YoVDO

GPT-4o API Deep Dive: Text Generation, Streaming, Vision, and Function Calling

Offered By: Venelin Valkov via YouTube

Tags

GPT-4 Courses Computer Vision Courses Image Analysis Courses Text Generation Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Dive deep into the capabilities of GPT-4o, OpenAI's top-ranked model on the LMSYS Chatbot Arena Leaderboard, in this comprehensive 22-minute video tutorial. Explore its multimodal abilities in handling text and images, as well as its proficiency in function calling. Learn to set up Google Colab, prompt via the API, count tokens, implement streaming, simulate chat interactions, generate JSON-only responses, utilize vision capabilities for image input and text extraction, and leverage function calling for agent tools. Gain practical insights into applying the OpenAI API to enhance your projects and understand the model's inference speed and performance through various demonstrations.

Syllabus

- What is GPT-4o?
- Text tutorial on MLExpert.io
- GPT-4o on LMSYS Leaderboard
- Google Colab Setup
- Prompting via the API
- Count Tokens in a Prompt
- Streaming
- Simulate Chat via the API
- JSON only Response
- Vision Image as Input and Text Extraction from Document
- Function Calling Tools for Agents
- Conclusion


Taught by

Venelin Valkov

Related Courses

Introduction to Artificial Intelligence
Stanford University via Udacity
Computer Vision: The Fundamentals
University of California, Berkeley via Coursera
Computational Photography
Georgia Institute of Technology via Coursera
Einführung in Computer Vision
Technische Universität München (Technical University of Munich) via Coursera
Introduction to Computer Vision
Georgia Institute of Technology via Udacity