Structured Outputs with Pydantic & OpenAI Function Calling

In this video, we delve into the fascinating realm of open AI function calling and getting structured outputs from Large Language Models! We start by explaining what function calling is and how OpenAI implements this feature. We demonstrate how to use Pydantic to create structured data types combined with OpenAI's function calling, leading to the generation of a fully functional quiz from an article or paper. Disclaimer: In the video I misused the expression: "Structured Prompting" when I meant: "Structured Outputs". 📚 Chapters: 0:00 - Introduction to Topic 0:02 - Overview of OpenAI Function Calling and Structure Prompting 0:09 - Detailed Explanation of Function Calling 0:32 - Steps Involved in Function Calling 0:57 - JSON Schema and Standard in Function Calling 1:59 - Sample Python Code Demonstration 3:25 - Discussion on Model Response and Function Integration 4:47 - Benefits of Function Calling 5:12 - Introduction to Pydantic Library 6:05 - Setting Up Data Structures in Pydantic 7:09 - Defining Quiz and Question Classes 9:00 - Generating a Quiz Using ChatGPT and Pydantic 11:58 - Structured Prompting Approach with OpenAI Function Calling and Pydantic 13:02 - Conclusion and Next Steps 🔗 Links: - Source code: https://github.com/EnkrateiaLucca/quiz-ai-app/tree/main - Subscribe!: https://www.youtube.com/channel/UCu8WF59Scx9f3H1N_FgZUwQ - Tiktok: https://www.tiktok.com/@enkrateialucca?lang=en - Twitter: https://twitter.com/LucasEnkrateia - LinkedIn: https://www.linkedin.com/in/lucas-soares-969044167/ - If you want to support me, check out my full introduction course on prompt engineering here: https://automatalearninglab.thinkific.com/courses/prompt-engineering-basics Support the Channel! - Buy me a cup of coffee: https://tr.ee/7tYsD-tUu2 - Paypal: https://paypal.me/lucasenkrateia?country.x=PT&locale.x=pt_PT