xuanli199
duoduo
A gamified, AI-powered Flutter app that lets you create custom question decks from text, images, and shared content to learn with XP, streaks, achievements, and multiple quiz modes.
Why it is worth attention
It provides a typed, native Flutter API for semantic video search using natural language, speech, text, and imagery, with streaming uploads and full cancellation support.
Who it is for
- Flutter mobile developers
- Developers building video-centric applications
- Teams seeking multimodal search in their apps
- Developers needing controlled, app-owned credential management
Use cases
- Search video libraries by spoken words or displayed text via ASR/OCR
- Find visual moments in videos using natural language queries
- Upload videos from device storage or camera with live progress and cancellation
- Integrate multimodal search into existing Flutter apps without custom login UI
Strengths
- Typed, small Dart API with focused resource classes (auth, searches, collections, etc.)
- Streamed uploads that avoid loading entire files into memory
- Per-operation cancellation tokens for reliable lifecycle management
- App-owned runtime credentials with no imposed login screen
Considerations
- Flutter Web is not supported in the current release
- Multipart upload is experimental and requires explicit opt-in
- Requires Flutter 3.44+ and Dart 3.12+, limiting compatibility with older projects
README quick start
VModal for Flutter Give your Android and iOS apps a multimodal memory. Upload video. Find moments by meaning, speech, text, or imagery.Keep the experience fast, native, and 100% Flutter.
Turn every video library into an experience your users can explore.
Build the feature people remember
VModal brings multimodal video search and mobile-friendly uploads to Dart with a small, typed API. Your app owns the interface; the SDK handles the VModal gateway, request models, responses, upload streams, progress, and cancellation.
| Your Flutter experience | VModal gives you |
|---|---|
| “Find the cyclist in the red jacket” | Semantic video and image search |
| Search words spoken or shown on screen | ASR and OCR search sources |
| Upload from a picker or camera flow | Streamed, signed uploads with live progress |
| A cancel button that really cancels | Per-operation cancellation tokens |
| Collection and indexing screens | Typed collection, index, usage, and image resources |
| Login and account switching your way | App-owned runtime credentials—no login UI imposed |
Start in minutes
The public package source is available on GitHub. Add it to your app:
dependencies:
vmodal_sdk_flutter:
git:
url: https://github.com/v-modal/vmodal_sdk_flutter.git
ref: main
Then run:
flutter pub get
Create one client from the API key already loaded by your authenticated app:
import 'package:vmodal_sdk_flutter/vmodal_sdk_flutter.dart';
final keys = MutableApiKeyProvider(runtimeApiKey);
final vmodal = VmodalClient(
config: SdkConfig(apiKeyProvider: keys),
);
The SDK never owns your login screen or persists your API key. It receives an in-memory credential from your application at runtime.
Search video with natural language
final groups = await vmodal.collections.listGroups(mode: 'vid_file');
if (groups.data.isEmpty) {
throw StateError('No video collection exists for this API key');
}
final group = groups.data.first;
final version = group.latestLancedbVersion;
if (version == null) {
throw StateError('The collection has no searchable LanceDB version');
}
final results = await vmodal.searches.searchVideo(
SearchRequest(
queryText: 'the cyclist crossing the bridge at sunset',
groupName: group.groupName,
searchSources: const ['image'],
versionLancedb: ver
Description
V- Modal AI: Search anything anywhere SDK Flutter
Related repositories
Similar projects matched by category, topics, and programming language.