如何基于 LLM 集成应用程序 API ?How a LLM-based application, integrates a custom function (API)?
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.
这里的一般问题是如何创建基于 GPT3 的会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“部分非确定性”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.
在实践中,您想要调用任何自定义函数(API 充当信息检索或一次性操作)来修改 LLM 完成,让 LLM 根据需要调用该函数。<