HTTP Basics

HTTP (HyperText Transfer Protocol) is how your code talks to AI services. Understanding it is essential for working with any API.

The Request-Response Model

Your Code  ──[Request]──>  API Server
           <──[Response]──

Every API interaction follows this pattern:

1. Your code sends a request
2. The server processes it
3. The server returns a response

HTTP Methods

Method	Purpose	AI Use Case
GET	Retrieve data	List models, check status
POST	Send data	Chat completions, embeddings
PUT	Update data	Update fine-tuned models
DELETE	Remove data	Delete files, cancel jobs

Most AI API calls use POST because you're sending prompts/messages.

Request Structure

POST /v1/chat/completions HTTP/1.1
Host: api.openai.com
Authorization: Bearer sk-your-key
Content-Type: application/json

{
    "model": "gpt-4",
    "messages": [{"role": "user", "content": "Hello!"}]
}

Key components:

• Method + Path: What action and where
• Headers: Metadata (auth, content type)
• Body: The actual data (JSON for AI APIs)

Response Structure

HTTP/1.1 200 OK
Content-Type: application/json

{
    "choices": [
        {"message": {"content": "Hello! How can I help?"}}
    ]
}

HTTP Status Codes

Code	Meaning	What to Do
200	Success	Process the response
400	Bad request	Check your request format
401	Unauthorized	Check API key
429	Rate limited	Wait and retry
500	Server error	Retry or contact support

Headers You'll Use Often

headers = {
    "Authorization": "Bearer sk-your-api-key",
    "Content-Type": "application/json",
    "Accept": "application/json"
}

Next, we'll use the requests library to make these calls in Python. :::