法律文件摘要

details_to_extract = [
    "涉及方（轉租人、承租人和原始出租人）",
    "物業詳情（地址、描述和允許用途）",
    "期限和租金（開始日期、結束日期、月租金和押金）",
    "責任（公用事業、維護和修繕）",
    "同意和通知（房東同意和通知要求）",
    "特殊條款（家具、停車和轉租限制）",
]

from io import BytesIO
import re

import pypdf
import requests


def get_llm_text(pdf_file):
    reader = pypdf.PdfReader(pdf_file)
    text = "\n".join([page.extract_text() for page in reader.pages])

    # Remove extra whitespace
    text = re.sub(r"\s+", " ", text)

    # Remove page numbers
    text = re.sub(r"\n\s*\d+\s*\n", "\n", text)

    return text


# Create the full URL from the GitHub repository
url = "https://raw.githubusercontent.com/anthropics/anthropic-cookbook/main/skills/summarization/data/Sample Sublease Agreement.pdf"
url = url.replace(" ", "%20")

# Download the PDF file into memory
response = requests.get(url)

# Load the PDF from memory
pdf_file = BytesIO(response.content)

document_text = get_llm_text(pdf_file)
print(document_text[:50000])

# Initialize the Anthropic client
client = anthropic.Anthropic()


def summarize_document(
    text, details_to_extract, model="claude-opus-4-7", max_tokens=1000
):
    # Format the details to extract to be placed within the prompt's context
    details_to_extract_str = "\n".join(details_to_extract)

    # Prompt the model to summarize the sublease agreement
    prompt = f"""Summarize the following sublease agreement. Focus on these key aspects:

    {details_to_extract_str}

    Provide the summary in bullet points nested within the XML header for each section. For example:

    <parties involved>
    - Sublessor: [Name]
    // Add more details as needed
    </parties involved>

    If any information is not explicitly stated in the document, note it as "Not specified". Do not preamble.

    Sublease agreement text:
    {text}
    """

    response = client.messages.create(
        model=model,
        max_tokens=max_tokens,
        system="You are a legal analyst specializing in real estate law, known for highly accurate and detailed summaries of sublease agreements.",
        messages=[
            {"role": "user", "content": prompt},
        ],
    )

    return response.content[0].text


sublease_summary = summarize_document(document_text, details_to_extract)
print(sublease_summary)

# Initialize the Anthropic client
client = anthropic.Anthropic()


def chunk_text(text, chunk_size=20000):
    return [text[i : i + chunk_size] for i in range(0, len(text), chunk_size)]


def summarize_long_document(
    text, details_to_extract, model="claude-opus-4-7", max_tokens=1000
):
    # Format the details to extract to be placed within the prompt's context
    details_to_extract_str = "\n".join(details_to_extract)

    # Iterate over chunks and summarize each one
    chunk_summaries = [
        summarize_document(
            chunk, details_to_extract, model=model, max_tokens=max_tokens
        )
        for chunk in chunk_text(text)
    ]

    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:

    <chunked_summaries>
    {"".join(chunk_summaries)}
    </chunked_summaries>

    Focus on these key aspects:
    {details_to_extract_str})

    Provide the summary in bullet points nested within the XML header for each section. For example:

    <parties involved>
    - Sublessor: [Name]
    // Add more details as needed
    </parties involved>

    If any information is not explicitly stated in the document, note it as "Not specified". Do not preamble.
    """

    response = client.messages.create(
        model=model,
        max_tokens=max_tokens,
        system="You are a legal expert that summarizes notes on one document.",
        messages=[
            {"role": "user", "content": final_summary_prompt},
        ],
    )

    return response.content[0].text


long_summary = summarize_long_document(document_text, details_to_extract)
print(long_summary)