Skip to main content

Decision models

A decision model scores predefined answers instead of generating text. NobodyWho currently supports only Laya GGUF decision models.

Load a model​

import { Decision } from "react-native-nobodywho";

const decision = await Decision.fromPath({
  modelPath: "hf://ggml-org/Laya-GGUF/Laya-Q8_0.gguf",
});

You can also create a decision model from a loaded model:

import { Decision, Model } from "react-native-nobodywho";

const model = await Model.load({ modelPath: "/path/to/model.gguf" });
const decision = new Decision({ model, contextSize: 1024 });

Make a decision​

Pass text or any JSON value as state. questions is a record keyed by question ID. Each question has instructions and criteria appropriate to its type.

import { Decision } from "react-native-nobodywho";

async function classify() {
  const decision = await Decision.fromPath({
    modelPath: "hf://ggml-org/Laya-GGUF/Laya-Q8_0.gguf",
  });
  const response = await decision.decide({
    state: { message: "I was charged twice. Please refund the duplicate payment." },
    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"],
      },
    },
  });

  console.log(response.answers.department);
  console.log(response.answers.refund);
  console.log(response.answers.urgency);
  console.log(response.usage.input_tokens, response.usage.output_tokens); // output_tokens is always 0
  decision.destroy();
}

void classify();

Choose a question type​

Select an option with choice​

Provide a record of option IDs and descriptions in criteria. The answer's choice is the selected ID; probabilities gives the probability for each option.

Check a condition with noul​

Use noul for a yes-or-no judgment. Its noul value is the probability that the answer is yes, from 0 to 1. Optional criteria can provide additional labels or descriptions.

Rate content with score​

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

Read the return values​

decide returns a DecisionResponse with answers and usage. Each answer is a DecisionAnswer matching its question type. choice and score answers include confidence, a value from 0 to 1. score also includes legend; noul contains only its probability. High confidence does not guarantee a correct answer.

usage.input_tokens counts input tokens evaluated across questions. usage.output_tokens is always 0 because decision models do not generate text. Call decision.destroy() when finished to free native resources.