OpenAI API: Multimodal Development with GPT-4o
37mGeneral2024-06-07
Authors
Morten Rand-Hendriksen
Senior Staff Instructor, Speaker, Web Designer, and Software Developer
Course details
In this hands-on course you’ll use the OpenAI API to leverage the multimodal capabilities of GPT-4o and function calling to extract text from images, conform the data to JSON, and call functions to save the extracted data to a spreadsheet.
Learning objectives
Apply GPT-4o API for image analysis.
Capture structured data using AI function calling.
Develop with multimodal AI capabilities.
Learning objectives
Apply GPT-4o API for image analysis.
Capture structured data using AI function calling.
Develop with multimodal AI capabilities.
Skills covered
GPTAPIsOpenAIProgramming FoundationsGenerative AIArtificial Intelligence (AI)Software DevelopmentOne-Off
Concepts
Introduction
- Multimodal development with GPT-4o
Multimodal development
- Exploring multimodal capabilities with ChatGPT
- Project setup and walk-through
- Using GPT-4o through the API
- Interpreting images with the API using GPT-4o
- Making GPT-4o output JSON
- Combining multimodal and function calling
- Converting image data to spreadsheet data
- Setting up a multimodal flow with Python and GPT-4o
Conclusion
- Next steps