Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
docs(structured): split decide_batch's keywords by who reads them
Aashish1b6c4c038bbb
diff --git a/docs/structured.md b/docs/structured.mdindex f4a9ce14..61c10ac5 100644--- a/docs/structured.md+++ b/docs/structured.md@@ -141,9 +141,16 @@ values = agent.decide_batch(ticket_texts, schema=Ticket) # values[i] maresults = router.decide_batch(states, schema=Ticket, return_details=True, batch_size=64)```-On a `Router` each state is still routed on its own, so one call can span checkpoints. Keyword-arguments reach `predict_batch`, so `batch_size=`, `model=` and hooks work as they do for `decide`.-`Agent`, `ONNXAgent` and `Router` all have it; a runner without `predict_batch` raises+On a `Router` each state is still routed on its own, so one call can span checkpoints. Which+keywords reach `predict_batch` depends on who reads them. The call-level ones — `batch_size=`,+`hooks=`, `sort_by_length=` — are passed as keywords to `predict_batch`. The routing pins and the+token budget — `model=`, `task=`, `lang=`, `lang_guess=`, `max_len=`, `head_max_len=`, the tuple+`laya/structured.py::_ROUTER_REQUEST_KEYS` names — are read off every *request* by a `Router`, whose+`predict_batch` declares none of them, so `decide_batch` copies them onto each request instead; that+is why `decide_batch(states, schema=..., model="multilingual")` pins a checkpoint the way `decide`+does. On an `Agent`-like runner the split is visible: its `predict_batch` declares `batch_size=`,+`hooks=` and `lang=` but no `model=` and swallows nothing, so `model=` there is a `TypeError`, not a+silent extra keyword. `Agent`, `ONNXAgent` and `Router` all have it; a runner without `predict_batch` raises`TypeError` rather than silently falling back to a loop — call `decide` per state there. Batching can shift borderline argmaxes thesame way `predict_batch` does; the README records the measured speedups for both devices.