16. Working with APIs

HTTP Basics

AI services expose REST APIs. You send a request; you get a response. The requests library handles this in Python:

import requests

response = requests.get("https://api.example.com/models")
print(response.status_code)  # 200 = success
print(response.text)         # Raw response text

POST Requests

AI APIs typically use POST for completions:

import requests

url = "https://api.openai.com/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
payload = {
    "model": "gpt-4",
    "messages": [
        {"role": "user", "content": "Hello"}
    ],
    "temperature": 0.7
}

response = requests.post(url, headers=headers, json=payload)
print(response.status_code)
print(response.json())

Response Handling

response = requests.post(url, headers=headers, json=payload)

if response.status_code == 200:
    data = response.json()
    print(data["choices"][0]["message"]["content"])
else:
    print(f"Error {response.status_code}: {response.text}")

Query Parameters

# GET with query parameters
params = {
    "model": "gpt-4",
    "limit": 10
}
response = requests.get(
    "https://api.openai.com/v1/models",
    headers=headers,
    params=params
)

Local verification checkpoint

Run the smallest example from this chapter in a local workspace and record the package version, runtime, data path, and observed output. If the result depends on model size, vector count, CPU/GPU backend, or available memory, note that constraint beside the exercise so the lesson remains reproducible.

Local verification checkpoint

Run the smallest example from this chapter in a local workspace and record the package version, runtime, data path, and observed output. If the result depends on model size, vector count, CPU/GPU backend, or available memory, note that constraint beside the exercise so the lesson remains reproducible.