法:
curl https://api.openai.com/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "text-davinci-003",
"prompt": "I am a highly intelligent question answering bot. If you ask me a question that is rooted in truth, I will give you the answer. If you ask me a question that is nonsense, trickery, or has no clear answer, I will respond with \"Unknown\".\n\nQ: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: Unknown\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.\n\nQ: How many squigs are in a bonk?\nA: Unknown\n\nQ: Where is the Valley of Kings?\nA:",
"temperature": 0,
"max_tokens": 100,
"top_p": 1,
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"stop": ["\n"]
}'
你就会得到一个json文件.
或者用python
{
"id": "你的3.5API_key",
"object": "chat.completion",
"created": 1677737615,
"model": "gpt-3.5-turbo-0301",
"usage": {
"prompt_tokens": 39,
"completion_tokens": 35,
"total_tokens": 74
},
"choices": [
{
"message": {
"role": "assistant",
"content": "您好,我是个AI助手,没有具体的名字。您需要我帮助您处理json文件格式吗?"
},
"finish_reason": "stop",
"index": 0
}
]