Anthropic Claude API integration with website

Anthropic Claude API Integration with Website

Claude API from Anthropic provides access to the Claude 3 family (Haiku, Sonnet, Opus). Claude distinguishes itself with a long context window (200K tokens in Claude 3), precision in instruction following, and strong performance with code and structured text.

Basic Integration

use Anthropic\Anthropic;

$client = new Anthropic(['apiKey' => config('services.anthropic.api_key')]);

$message = $client->messages->create([
    'model'      => 'claude-3-5-haiku-20241022',
    'max_tokens' => 1024,
    'system'     => 'You are a product documentation assistant.',
    'messages'   => [
        ['role' => 'user', 'content' => $userQuestion],
    ],
]);

$answer = $message->content[0]->text;

Streaming

import anthropic

client = anthropic.Anthropic()

async def stream_response(user_message: str):
    with client.messages.stream(
        model='claude-3-5-haiku-20241022',
        max_tokens=1024,
        messages=[{'role': 'user', 'content': user_message}],
    ) as stream:
        for text in stream.text_stream:
            yield text

Structured Output via Tools (tool_use)

Claude supports tool_use for obtaining structured JSON:

tools = [{
    'name': 'extract_product_info',
    'description': 'Extract product information from text',
    'input_schema': {
        'type': 'object',
        'properties': {
            'name':        {'type': 'string'},
            'price':       {'type': 'number'},
            'sku':         {'type': 'string'},
            'description': {'type': 'string'},
            'features':    {'type': 'array', 'items': {'type': 'string'}},
        },
        'required': ['name', 'price'],
    },
}]

response = client.messages.create(
    model='claude-3-5-sonnet-20241022',
    max_tokens=1024,
    tools=tools,
    messages=[{
        'role': 'user',
        'content': f'Extract product information:\n\n{product_description}',
    }],
)

# Extract tool_use result
for block in response.content:
    if block.type == 'tool_use' and block.name == 'extract_product_info':
        product_data = block.input
        break

Long Context (200K tokens)

Claude's unique advantage is the ability to pass an entire document or codebase into the context:

# Analyze a long PDF document (convert to text)
with open('contract.txt', 'r') as f:
    document = f.read()

response = client.messages.create(
    model='claude-3-5-sonnet-20241022',
    max_tokens=2048,
    messages=[{
        'role': 'user',
        'content': f"Read the contract and answer: what are the termination conditions?\n\nContract:\n{document}",
    }],
)

Vision: Image Analysis

import base64

with open('screenshot.png', 'rb') as f:
    image_data = base64.standard_b64encode(f.read()).decode('utf-8')

response = client.messages.create(
    model='claude-3-5-sonnet-20241022',
    max_tokens=1024,
    messages=[{
        'role': 'user',
        'content': [
            {'type': 'image', 'source': {'type': 'base64', 'media_type': 'image/png', 'data': image_data}},
            {'type': 'text',  'text': 'Describe what is shown in the screenshot'},
        ],
    }],
)

Comparison with OpenAI

Timeline

Basic integration with chat: 1–2 days. Structured output + vision: +2 days.