Anthropic Claude

In this notebook we will prompt the LLM Claude from anthropic.

import anthropic

def prompt_claude(message:str, model="claude-3-5-sonnet-20240620"):
    """
    A prompt helper function that sends a message to anthropic
    and returns only the text response.

    Example models: claude-3-5-sonnet-20240620 or claude-3-opus-20240229
    """
    from anthropic import Anthropic
    
    # convert message in the right format if necessary
    if isinstance(message, str):
        message = [{"role": "user", "content": message}]
        
    # setup connection to the LLM
    client = Anthropic()
    
    message = client.messages.create(
        max_tokens=4096,
        messages=message,
        model=model,
    )

    # extract answer
    return message.content[0].text

prompt_claude("What is the capital of France?")

'The capital of France is Paris.'

Listing available models

client = anthropic.Anthropic()
models = client.models.list().data

for m in models:
    print(m.id)

claude-3-7-sonnet-20250219
claude-3-5-sonnet-20241022
claude-3-5-haiku-20241022
claude-3-5-sonnet-20240620
claude-3-haiku-20240307
claude-3-opus-20240229
claude-3-sonnet-20240229
claude-2.1
claude-2.0