逐行搜索

export TYPESAFE_API_KEY="your-key-here"

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

import os
import urllib.request
from pathlib import Path

from cooksafe import JsonCache
from typesafe_sdk import Choice, Noul, NoulCriteria, TypeSafeClient

TYPESAFE_MODEL = "jev-1.12"

client = TypeSafeClient(
    api_key=os.environ.get("TYPESAFE_API_KEY", "cache-only"), timeout=120.0
)
json_cache = JsonCache(Path("json_cache.json"))

GIST = (
    "https://gist.githubusercontent.com/eugene-shvarts/900632789a24983d5678ffd508dd01f6"
    "/raw/cf9c2ab422d568deade949ef0a06bed6896964b9/github-tos.txt"
)


@json_cache
def fetch_document(url: str) -> str:
    request = urllib.request.Request(
        url, headers={"User-Agent": "typesafe-cookbook/1.0"}
    )
    with urllib.request.urlopen(request) as response:
        return response.read().decode()


LINES = fetch_document(GIST).splitlines()

def line_id(i: int) -> str:
    return f"L{i:03d}"


DOCUMENT = "\n".join(f"{line_id(i)}| {line}" for i, line in enumerate(LINES))

def where_question(query: str) -> Choice:
    return Choice(
        instructions=f'Which line of the document contains the answer to: "{query}"?',
        criteria={line_id(i): None for i in range(len(LINES))},
    )

def exists_question(query: str) -> Noul:
    return Noul(
        instructions=f'Does any line of the document address or answer: "{query}"?',
        criteria=NoulCriteria(
            true="At least one line of the document states or directly implies the answer",
            false="No line of the document addresses this",
        ),
    )

@json_cache
def _find(
    model: str,
    state: str,
    where: Choice,
    exists: Noul,
) -> dict:
    response = client.system_one(
        state=state,
        questions={"where": where, "exists": exists},
        model=model,
    )
    probabilities = response.answers["where"].probabilities
    return {
        "exists": response.answers["exists"].noul,
        "relevance": [probabilities.get(line_id(i), 0.0) for i in range(len(LINES))],
    }


def find(query: str) -> dict:
    return _find(
        TYPESAFE_MODEL,
        DOCUMENT,
        where_question(query),
        exists_question(query),
    )

FOUND, ABSENT = 0.7, 0.35  # present answers typically read >=0.9, absent <=0.05


def verdict(exists: float) -> str:
    if exists >= FOUND:
        return "answered in this document"
    return "not in this document" if exists < ABSENT else "partially addressed"


def show(query: str, top: int = 4) -> dict:
    result = find(query)
    print(f'"{query}"')
    print(f"  exists {result['exists']:.2f} -> {verdict(result['exists'])}")
    ranked = sorted(
        range(len(LINES)), key=lambda i: result["relevance"][i], reverse=True
    )
    for i in ranked[:top]:
        bar = "#" * max(1, round(result["relevance"][i] * 12))
        preview = LINES[i][:58].rstrip()
        print(f"  {line_id(i)}  {result['relevance'][i]:.2f}  {bar:<12}  {preview}")
    return result

print(f"{len(LINES)} lines, {len(DOCUMENT):,} characters\n")
show("who owns the code I upload?")
print()
show("can GitHub kick me off the platform without warning?")
print()
show("do I have to take disputes to arbitration?", top=2)
print()
show("can minors use GitHub with parental permission?", top=2)