def chunk_text(text, chunk_size=2000):
    return [text[i : i + chunk_size] for i in range(0, len(text), chunk_size)]


def summarize_long_document(text, max_tokens=2000):
    chunks = chunk_text(text)

    # Iterate over chunks and summarize each one
    # We use guided_legal_summary here, but you can use basic_summarize or any other summarization function
    # Note that we'll also use haiku for the interim summaries, and the 3.5 sonnet for the final summary
    chunk_summaries = [
        guided_sublease_summary(chunk, model="claude-haiku-4-5", max_tokens=max_tokens)
        for chunk in chunks
    ]

    final_summary_prompt = f"""

    You are looking at the chunked summaries of multiple documents that are all related. Combine the following summaries of the document from different truthful sources into a coherent overall summary:

    {"".join(chunk_summaries)}
…
    Summary:
    """

    response = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=max_tokens,
        system="You are a legal expert that summarizes notes on one document.",
        messages=[
            {"role": "user", "content": final_summary_prompt},
            {
                "role": "assistant",
                "content": "Here is the summary of the legal document: <summary>",
            },
        ],
        stop_sequences=["</summary>"],
    )

    return response.content[0].text

Échauffement