PyData Global 2023

Let chatGPT decide and run the function!
12-06, 11:00–11:30 (UTC), Data Track

We all know chatGPT is smart, but is it smart enough to choose a function from a query. We will discuss it through openai function calling, and will let it choose the function according to the query. Also, discusses the extracted json output with a demo.


Some people might wonder what is Openai function calling and why it is 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. We will also let it decide which function to call just with the query and let it act like an agent!

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.


Prior Knowledge Expected

Previous knowledge expected

Sonam is working as the developer advocate for qdrant engine, previously 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.