upd readme mail application

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)
+- **🔄 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
-- **🏗️ Pluggable Backends**: DiskANN, HNSW/FAISS with unified API
+- **📈 Scalable Architecture** - Handles millions of documents on consumer hardware; the larger your dataset, the more LEANN can save
-- **🔄 Real-time Embeddings**: Dynamic computation using optimized ZMQ servers
+- **🎯 Graph Pruning** - Advanced techniques to minimize the storage overhead of vector search to a limited footprint
-- **📈 Scalable Architecture**: Handles millions of documents on consumer hardware
+- **🏗️ Pluggable Backends** - DiskANN, HNSW/FAISS with unified API
-- **🎯 Graph Pruning**: Advanced techniques for memory-efficient search
 
 ### 🛠️ Technical Highlights
-
+- **🔄 Recompute Mode** - Highest accuracy scenarios while eliminating vector storage overhead
-- **Zero-copy operations** for maximum performance
+- **⚡ Zero-copy Operations** - Minimize IPC overhead by transferring distances instead of embeddings
-- **SIMD-optimized** distance computations (AVX2/AVX512)
+- **🚀 High-throughput Embedding Pipeline** - Optimized batched processing for maximum efficiency
-- **Async embedding pipeline** with batched processing
+- **🎯 Two-level Search** - Novel coarse-to-fine search overlap for accelerated query processing (optional)
-- **Memory-mapped indices** for fast startup
+- **💾 Memory-mapped Indices** - Fast startup with raw text mapping to reduce memory overhead
-- **Recompute mode** for highest accuracy scenarios
+- **🚀 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>
+
 
 ## 📊 Benchmarks
 

examples/mail_reader_leann.py

@@ -1,6 +1,7 @@
 import os
 import asyncio
 import dotenv
+import argparse
 from pathlib import Path
 from typing import List, Any
 from leann.api import LeannBuilder, LeannSearcher, LeannChat
@@ -8,6 +9,9 @@ from llama_index.core.node_parser import SentenceSplitter
 
 dotenv.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():
-    # Base path to the mail data directory
+    # Parse command line arguments
-    base_mail_path = "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data"
+    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)')
     
-    INDEX_DIR = Path("./mail_index_leann_raw_text_all_dicts")
+    args = parser.parse_args()
+
+    print(f"args: {args}")
+    
+    # Base path to the mail data directory
+    base_mail_path = args.mail_path
+    
+    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 directories
     from LEANN_email_reader import EmlxReader
     messages_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
+        if args.query:
-        queries = [
+            # Run single query
-            "Hows Berkeley Graduate Student Instructor",
+            await query_leann_index(index_path, args.query)
-            "how's the icloud related advertisement saying",
+        else:
-            "Whats the number of class recommend to take per semester for incoming EECS students"
+            # Example queries
-
+            queries = [
-        ]
+                "Hows Berkeley Graduate Student Instructor",
-        
+                "how's the icloud related advertisement saying",
-        for query in queries:
+                "Whats the number of class recommend to take per semester for incoming EECS students"
-            print("\n" + "="*60)
+            ]
-            await query_leann_index(index_path, query)
+            
+            for query in queries:
+                print("\n" + "="*60)
+                await query_leann_index(index_path, query)
 
 if __name__ == "__main__":
     asyncio.run(main())