httpx, which gives sync and async
from one API — so AsyncTokz is not a second HTTP stack with its own timeout
semantics to keep in step. Only decide_local needs more, through
pip install "tokz[local]".
Decide
tokz.decide(inputs, decisions, *, model=None, timeout=60.0) and
tokz.list_decision_models(). See the Decisions API. decide is never
retried, because a retry could bill twice.
Tokz(api_key, base_url="https://api.tokz.dev", client=None) accepts your own
httpx.Client for proxies or tests; a client you pass in is not closed for you. Use
with Tokz(...) as tokz: or call close().
Fine tunes
Call a fine tune by name. Needs 0.6+. Up to 16 texts on our servers, and the answer is always underdecision. For a multi-label model read selected, because best
names a label even when selected is empty.
decide_local runs the same model on this machine for free, with the same result shape.
~/.cache/tokz on every OS and verifies its hashes.
TOKZ_CACHE_DIR moves the cache. After that it works offline, and asks the server about once
an hour whether the model still exists. The extra keeps onnxruntime at 1.26.0 or older,
because newer versions change the scores. See Fine Tune.
Async
decide_local runs on a worker thread.
Errors
Both are importable from
tokz.