Извлечение предварительно разобранных значений

pip install ipython phonenumbers "typesafe-sdk>=0.5.7" cooksafe --extra-index-url https://pypi.typesafe.ai/

import os
import re
from decimal import Decimal
from pathlib import Path

import phonenumbers
from cooksafe import JsonCache, make_playground_link
from IPython.display import Markdown, display
from typesafe_sdk import Choice, Noul, TypeSafeClient

TYPESAFE_MODEL = "jev-1.12"
NONE = "none"  # the escape hatch on every selection: "none of the candidates fits"

# base_url defaults to https://api.typesafe.ai/ ; the env override points at another deployment.
ts = TypeSafeClient(
    api_key=os.environ.get(
        "TYPESAFE_API_KEY", "cache-only"
    ),  # cached re-renders need no key
    base_url=os.environ.get("TYPESAFE_BASE_URL"),
    timeout=30.0,
)
json_cache = JsonCache(Path("json_cache.json"))

EMAIL_RE = re.compile(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}")
PHONE_RE = re.compile(r"\(?\+?\d[\d\s()\-.]{6,}\d")
MONEY_RE = re.compile(r"[$€£¥]\s?\d[\d,]*(?:\.\d{2})?")


def find(pattern: re.Pattern, text: str) -> list[str]:
    """Code-side candidate finder: recall-tuned regex, deduped, in document order."""
    seen: set[str] = set()
    out: list[str] = []
    for match in pattern.findall(text):
        span = match.strip()
        if span and span not in seen:
            seen.add(span)
            out.append(span)
    return out


@json_cache
def pick(document: str, candidates: list[str], question: str) -> dict:
    """TypeSafe selects which found span plays the role. Returns {choice, confidence}.

    The options ARE the candidate spans, so ``choice`` is a verbatim copy of one of them (or the
    ``none`` hatch) - the model chooses, code owns the string."""
    criteria = {c: None for c in candidates} | {
        NONE: "None of these is the requested value."
    }
    answer = ts.system_one(
        state=document,
        questions={"pick": Choice(instructions=question, criteria=criteria)},
        model=TYPESAFE_MODEL,
    ).answers["pick"]
    return {"choice": answer.choice, "confidence": answer.confidence}


@json_cache
def classify(document: str, question: str, options: list[str]) -> dict:
    """A small Choice over a fixed label set (currency, country, ...). Returns {choice, confidence}."""
    answer = ts.system_one(
        state=document,
        questions={
            "q": Choice(instructions=question, criteria={o: None for o in options})
        },
        model=TYPESAFE_MODEL,
    ).answers["q"]
    return {"choice": answer.choice, "confidence": answer.confidence}


@json_cache
def is_true(document: str, question: str) -> float:
    """A yes/no Noul. Returns P(yes)."""
    return (
        ts.system_one(
            state=document,
            questions={"q": Noul(instructions=question)},
            model=TYPESAFE_MODEL,
        )
        .answers["q"]
        .noul
    )

EMAIL_DOC = """From: Dana Whit <dana.whit@acme-corp.com>
To: billing@acme-corp.com
Cc: orders@acme-corp.com
Reply-To: dana.personal@gmail.com

Hi team - please don't use the billing alias for this one. Send my receipt to my
personal address instead. Thanks, Dana."""

emails = find(EMAIL_RE, EMAIL_DOC)
receipt = pick(
    EMAIL_DOC, emails, "Which email address does the sender want their receipt sent to?"
)
sender = pick(
    EMAIL_DOC, emails, "Which email address did this message come from (the From line)?"
)

print("candidates :", emails)
# code copies the picked value verbatim and normalizes (lowercase); it never re-types it
print(
    f"receipt -> : {receipt['choice'].lower():<28} (conf {receipt['confidence']:.2f})"
)
print(f"sender  -> : {sender['choice'].lower():<28} (conf {sender['confidence']:.2f})")

candidates : ['dana.whit@acme-corp.com', 'billing@acme-corp.com', 'orders@acme-corp.com', 'dana.personal@gmail.com']
receipt -> : dana.personal@gmail.com      (conf 0.98)
sender  -> : dana.whit@acme-corp.com      (conf 1.00)

PHONE_DOC = """Reach our San Francisco office at these numbers: main desk (415) 555-0199,
billing fax (415) 555-0142, and my direct cell (415) 555-0177. Call the cell if it's urgent."""

phones = find(PHONE_RE, PHONE_DOC)
mobile = pick(PHONE_DOC, phones, "Which of these is the direct mobile / cell number?")
region = classify(
    PHONE_DOC,
    "In what country is this office located?",
    ["US", "GB", "DE", "FR", "CA", "AU"],
)

# code copies the picked value and normalizes it with the model-supplied country
parsed = phonenumbers.parse(mobile["choice"], region["choice"])
e164 = phonenumbers.format_number(parsed, phonenumbers.PhoneNumberFormat.E164)

print("candidates :", phones)
print(f"mobile  -> : {mobile['choice']}  (conf {mobile['confidence']:.2f})")
print(f"country -> : {region['choice']}  (conf {region['confidence']:.2f})")
print(f"E.164   -> : {e164}")

candidates : ['(415) 555-0199', '(415) 555-0142', '(415) 555-0177']
mobile  -> : (415) 555-0177  (conf 1.00)
country -> : US  (conf 0.90)
E.164   -> : +14155550177

MONEY_DOC = """Invoice INV-2087.
Subtotal: $1,200.00
Sales tax: $115.50
Total due: $1,315.50
A $50.00 courtesy credit from last month has already been applied."""

amounts = find(MONEY_RE, MONEY_DOC)
currency = classify(
    MONEY_DOC,
    "What currency are these amounts in?",
    ["USD", "EUR", "GBP", "JPY", "CAD"],
)
total = pick(MONEY_DOC, amounts, "Which amount is the total the customer must pay?")
credit = pick(
    MONEY_DOC, amounts, "Which amount is the courtesy credit that was applied?"
)


def to_decimal(value: str) -> Decimal:
    """Copy the picked value and parse the number in code (US grouping/decimal here)."""
    return Decimal(re.sub(r"[^\d.]", "", value))


for label, chosen in [("total due", total), ("credit", credit)]:
    is_credit = is_true(
        MONEY_DOC,
        f"Is the amount {chosen['choice']} a credit or refund to the customer, not a charge?",
    )
    kind = "credit" if is_credit > 0.5 else "charge"
    print(
        f"{label:<10}: {chosen['choice']:<10} -> {to_decimal(chosen['choice'])} {currency['choice']} "
        f"({kind}, P(credit)={is_credit:.2f})"
    )
print("\ncandidates :", amounts)

total due : $1,315.50  -> 1315.50 USD (charge, P(credit)=0.01)
credit    : $50.00     -> 50.00 USD (credit, P(credit)=0.99)

candidates : ['$1,200.00', '$115.50', '$1,315.50', '$50.00']

receipt_criteria = {e: None for e in emails} | {
    NONE: "None of these is the requested value."
}
playground_link = make_playground_link(
    EMAIL_DOC,
    {
        "receipt": Choice(
            instructions="Which email address does the sender want their receipt sent to?",
            criteria=receipt_criteria,
        )
    },
    models=[TYPESAFE_MODEL],
)
display(
    Markdown(
        f"🔗 [Open this thread + selection in the TypeSafe playground]({playground_link})"
    )
)