Mobile RAG Engine

Production-ready, fully local RAG (Retrieval-Augmented Generation) engine for Flutter.

Powered by a Rust core, it delivers lightning-fast vector search and embedding generation directly on the device. No servers, no API costs, no latency.

---

Why this package?

No Rust Installation Required

You do NOT need to install Rust, Cargo, or Android NDK.

This package includes pre-compiled binaries for iOS, Android, and macOS. Just pub add and run.

Performance

Feature	Pure Dart	Mobile RAG Engine (Rust)
Tokenization	Slow	10x Faster (HuggingFace tokenizers)
Vector Search	O(n)	O(log n) (HNSW Index)
Memory Usage	High	Optimized (Zero-copy FFI)

100% Offline & Private

Data never leaves the user's device. Perfect for privacy-focused apps (journals, secure chats, enterprise tools).

---

Features

End-to-End RAG Pipeline

One package, complete pipeline. From any document format to LLM-ready context.

Key Features

Category	Features
Document Input	PDF, DOCX, Markdown, Plain Text with smart dehyphenation
Chunking	Semantic chunking, Markdown structure-aware, header path inheritance
Search	HNSW vector + BM25 keyword hybrid search with RRF fusion
Storage	SQLite persistence, HNSW Index persistence (fast startup), connection pooling, resumable indexing
Collections	Collection-scoped ingest/search/rebuild via inCollection('id')
Performance	Rust core, 10x faster tokenization, thread control, memory optimized
Context	Token budget, adjacent chunk expansion, single source mode

---

Requirements

Platform	Minimum Version
iOS	13.0+
Android	API 21+ (Android 5.0 Lollipop)
macOS	10.15+ (Catalina)

ONNX Runtime is bundled automatically via the onnxruntime plugin. No additional native setup required.

---

Installation

1. Add the dependency

dependencies:
  mobile_rag_engine:

2. Download Model Files

# Create assets folder
mkdir -p assets && cd assets

# Download BGE-m3 model (INT8 quantized, multilingual)
curl -L -o model.onnx "https://huggingface.co/Teradata/bge-m3/resolve/main/onnx/model_int8.onnx"
curl -L -o tokenizer.json "https://huggingface.co/BAAI/bge-m3/resolve/main/tokenizer.json"

See Model Setup Guide for alternative models and production deployment strategies.

---

Quick Index

Features

• Adjacent Chunk Retrieval - Fetch surrounding context.
• Index Management - Stats, persistence, and recovery.
• Markdown Chunker - Structure-aware text splitting.
• Prompt Compression - Reduce token usage.
• Search by Source - Filter results by document.
• Search Strategies - Tune ranking and retrieval.

Guides

• Quick Start - Setup in 5 minutes.
• Graph v2.1 Design - Graph-enhanced retrieval implementation plan.
• Graph v2.1 Risk Register - Predicted risks and mitigation assumptions.
• Model Setup - Choosing and downloading models.
• Troubleshooting - Common fixes.
• FAQ - Frequently asked questions.

Testing

• Unit Testing - Mocking for isolated tests.

---

Initialize the engine once in your main() function:

Initialization Parameters

await MobileRag.initialize(
  tokenizerAsset: 'assets/tokenizer.json',
  modelAsset: 'assets/model.onnx',
  deferIndexWarmup: true,
);

// Before first search:
if (!MobileRag.instance.isIndexReady) {
  await MobileRag.instance.warmupFuture;
}

Then use it anywhere in your app:

class MySearchScreen extends StatelessWidget {
  Future<void> _search() async {
    // 2. Add Documents (auto-chunked & embedded)
    await MobileRag.instance.addDocument(
      'Flutter is a UI toolkit for building apps.',
    );
    await MobileRag.instance.addDocument(
      'Flutter is a UI toolkit for building apps.',
    );
    // Indexing is automatic! (Debounced 500ms)
    // Optional: await MobileRag.instance.rebuildIndex(); // Call if you want it done NOW
  
    // 3. Search with LLM-ready context
    final result = await MobileRag.instance.search(
      'What is Flutter?', 
      tokenBudget: 2000,
    );
    
    print(result.context.text); // Ready to send to LLM
  }
}

Multi-Collection (v1)

Use collection scopes when you want independent rebuild boundaries per category.

final business = MobileRag.instance.inCollection('business');
final travel = MobileRag.instance.inCollection('travel');

await business.addDocument('Quarterly planning memo...');
await travel.addDocument('Kyoto itinerary...');

if (!travel.isIndexReady) {
  await travel.warmupFuture;
}
final travelHits = await travel.searchHybrid('itinerary');
print(travelHits.length);

If you do not specify a collection, the engine uses the default __default__ collection for backward compatibility.

Advanced Usage: For fine-grained control, you can still use the low-level APIs (initTokenizer, EmbeddingService, SourceRagService) directly. See the API Reference.

---

Model Options

Model	Dimensions	Size	Max Tokens	Languages
Teradata/bge-m3 (INT8)	1024	~542 MB	8,194	100+ (multilingual)
all-MiniLM-L6-v2	384	~25 MB	256	English only

Important: The embedding dimension must be consistent across all documents. Switching models requires re-embedding your entire corpus.

Custom Models: Export any Sentence Transformer to ONNX:

pip install optimum[exporters]
optimum-cli export onnx --model sentence-transformers/YOUR_MODEL ./output

See Model Setup Guide for deployment strategies and troubleshooting.

---

Documentation

Guide	Description
Quick Start	Get started in 5 minutes
Model Setup	Model selection, download, deployment strategies
FAQ	Frequently asked questions
Troubleshooting	Problem solving guide

---

Sample App

Check out the example application using this package. This desktop app demonstrates full RAG pipeline integration with an LLM (Gemma 2B) running locally on-device.

mobile-ondevice-rag-desktop

---

Contributing

Bug reports, feature requests, and PRs are all welcome!

License

This project is licensed under the MIT License.