cocacola-lab / chatie Goto Github PK

请问DUIE2.0官方没提供测试集的标签，您如何划分的测试集

Error communicating with OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by ProxyError('Cannot connect to proxy.', NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f20e6998910>: Failed to establish a new connection: [Errno 111] Connection refused

我的API Key在GPT4IE中可以正确返回结果，为什么在ChatIE中报错error-stage1:Incorrect API key provided: key 3. You can find your API key at https://platform.openai.com/account/api-keys.

你好，
我看论文中的你们对“Vanilla Prompt vs. Our Chat-based Prompt”做了对比，这里的Vanilla Prompt具体有文章吗？是哪篇文章做的提示学习吗？想了解下，方便解释一下吗，谢谢。

按照项目说明的步骤：

1. Run npm run start 。 浏览器自动弹出界面。
2. cd back-end and Run python run.py. 。弹出提示：Running on http://127.0.0.1:3000/ (Press CTRL+C to quit)，进入链接http://127.0.0.1:3000，界面内容为：Not Found。The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again.
3. 我的key，openai.proxy都设置完成了。
   4.我在前端尝试输入一段话，就报错：http://localhost:5000/ says SyntaxError: Unexpected token '<', "<!DOCTYPE "... is not valid JSON。后端也报错：TypeError: The view function did not return a valid response. The function either returned None or ended without a return statement.

our openai account has expired, we will update if we buy a new plan.

{"detail":{"message":"Your authentication token has expired. Please try signing in again.","type":"invalid_request_error","param":null,"code":"token_expired"}} OpenAI: {"detail":{"message":"Your authentication token has expired. Please try signing in again.","type":"invalid_request_error","param":null,"code":"token_expired"}} (code: 401)
以上是错误信息
应该是指access token过期了。
不太懂access token这个是什么意思，和openai的key有关吗？如何修复？

您好，很棒的一篇工作。
请问会不会将经过Prompt转换后的数据集分享出来 :)

This may relate more to the paper than the tool, sorry if it is the wrong channel.

How exactly is your NER evaluation performed. The relevant section in the paper is as follows:

We only consider the complete matching and use the micro F1 to evaluate NER task.
Only when both the border and the type of the predicted entity and the true entity are the same will we regard it as a correct prediction.

Given your example prompts in the appendix only list expected outputs of the form: ["Japan", "LOC"], there is no direct access to a border/offset. Do you just look for the answer text in the original sentence and take that index?

"error-stage1:Rate limit reached for default-gpt-3.5-turbo in organization org-NATszHOraQIVn1LhMbHGpI3Q on requests per min. Limit: 3 / min. Please try again in 20s. Contact [email protected] if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method."

openai官方对请求速率限制一分钟3个，在此提醒一下。
因为是多轮框架，所以一个实例中间可能会断，影响结果。
Solve：TODO

请问这个应该如何设置

hello, did you test the event detection performance (trigger identification and trigger classification) on the ACE2005 dataset ? According to the paper, only contain arguments classification are considered. Did I miss anything?

您好，请问你们的prompt template是人工定义的吧，定义时有没有考虑测试更换不同的template内容呢？还有测试不同数据集的时候是将一条一条句子带入template后测试的吗？能不能整个数据集上传完成抽取？

"error-stage1:Incorrect API key provided: sk-5ZHQn*****************************************************************************************pYxy. You can find your API key at https://platform.openai.com/account/api-keys."

请问下API key测试可用，为啥代码里面报错incorrect api key

按理说这两个Du数据集在关系类型上比其他两个同类任务的数据集要丰富的多，根据其他研究者的类似结论，当关系类型很丰富的情况下，chatGPT应该更难做，为什么在这两个数据集上这么反常呢？

谢谢你们的开源贡献和新想法！

最近openai API似乎很慢，总是报RateLimitError的错误，几乎没法批量调用数据生成答案。想了解一下你们是如何解决的？付费成为plus会不会好一点。