Description:

Some people might wonder what is Openai function calling and why is it important; this talk goes in-depth on why and how to use OpenAI function calling feature for GPT models. It improves the output of your model a lot and reduces errors and hallucinations. After all, it is just not a chatbot; it's your brand that is interacting with your customers.

With function calling, developers can now describe functions to gpt-4-0613 and gpt-3.5-turbo-0613, and have the model intelligently choose to output a JSON object containing arguments to call those functions. It allows developers to get structured data back from the model more reliably. In other words, it generates the JSON output in the data structure you gave in the description for the function.

Why might we need OpenAI function calling in ChatCompletion? It should be kept in mind that for complex mathematical queries it's important to run it in ChatCompletion as function calling and not simple ChatCompletion. According to research, ChatGPT can sometimes lead to wrong numerical answers. You can read about the mathematical capability of ChatGPT https://arxiv.org/pdf/2301.13867.pdf

Video URL:

https://youtu.be/e0tqSeOib4E

Content URLs:

Github https://github.com/RasaHQ/OpenAI_func_calling slides https://docs.google.com/presentation/d/13SIM0dARCFThUHY4gwVwS6_npWb8aVBNgi1CVzfx0jk/edit?usp=sharing

Speaker Info:

Sonam is working as the developer advocate for Rasa. She has previously worked as an AI researcher at Saama Technologies on various AI projects for Pfizer and NIH For drug trials and Inclusion in medicine. She is passionate about Language models and has made various videos explaining generative AI for Rasa developers. She is a published author in ACL and loves to give talks at conferences, meet developers.

Speaker Links:

[Youtube:][1] : https://www.youtube.com/@RasaHQ

My previous talks are available at: sonamtalks.com