perf(android): replace flutter_gemma with llamadart — 150 MB → 42 MB APK

.github/workflows/release.yml

@@ -34,8 +34,10 @@ jobs:
       - name: Generate ObjectBox bindings
         run: dart run build_runner build --delete-conflicting-outputs
 
-      - name: Build release APK
-        run: flutter build apk --release --split-per-abi --target-platform android-arm64,android-x64
+      - name: Build release APKs
+        run: |
+          flutter build apk --flavor lite -t lib/main_lite.dart --release --split-per-abi --target-platform android-arm64,android-x64
+          flutter build apk --flavor full -t lib/main_full.dart --release --split-per-abi --target-platform android-arm64,android-x64
 
       - name: Rename APKs with version
         run: |

android/app/build.gradle.kts

@@ -20,10 +20,7 @@ android {
     }
 
     defaultConfig {
-        // TODO: Specify your own unique Application ID (https://developer.android.com/studio/build/application-id.html).
         applicationId = "dev.koshika.koshika"
-        // You can update the following values to match your application needs.
-        // For more information, see: https://flutter.dev/to/review-gradle-config.
         minSdk = flutter.minSdkVersion
         targetSdk = flutter.targetSdkVersion
         versionCode = flutter.versionCode
@@ -32,8 +29,6 @@ android {
 
     buildTypes {
         release {
-            // TODO: Add your own signing config for the release build.
-            // Signing with the debug keys for now, so `flutter run --release` works.
             signingConfig = signingConfigs.getByName("debug")
             isMinifyEnabled = true
             isShrinkResources = true
@@ -48,6 +43,32 @@ android {
             excludes += "**/libimagegenerator_gpu.so"
         }
     }
+
+    flavorDimensions += "appType"
+    productFlavors {
+        create("lite") {
+            dimension = "appType"
+            applicationIdSuffix = ".lite"
+            versionNameSuffix = "-lite"
+        }
+        create("full") {
+            dimension = "appType"
+        }
+    }
+}
+
+// Strip llama.cpp native libs from the lite flavor APK.
+// This runs after packaging to remove AI inference libraries,
+// keeping the lite APK small (~15MB smaller).
+androidComponents {
+    onVariants(selector().withFlavor("appType" to "lite")) { variant ->
+        variant.packaging.jniLibs.excludes.addAll(listOf(
+            "**/libllama.so",
+            "**/libggml*.so",
+            "**/libmtmd.so",
+            "**/libllamadart.so",
+        ))
+    }
 }
 
 flutter {

android/app/proguard-rules.pro

@@ -1,7 +1,3 @@
-# MediaPipe optional proto classes (not needed at runtime)
--dontwarn com.google.mediapipe.proto.**
--dontwarn com.google.mediapipe.framework.GraphProfiler
-
 # ML Kit optional language model classes (only Latin script is used)
 -dontwarn com.google.mlkit.vision.text.chinese.**
 -dontwarn com.google.mlkit.vision.text.devanagari.**

lib/constants/ai_prompts.dart

@@ -3,12 +3,11 @@
 /// Keeping prompts here (rather than inlined in service files) makes them
 /// easy to review, iterate, and A/B test without touching service logic.
 abstract final class AiPrompts {
-  /// System prompt for the Gemma chat model.
+  /// System prompt injected before every user query.
   ///
-  /// Injected as a [Message.systemInfo] turn before every user query.
   /// Lab data context is added separately to the user turn so that
   /// small (1B-param) models cannot ignore it.
-  static const String gemmaSystemPrompt = '''
+  static const String systemPrompt = '''
 You are Koshika AI, a helpful on-device health assistant built into the Koshika app. You help users understand their lab report results.
 
 CRITICAL RULES:

lib/main.dart

@@ -1,7 +1,6 @@
 import 'dart:ui';
 
 import 'package:flutter/material.dart';
-import 'package:flutter_gemma/flutter_gemma.dart';
 
 import 'screens/chat_screen.dart';
 import 'screens/dashboard_screen.dart';
@@ -11,22 +10,31 @@ import 'screens/settings_screen.dart';
 import 'screens/splash_screen.dart';
 import 'services/objectbox_store.dart';
 import 'services/biomarker_dictionary.dart';
-import 'services/embedding_service.dart';
-import 'services/gemma_service.dart';
+import 'services/llm_embedding_service.dart';
+import 'services/llm_service.dart';
 import 'services/vector_store_service.dart';
 import 'theme/app_colors.dart';
 import 'theme/koshika_design_system.dart';
 
 /// Global references — initialized in SplashScreen before navigation.
 late ObjectBoxStore objectbox;
 late BiomarkerDictionary biomarkerDictionary;
-late GemmaService gemmaService;
-late EmbeddingService embeddingService;
+late LlmService llmService;
+late LlmEmbeddingService embeddingService;
 late VectorStoreService vectorStoreService;
 
-Future<void> main() async {
+/// Whether AI features are enabled. Set by the entry point
+/// (main_full.dart vs main_lite.dart).
+bool kAiEnabled = true;
+
+/// Default entry point — full flavor with AI enabled.
+/// For flavor-specific builds, use main_full.dart or main_lite.dart.
+Future<void> main() async => appMain(aiEnabled: true);
+
+/// Shared app bootstrap — called from entry-point files.
+Future<void> appMain({required bool aiEnabled}) async {
   WidgetsFlutterBinding.ensureInitialized();
-  await FlutterGemma.initialize(maxDownloadRetries: 5);
+  kAiEnabled = aiEnabled;
   runApp(const KoshikaApp());
 }
 
@@ -123,19 +131,19 @@ class HomeScreen extends StatefulWidget {
 class _HomeScreenState extends State<HomeScreen> {
   int _currentIndex = 0;
 
+  /// Screens available depends on whether AI is enabled.
+  List<Widget> get _screens => kAiEnabled
+      ? const [
+          DashboardScreen(),
+          ReportsScreen(),
+          ChatScreen(),
+          SettingsScreen(),
+        ]
+      : const [DashboardScreen(), ReportsScreen(), SettingsScreen()];
+
   Widget _buildCurrentScreen() {
-    switch (_currentIndex) {
-      case 0:
-        return const DashboardScreen();
-      case 1:
-        return const ReportsScreen();
-      case 2:
-        return const ChatScreen();
-      case 3:
-        return const SettingsScreen();
-      default:
-        return const DashboardScreen();
-    }
+    if (_currentIndex < _screens.length) return _screens[_currentIndex];
+    return const DashboardScreen();
   }
 
   @override
@@ -175,21 +183,23 @@ class _HomeScreenState extends State<HomeScreen> {
                       label: 'Reports',
                       onTap: () => setState(() => _currentIndex = 1),
                     ),
+                    if (kAiEnabled)
+                      _NavItem(
+                        index: 2,
+                        currentIndex: _currentIndex,
+                        icon: Icons.chat_outlined,
+                        activeIcon: Icons.chat,
+                        label: 'Chat',
+                        onTap: () => setState(() => _currentIndex = 2),
+                      ),
                     _NavItem(
-                      index: 2,
-                      currentIndex: _currentIndex,
-                      icon: Icons.chat_outlined,
-                      activeIcon: Icons.chat,
-                      label: 'Chat',
-                      onTap: () => setState(() => _currentIndex = 2),
-                    ),
-                    _NavItem(
-                      index: 3,
+                      index: kAiEnabled ? 3 : 2,
                       currentIndex: _currentIndex,
                       icon: Icons.settings_outlined,
                       activeIcon: Icons.settings,
                       label: 'Settings',
-                      onTap: () => setState(() => _currentIndex = 3),
+                      onTap: () =>
+                          setState(() => _currentIndex = kAiEnabled ? 3 : 2),
                     ),
                   ],
                 ),

lib/main_full.dart

@@ -0,0 +1,4 @@
+import 'main.dart';
+
+/// Entry point for the full flavor — includes all AI features.
+Future<void> main() async => appMain(aiEnabled: true);

lib/main_lite.dart

@@ -0,0 +1,4 @@
+import 'main.dart';
+
+/// Entry point for the lite flavor — no AI, no model downloads.
+Future<void> main() async => appMain(aiEnabled: false);

lib/models/biomarker_result.dart

@@ -61,8 +61,9 @@ class BiomarkerResult {
   @Index()
   DateTime testDate;
 
-  /// Embedding vector for RAG (stored as float list, used with HNSW later)
+  /// Embedding vector for RAG (384-dim from bge-small-en-v1.5).
   @Property(type: PropertyType.floatVector)
+  @HnswIndex(dimensions: 384)
   List<double>? embedding;
 
   BiomarkerResult({

lib/models/llm_model_config.dart

@@ -0,0 +1,110 @@
+/// Configuration for a downloadable GGUF model (curated or custom).
+class LlmModelConfig {
+  final String id;
+  final String name;
+  final String downloadUrl;
+  final int estimatedSizeMB;
+  final String description;
+  final bool isCustom;
+
+  const LlmModelConfig({
+    required this.id,
+    required this.name,
+    required this.downloadUrl,
+    required this.estimatedSizeMB,
+    required this.description,
+    this.isCustom = false,
+  });
+
+  /// Derive the on-disk filename from the download URL.
+  String get filename {
+    final uri = Uri.parse(downloadUrl);
+    return uri.pathSegments.isNotEmpty ? uri.pathSegments.last : '$id.gguf';
+  }
+
+  /// Human-readable size string.
+  String get formattedSize {
+    if (estimatedSizeMB == 0) return 'Unknown';
+    if (estimatedSizeMB >= 1000) {
+      return '${(estimatedSizeMB / 1000).toStringAsFixed(1)} GB';
+    }
+    return '~$estimatedSizeMB MB';
+  }
+}
+
+/// Registry of curated chat models + factory for custom GGUF URLs.
+abstract final class LlmModelRegistry {
+  static const defaultModelId = 'qwen3-0.6b';
+
+  static const List<LlmModelConfig> curated = [
+    LlmModelConfig(
+      id: 'smollm2-360m',
+      name: 'SmolLM2 360M',
+      downloadUrl:
+          'https://huggingface.co/bartowski/SmolLM2-360M-Instruct-GGUF/resolve/main/SmolLM2-360M-Instruct-Q4_K_M.gguf',
+      estimatedSizeMB: 230,
+      description: 'Smallest, fastest load, lowest RAM',
+    ),
+    LlmModelConfig(
+      id: 'qwen3-0.6b',
+      name: 'Qwen3 0.6B',
+      downloadUrl:
+          'https://huggingface.co/bartowski/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B-Q4_K_M.gguf',
+      estimatedSizeMB: 430,
+      description: 'Balanced quality and size',
+    ),
+    LlmModelConfig(
+      id: 'llama3.2-1b',
+      name: 'Llama 3.2 1B',
+      downloadUrl:
+          'https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf',
+      estimatedSizeMB: 770,
+      description: 'Strong instruction following',
+    ),
+    LlmModelConfig(
+      id: 'gemma3-1b',
+      name: 'Gemma 3 1B',
+      downloadUrl:
+          'https://huggingface.co/bartowski/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it-Q4_K_M.gguf',
+      estimatedSizeMB: 780,
+      description: 'Most capable curated model',
+    ),
+  ];
+
+  /// Embedding model — fixed, not user-selectable.
+  static const embeddingModel = LlmModelConfig(
+    id: 'bge-small-en',
+    name: 'bge-small-en-v1.5',
+    downloadUrl:
+        'https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/resolve/main/bge-small-en-v1.5-q8_0.gguf',
+    estimatedSizeMB: 67,
+    description: 'Semantic search model',
+  );
+
+  /// Create a config for a user-provided GGUF URL.
+  static LlmModelConfig custom({
+    required String name,
+    required String downloadUrl,
+  }) {
+    return LlmModelConfig(
+      id: 'custom',
+      name: name,
+      downloadUrl: downloadUrl,
+      estimatedSizeMB: 0,
+      description: 'Custom GGUF model',
+      isCustom: true,
+    );
+  }
+
+  /// Look up a curated model by id. Returns null for unknown ids.
+  static LlmModelConfig? findById(String id) {
+    for (final m in curated) {
+      if (m.id == id) return m;
+    }
+    return null;
+  }
+
+  /// The default curated model.
+  static LlmModelConfig get defaultModel =>
+      findById(defaultModelId) ?? curated.first;
+}

lib/models/model_info.dart

@@ -26,7 +26,7 @@ class ModelInfo {
   final int estimatedSizeMB;
   final ModelStatus status;
 
-  /// Download progress as an integer 0–100 (from flutter_gemma callback).
+  /// Download progress as an integer 0–100.
   final int downloadProgress;
   final String? errorMessage;
 

lib/models/retrieval_result.dart

@@ -0,0 +1,21 @@
+/// App-owned retrieval result for the RAG pipeline.
+///
+/// Replaces flutter_gemma's RetrievalResult so the pipeline is
+/// decoupled from the inference engine.
+class RetrievalResult {
+  final String id;
+  final String content;
+
+  /// JSON-encoded metadata (biomarkerKey, reportId, flag, testDate, labName).
+  final String? metadata;
+
+  /// Cosine similarity score in [0, 1].
+  final double score;
+
+  const RetrievalResult({
+    required this.id,
+    required this.content,
+    this.metadata,
+    this.score = 0.0,
+  });
+}

lib/objectbox-model.json

@@ -94,7 +94,9 @@
         {
           "id": "16:557227151494494808",
           "name": "embedding",
-          "type": 28
+          "indexId": "6:3191674845316224774",
+          "type": 28,
+          "flags": 8
         }
       ],
       "relations": []
@@ -268,7 +270,7 @@
     }
   ],
   "lastEntityId": "5:1397208082251365964",
-  "lastIndexId": "5:2477129363995053950",
+  "lastIndexId": "6:3191674845316224774",
   "lastRelationId": "0:0",
   "lastSequenceId": "0:0",
   "modelVersion": 5,