mediapipe_decision

Google's MediaPipe Decision Maker for Dart and Flutter. Ask a yes-or-no, choice or score question about a piece of text and get Google's answer with calibrated probabilities, in one forward pass of a small model rather than by generating text. Every call runs Google's official MediaPipe pipeline.

Platforms

Task	Class	Android	iOS	macOS arm64	Linux x64	Windows x64	Web
Decision Maker	DecisionMaker	✓	✓	✓	✓	✓	✓

The runtimes are Google's MediaPipe 1.2.0: its per-family decision C library (its nightly build of October 18, 2026), which this package's build hook downloads and checks against its SHA-256 on Android 9+, iOS 15+, macOS 14+, Linux and Windows, on the CPU; and @mediapipe/tasks-decision 1.2.0-rc.20261018 in browsers, on the GPU delegate. Google's browser runtime fails every evaluation on the CPU delegate and on browsers without a hardware WebGPU adapter (UP-049), so queryDecisionMakerCapabilities() offers browsers only the GPU, and only on such an adapter; there it answers as the desktop library does.

Google's browser runtime fails with some models: queryDecisionMakerCapabilities(model) says where a model runs, and create refuses one the runtime here cannot before downloading it. In WebKit, the engine of Safari and of every browser on iOS, it embeds every text as zeros with both EmbeddingGemma 2 models, so every option scores the same (UP-054); in every browser it aborts while it creates the task with either GLiNER2.5-Decide model (UP-055). queryDecisionMakerCapabilities(model) reports both, and Laya runs in every browser with a hardware WebGPU adapter. The browser runtime also ignores normalizePrior and scoringMode (UP-056).

Installation

Add the package from pub.dev, from your app's root:

flutter pub add mediapipe_decision

This adds mediapipe_decision: ^0.1.3 to your app's pubspec.yaml. mediapipe_core comes with it, and mediapipe_decision.dart exports its types, so you do not add or import core yourself.

Quick start

import 'package:mediapipe_decision/mediapipe_decision.dart';

Future<void> decide() async {
  final capabilities = await queryDecisionMakerCapabilities();
  final task = await DecisionMaker.create(
    DecisionMakerOptions(
      model: DecisionModels.layaS256,
      // The CPU natively, the GPU in browsers.
      delegate: capabilities.supportedDelegates.first,
    ),
  );
  try {
    const text = 'My order arrived broken and I want my money back.';
    final refund = await task.evaluateBoolean(
      text,
      BooleanQuestion('The customer wants a refund.'),
    );
    final topic = await task.evaluateChoice(
      text,
      ChoiceQuestion({
        'shipping': 'A problem with delivery or a damaged package',
        'billing': 'A question about a charge or a refund',
        'other': 'Anything else',
      }),
    );
    final mood = await task.evaluateScore(
      text,
      ScoreQuestion(['very unhappy', 'unhappy', 'neutral', 'happy']),
    );
    print('${refund.value} ${topic.selectedKey} ${mood.expectedScore}');
  } finally {
    await task.dispose();
  }
}

DecisionModels pins Google's decision models: Laya and GLiNER2.5-Decide (layaS256, layaS512, glinerS256, glinerS512: 678 MB to 1.08 GB), and EmbeddingGemma 2, which answers as fast at a fraction of the download: embeddingGemma2Text (165 MB) and embeddingGemma2TextVision (388 MB), which answer the same, everywhere but WebKit (UP-054 above). They are large, so an app usually downloads one on first use rather than bundling it: set ModelStore.allowDownloads = true before create, or pass modelPath. In browsers, modelPath can be the model's URL in Google's bucket, which Google's runtime then fetches itself.

Questions and answers

• BooleanQuestion(condition, threshold:, temperature:, normalizePrior:) answers with BooleanResult(value, probabilityTrue, confidence).
• ChoiceQuestion(criteria, instructions:, temperature:, scoringMode:, normalizePrior:), where criteria maps each option's key to a description, answers with ChoiceResult(selectedKey, probabilities, confidence, predictionSet). The probabilities come in the question's order on every platform, and the prediction set is Google's Python rule: the most likely keys until 90% is covered.
• ScoreQuestion(rubric, instructions:, temperature:), lowest level first, answers with ScoreResult(expectedScore, probabilities, confidence, selectedKey).

Each has a batch form (evaluateBooleanBatch and so on) with an optional sharedPrefix. Calls run one at a time, in call order.

Libraries

mediapipe_decision

Google's MediaPipe Decision Maker: yes-or-no, choice and score questions about a text, answered with calibrated probabilities on Android, iOS, macOS, Linux, Windows and the web.

mediapipe_decision_web

Flutter's registration of Google's browser runtime behind Decision Maker. Not for applications: import mediapipe_decision.dart.

models

The verified official models of the Decision Maker, DecisionModels, which mediapipe_decision.dart also exports. bundle_models reads them from this library alone.

platform_interface

Where the browser plugin plugs Google's JavaScript runtime into Decision Maker.