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:
"""CosVec 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
)
The regex finds candidate values in the document, CosVec picks one, and downstream
code normalizes it and acts on it.