Chapter 2: Anthropic and Other APIs

Anthropic Claude API

import anthropic
client = anthropic.Anthropic()

message = client.messages.create(
    model="claude-3-sonnet-20240229",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, Claude!"}]
)

Google Gemini API

import google.generativeai as genai
genai.configure(api_key='YOUR_KEY')

model = genai.GenerativeModel('gemini-pro')
response = model.generate_content("Hello!")

API Comparison

Feature	OpenAI	Anthropic	Google
Max Context	128K	200K	1M+
Multimodal	Yes	Yes	Yes
Function Calling	Yes	Yes	Yes

Migration Strategy

Use abstraction layers like LangChain or LiteLLM:

from litellm import completion

# Same interface, different providers
response = completion(
    model="gpt-4",  # or "claude-3-opus" or "gemini-pro"
    messages=[{"role": "user", "content": "Hello"}]
)

---

← Chapter 1Chapter 3 →