Decision models

A decision model scores predefined answers instead of generating text. When you need to classify data and already know the possible answers, these models are a good choice.

Load a model

NobodyWho currently supports only Laya GGUF decision models.

Create a decision model directly from its path, or pass a NobodyWhoModel. Await the create call immediately.

var decision = await NobodyWhoDecision.create(
    "hf://ggml-org/Laya-GGUF/Laya-Q8_0.gguf",
    {"n_ctx": 1024}
)
if decision == null:
    push_error("Could not load decision model")
    return

You can also create and pass a shared model:

var model = await NobodyWhoModel.create("res://model.gguf", {})
var decision = await NobodyWhoDecision.create(model, {"n_ctx": 1024})

Make a decision

Call decide with a state and a dictionary of question IDs. State can be a String, Dictionary, or Array.

var state = {"message": "I was charged twice. Please refund the duplicate payment."}
var questions = {
    "department": {
        "type": "choice",
        "instructions": "Which team should handle this?",
        "criteria": {"billing": "Payments and refunds", "technical": "Bugs and login problems"},
    },
    "refund": {
        "type": "noul",
        "instructions": "Is a refund requested?",
    },
    "urgency": {
        "type": "score",
        "instructions": "How urgent is this?",
        "criteria": ["can wait", "soon", "urgent"],
    },
}
var response = await decision.decide(state, questions)
if response == null:
    push_error("Decision failed")
    return
print(response["answers"]["department"]["choice"])
print(response["usage"]["output_tokens"]) # Always 0

Select an option with choice

Use choice when one of a set of named options is the answer. Its criteria dictionary maps option IDs to descriptions. The answer includes the selected ID and probabilities for each option.

Check a condition with noul

Use noul for a yes-or-no question. Its noul value is the probability that the answer is yes, from 0 to 1. Criteria are optional.

Rate content with score

Use score for an ordered scale. Provide two to ten descriptions in criteria, from lowest to highest. The score is the probability-weighted average of zero-based levels, not a probability. Its legend maps level IDs to descriptions.

Read the return values

decide returns a dictionary with answers and usage, or null on failure.

• answers maps question IDs to answer dictionaries. Each has a type. choice includes choice, probabilities, and confidence; score includes score, legend, probabilities, and confidence; noul includes noul.
• confidence indicates how concentrated the probabilities are. It is available for choices and scores, and does not guarantee correctness.
• usage contains input_tokens and output_tokens. Decisions run non-generatively, so output_tokens is always 0.