Anthropic 教程：如何构建自己的司法人工智能助手

mkdir claude_tutorialcd claude_tutorialpython3 -m venv venv# Linux/MacOSsource venv/bin/activate# Windowsvenv\\Scripts\\activate.bat

pip install PyPDF2 pycryptodome # PyPDF2 and ycryptodome are used to read PDF filespip install anthropic # Anthropic SDK

pip install fastapi uvicorn # framework for creating APIs and a server to serve those APIs respectively

import osfrom PyPDF2 import PdfReaderimport anthropicfrom fastapi import FastAPI, Response

API_KEY = "sk-ant-..."anthropic_client = anthropic.Client(API_KEY)app = FastAPI()

async def mine_case(path: str, input_prompt: str) -> str:    reader = PdfReader(path)    text = "\\n".join([page.extract_text() for page in reader.pages])    no_tokens = anthropic.count_tokens(text)    print(f"Number of tokens in text: {no_tokens}")    if no_tokens > 100000:        raise ValueError(f"Text is too long {no_tokens}.")    prompt = prompt = f"""    {anthropic.HUMAN_PROMPT}: here's a case file extract in <case> tags <case>{text}<case>    {anthropic.HUMAN_PROMPT}:understand then present the key pieces such as case ID, date, Plaintiff, Appellent, what is the case type, jurisdiction, a short summary, sentiment and its impact on business, and adverse findings, and outcome and put them in separate xml tags.        \\n\\n{anthropic.AI_PROMPT}:\\n\\ncase:"""    res = anthropic_client.completion(prompt=prompt, model="claude-v1.3-100k", max_tokens_to_sample=1000)    return res["completion"]

# Add our endpoint that invoke our function we created earlier and set it to return response as xml@app.get("/case", response_class=Response, responses={200: {"content": {"application/xml": {}}}})async def get_case():    # let's define our prompt and pass it to our function        return Response(content= await mine_case('test.pdf'), media_type="application/xml")

uvicorn main:app --reload

<date> 2021</date><case>Michele Yates v. Pinellas Hematology & Oncology, P.A. , 8:16-cv-00799- WFJ -CPT</case><Plaintiff>Michele Yates,</Plaintiff><Appellent>Pinellas Hematology & Oncology, P.A.</Appellent><casetype>Qui Tam Action</casetype><jurisdiction>United States Court of Appeals For the Eleventh Circuit</jurisdiction><shortsummary>The jury in this qui tam case found that Pinellas Hematology & Oncology violated the False Claims Act, 31 U.S.C. § 3729 et seq., on 214 occasions, and that the United States had sustained $755.54 in damages.The district court trebled the damages and imposed statutory minimum penalties of $1,177,000.</shortsummary><sentiment>Adverse</sentiment><impact>The adverse findings and penalties imposed can negatively impact the business and reputation of the company.</impact><adversefindings>The jury found Pinellas Hematology & Oncology violated the False Claims Act by defrauding the federal government through the submission of 214 false claims resulting in damages of $755.54.</adversefindings><outcome>The district court imposed treble damages of $2266.62 and statutory penalties of $1,177,000.</outcome>

# Example prompt    prompt = f"""{anthropic.HUMAN_PROMPT}: here's a research article extract in <article> tags <article>{text}<article>    {anthropic.HUMAN_PROMPT}: As an expert researcher, peer reviewer and principal investigator, read and understand the article then present the key findings and supporting arguments in bullet points.        \\n\\n{anthropic.AI_PROMPT}:\\n\\nsummary of effective dissemination of this research:"""