4.5 Batch Processing and Prompt Optimisation

import anthropic

client = anthropic.Anthropic()

# สร้าง batch
batch = client.messages.batches.create(
    requests=[
        {
            "custom_id": "review-001",
            "params": {
                "model": "claude-sonnet-4-20250514",
                "max_tokens": 200,
                "messages": [{"role": "user", "content": f"Classify: {review_1}"}]
            }
        },
        {
            "custom_id": "review-002",
            "params": {
                "model": "claude-sonnet-4-20250514",
                "max_tokens": 200,
                "messages": [{"role": "user", "content": f"Classify: {review_2}"}]
            }
        },
        # ... hundreds more
    ]
)

# Poll for completion
while batch.processing_status != "ended":
    batch = client.messages.batches.retrieve(batch.id)
    time.sleep(60)

# Get results
results = client.messages.batches.results(batch.id)
for result in results:
    print(f"{result.custom_id}: {result.result.message.content[0].text}")

# First call — cache the system prompt
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    system=[{
        "type": "text",
        "text": long_system_prompt,
        "cache_control": {"type": "ephemeral"}
    }],
    messages=[{"role": "user", "content": "Question 1"}]
)

# Subsequent calls — cached system prompt = 90% cheaper input tokens
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    system=[{
        "type": "text",
        "text": long_system_prompt,  # same text = cache hit
        "cache_control": {"type": "ephemeral"}
    }],
    messages=[{"role": "user", "content": "Question 2"}]
)