[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
upd readme mail application
yichuan520030910320c17899662f3d
diff --git a/README.md b/README.mdindex 2f17ead..c79d703 100755--- a/README.md+++ b/README.md@@ -123,26 +123,81 @@ This ensures the generated files are compatible with your system's protobuf libr### 🔥 Core Features-- **📊 Multiple Distance Functions**: L2, Cosine, MIPS (Maximum Inner Product Search)-- **🏗️ Pluggable Backends**: DiskANN, HNSW/FAISS with unified API-- **🔄 Real-time Embeddings**: Dynamic computation using optimized ZMQ servers-- **📈 Scalable Architecture**: Handles millions of documents on consumer hardware-- **🎯 Graph Pruning**: Advanced techniques for memory-efficient search+- **🔄 Real-time Embeddings** - Eliminate heavy embedding storage with dynamic computation using optimized ZMQ servers and highly optimized search paradigm (overlapping and batching) with highly optimized embedding engine+- **📈 Scalable Architecture** - Handles millions of documents on consumer hardware; the larger your dataset, the more LEANN can save+- **🎯 Graph Pruning** - Advanced techniques to minimize the storage overhead of vector search to a limited footprint+- **🏗️ Pluggable Backends** - DiskANN, HNSW/FAISS with unified API### 🛠️ Technical Highlights--- **Zero-copy operations** for maximum performance-- **SIMD-optimized** distance computations (AVX2/AVX512)-- **Async embedding pipeline** with batched processing-- **Memory-mapped indices** for fast startup-- **Recompute mode** for highest accuracy scenarios+- **🔄 Recompute Mode** - Highest accuracy scenarios while eliminating vector storage overhead+- **⚡ Zero-copy Operations** - Minimize IPC overhead by transferring distances instead of embeddings+- **🚀 High-throughput Embedding Pipeline** - Optimized batched processing for maximum efficiency+- **🎯 Two-level Search** - Novel coarse-to-fine search overlap for accelerated query processing (optional)+- **💾 Memory-mapped Indices** - Fast startup with raw text mapping to reduce memory overhead+- **🚀 MLX Support** - Ultra-fast recompute with quantized embedding models, accelerating building and search by 10-100x### 🎨 Developer Experience- **Simple Python API** - Get started in minutes- **Extensible backend system** - Easy to add new algorithms- **Comprehensive examples** - From basic usage to production deployment-- **Rich debugging tools** - Built-in performance profiling++## Applications on your MacBook++### light weight RAG on your apple email++LEANN can create a searchable index of your Apple Mail emails, allowing you to query your email history using natural language.++#### Quick Start++<details>+<summary><strong>📋 Click to expand: Command Examples</strong></summary>++```bash+# Use default mail path (works for most macOS setups)+python examples/mail_reader_leann.py++# Specify your own mail path+python examples/mail_reader_leann.py --mail-path "/Users/yourname/Library/Mail/V10/..."++# Run with custom index directory+python examples/mail_reader_leann.py --index-dir "./my_mail_index"++# Limit number of emails processed (useful for testing)+python examples/mail_reader_leann.py --max-emails 1000++# Run a single query+python examples/mail_reader_leann.py --query "Find emails about project deadlines"+```++</details>++#### Finding Your Mail Path++<details>+<summary><strong>🔍 Click to expand: How to find your mail path</strong></summary>++The default mail path is configured for a typical macOS setup. If you need to find your specific mail path:++1. Open Terminal+2. Run: `find ~/Library/Mail -name "Messages" -type d | head -5`+3. Use the parent directory(ended with Data) of the Messages folder as your `--mail-path`++</details>++#### Example Queries++<details>+<summary><strong>💬 Click to expand: Example queries you can try</strong></summary>++Once the index is built, you can ask questions like:+- "Show me emails about meeting schedules"+- "Find emails from my boss about deadlines"+- "What did John say about the project timeline?"+- "Show me emails about travel expenses"++</details>+## 📊 Benchmarksdiff --git a/examples/mail_reader_leann.py b/examples/mail_reader_leann.pyindex 8c5c043..b45c687 100644--- a/examples/mail_reader_leann.py+++ b/examples/mail_reader_leann.py@@ -1,6 +1,7 @@import osimport asyncioimport dotenv+import argparsefrom pathlib import Pathfrom typing import List, Anyfrom leann.api import LeannBuilder, LeannSearcher, LeannChat@@ -8,6 +9,9 @@ from llama_index.core.node_parser import SentenceSplitterdotenv.load_dotenv()+# Default mail path for macOS+DEFAULT_MAIL_PATH = "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data"+def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_path: str = "mail_index.leann", max_count: int = -1):"""Create LEANN index from multiple mail data sources.@@ -203,12 +207,30 @@ async def query_leann_index(index_path: str, query: str):print(f"Leann: {chat_response}")async def main():+ # Parse command line arguments+ parser = argparse.ArgumentParser(description='LEANN Mail Reader - Create and query email index')+ parser.add_argument('--mail-path', type=str, default=DEFAULT_MAIL_PATH,+ help=f'Path to mail data directory (default: {DEFAULT_MAIL_PATH})')+ parser.add_argument('--index-dir', type=str, default="./mail_index_leann_raw_text_all_dicts",+ help='Directory to store the LEANN index (default: ./mail_index_leann_raw_text_all_dicts)')+ parser.add_argument('--max-emails', type=int, default=1000,+ help='Maximum number of emails to process (-1 means all)')+ parser.add_argument('--query', type=str, default="Give me some funny advertisement about apple or other companies",+ help='Single query to run (default: runs example queries)')++ args = parser.parse_args()++ print(f"args: {args}")+# Base path to the mail data directory- base_mail_path = "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data"+ base_mail_path = args.mail_path- INDEX_DIR = Path("./mail_index_leann_raw_text_all_dicts")+ INDEX_DIR = Path(args.index_dir)INDEX_PATH = str(INDEX_DIR / "mail_documents.leann")+ print(f"Using mail path: {base_mail_path}")+ print(f"Index directory: {INDEX_DIR}")+# Find all Messages directoriesfrom LEANN_email_reader import EmlxReadermessages_dirs = EmlxReader.find_all_messages_directories(base_mail_path)@@ -218,20 +240,23 @@ async def main():return# Create or load the LEANN index from all sources- index_path = create_leann_index_from_multiple_sources(messages_dirs, INDEX_PATH)+ index_path = create_leann_index_from_multiple_sources(messages_dirs, INDEX_PATH, args.max_emails)if index_path:- # Example queries- queries = [- "Hows Berkeley Graduate Student Instructor",- "how's the icloud related advertisement saying",- "Whats the number of class recommend to take per semester for incoming EECS students"-- ]-- for query in queries:- print("\n" + "="*60)- await query_leann_index(index_path, query)+ if args.query:+ # Run single query+ await query_leann_index(index_path, args.query)+ else:+ # Example queries+ queries = [+ "Hows Berkeley Graduate Student Instructor",+ "how's the icloud related advertisement saying",+ "Whats the number of class recommend to take per semester for incoming EECS students"+ ]++ for query in queries:+ print("\n" + "="*60)+ await query_leann_index(index_path, query)if __name__ == "__main__":asyncio.run(main())\ No newline at end of file