13. API Integration - Programmatic AI
Move beyond chat interfaces and IDE tools - integrate AI directly into your applications via APIs. Build features like AI chatbots, content generation, code analysis, and more.
Major AI APIs for Developers
OpenAI API
GPT-4, GPT-3.5, DALL-E, Whisper, Embeddings
- • Chat Completions: Conversational AI
- • Function Calling: AI triggers your functions
- • Embeddings: Semantic search, RAG
- • Vision: Image understanding
- Pricing: Pay-per-token ($0.01-0.06 per 1K tokens)
Anthropic API (Claude)
Claude 3.5 Sonnet, Opus, Haiku
- • 200K context for large document processing
- • System prompts: Better instruction following
- • Tool use: Similar to function calling
- Pricing: Competitive with OpenAI
Google AI (Gemini)
Gemini Pro, Ultra (via Vertex AI)
- • 1M tokens context window
- • Multimodal: Text, images, video, audio
- • Grounding: Google Search integration
- Pricing: Very competitive
Quick Start Example (OpenAI)
// Node.js
import OpenAI from 'openai';
const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
const response = await openai.chat.completions.create({
model: "gpt-4",
messages: [
{ role: "system", content: "You are a helpful coding assistant" },
{ role: "user", content: "Explain async/await in JavaScript" }
]
});
console.log(response.choices[0].message.content);Common Use Cases
- • AI Chatbots: Customer support, internal tools
- • Content Generation: Blog posts, product descriptions
- • Code Analysis: Security scanning, code review
- • Semantic Search: Using embeddings + vector DB
- • Data Extraction: Structured output from unstructured text
Best Practices
- ✓ Rate limiting: Handle API rate limits gracefully
- ✓ Error handling: Retry with exponential backoff
- ✓ Caching: Cache responses when appropriate
- ✓ Cost monitoring: Track token usage to avoid surprises
- ✓ Streaming: Use streaming for better UX (real-time responses)