AI SDKs & APIs

AI SDKs & APIs

Duration: 2 Days

Description

Every major AI provider ships its own SDK, and they overlap just enough to be confusing and differ just enough to break code that assumes they’re interchangeable. This course builds a comparative, working understanding of the major AI SDKs and APIs — not “here’s the OpenAI SDK,” but the patterns that repeat across providers: authenticating and structuring calls, handling streaming responses so a UI doesn’t sit frozen mid-generation, using function calling to let a model trigger real code, and requesting structured output you can parse reliably instead of scraping free text. Hands-on exercises work directly against live APIs so participants build real fluency with the interfaces they’ll actually be shipping against.
Class time is divided between instructor-led explanation (40 percent) and hands-on coding (60 percent).

Audience

This course is for developers already building or planning to build AI-powered applications who want command of the SDK layer specifically, rather than a conceptual overview. It pairs well alongside or right after an introductory AI development course, once the underlying concepts (prompts, tokens, context) are already familiar and the question becomes “how do I actually wire this into an application.”

Objectives

  • Navigate the landscape of major AI SDKs and APIs
  • Use core API features: messages, tokens, parameters, and streaming
  • Implement function calling and tool use across SDKs
  • Work with embeddings and structured output
  • Compare providers and select appropriate tools
  • Apply patterns for authentication, error handling, and configuration

Prerequisites

Participants should be comfortable writing code and calling APIs. The following will help:

  • Working knowledge of Python (see Python Foundations)
  • Experience calling AI model APIs (see AI for Developers)

Related AI Courses

See the full AI training roadmap and course directory for how this fits into a broader learning path.

New to building with AI generally? Start with AI for Developers. Working specifically with OpenAI’s API? See Python OpenAI API for Developers. Ready to move from single API calls to full applications? See Building LLM Applications or LangChain & LangGraph for orchestration across multiple calls.

Course Outline

  • Module 1 – Course Introduction
    • Welcome and objectives
    • The AI SDK and API ecosystem
    • Common concepts across providers
  • Module 2 – Core API Patterns
    • Messages, roles, and parameters
    • Tokens, limits, and pricing models
    • Streaming and asynchronous calls
    • Authentication and configuration
  • Module 3 – Tool Use and Function Calling
    • Function calling across SDKs
    • Defining and handling tools
    • Structured and constrained output
    • Hands-on exercise: function calling in practice
  • Module 4 – Embeddings and Beyond
    • Working with embeddings APIs
    • Multimodal inputs and outputs
    • Specialized endpoints and capabilities
    • Hands-on exercise: using embeddings
  • Module 5 – Comparing and Choosing
    • Strengths and tradeoffs across providers
    • Abstraction layers and portability
    • Reliability, error handling, and fallbacks
    • Selecting tools for a task
  • Module 6 – Course Wrap-Up
    • Key takeaways
    • Resources for continued learning
    • Next steps