Hi
The general problem here is how to create conversational applications based on GPT3 able to accomplish task-oriented deterministic activities, overtaking the ‘partially-no-deterministic’ elaborations of generative systems.
Hi这里的一般问题是如何创建基于 GPT3 的对话应用程序，能够完成面向任务的确定性活动，超越生成系统的“部分无确定性”阐述。

In practice, you want to call any custom function (API acting as info retrieval or a disposable action) modifying the LLM completions letting the LLM to call that function as needed.
实际上，您希望调用任何自定义函数（充当信息检索或一次性操作的 API），修改 LLM 完成，让 LLM 根据需要调用该函数。

Practical examples? Consider a chatbot that help customers with usual informative answers but that allow to open a ticket on some help-desk system. Or consider a question/answering system that do need to retrieve some info in realtime, etc.
实例？考虑一个聊天机器人，它帮助客户提供通常的信息答案，但允许在某些帮助台系统上打开票证。或者考虑一个确实需要实时检索一些信息的问答系统，等等。

Let’s