[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
yichuan520030910320c611d0f30fbc
diff --git a/README.md b/README.mdindex c79d703..3c11c0d 100755--- a/README.md+++ b/README.md@@ -198,6 +198,68 @@ Once the index is built, you can ask questions like:</details>+### 🌐 Lightweight RAG on your Google Chrome History++LEANN can create a searchable index of your Chrome browser history, allowing you to query your browsing history using natural language.++#### Quick Start++<details>+<summary><strong>📋 Click to expand: Command Examples</strong></summary>++```bash+# Use default Chrome profile (auto-finds all profiles) and recommand method to run this because usually default file is enough+python examples/google_history_reader_leann.py+++# Run with custom index directory+python examples/google_history_reader_leann.py --index-dir "./my_chrome_index"++# Limit number of history entries processed (useful for testing)+python examples/google_history_reader_leann.py --max-entries 500++# Run a single query+python examples/google_history_reader_leann.py --query "What websites did I visit about machine learning?"++# Use only a specific profile (disable auto-find)+python examples/google_history_reader_leann.py --chrome-profile "~/Library/Application Support/Google/Chrome/Default" --no-auto-find-profiles+```++</details>++#### Finding Your Chrome Profile++<details>+<summary><strong>🔍 Click to expand: How to find your Chrome profile</strong></summary>++The default Chrome profile path is configured for a typical macOS setup. If you need to find your specific Chrome profile:++1. Open Terminal+2. Run: `ls ~/Library/Application\ Support/Google/Chrome/`+3. Look for folders like "Default", "Profile 1", "Profile 2", etc.+4. Use the full path as your `--chrome-profile` argument++**Common Chrome profile locations:**+- macOS: `~/Library/Application Support/Google/Chrome/Default`+- Linux: `~/.config/google-chrome/Default`++</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:+- "What websites did I visit about machine learning?"+- "Find my search history about programming"+- "What YouTube videos did I watch recently?"+- "Show me websites I visited about travel planning"++</details>+++## 📊 Benchmarksdiff --git a/examples/google_history_reader_leann.py b/examples/google_history_reader_leann.pyindex 4e92f7d..7342287 100644--- a/examples/google_history_reader_leann.py+++ b/examples/google_history_reader_leann.py@@ -1,5 +1,6 @@import osimport asyncio+import argparsetry:import dotenvdotenv.load_dotenv()@@ -13,6 +14,9 @@ from llama_index.core.node_parser import SentenceSplitter# dotenv.load_dotenv() # handled above if python-dotenv is available+# Default Chrome profile path+DEFAULT_CHROME_PROFILE = os.path.expanduser("~/Library/Application Support/Google/Chrome/Default")+def create_leann_index_from_multiple_chrome_profiles(profile_dirs: List[Path], index_path: str = "chrome_history_index.leann", max_count: int = -1):"""Create LEANN index from multiple Chrome profile data sources.@@ -217,32 +221,63 @@ async def query_leann_index(index_path: str, query: str):print(f"Leann: {chat_response}")async def main():- # Default Chrome profile path- default_chrome_profile = os.path.expanduser("~/Library/Application Support/Google/Chrome/Default")+ # Parse command line arguments+ parser = argparse.ArgumentParser(description='LEANN Chrome History Reader - Create and query browser history index')+ parser.add_argument('--chrome-profile', type=str, default=DEFAULT_CHROME_PROFILE,+ help=f'Path to Chrome profile directory (default: {DEFAULT_CHROME_PROFILE}), usually you dont need to change this')+ parser.add_argument('--index-dir', type=str, default="./chrome_history_index_leann_test",+ help='Directory to store the LEANN index (default: ./chrome_history_index_leann_test)')+ parser.add_argument('--max-entries', type=int, default=1000,+ help='Maximum number of history entries to process (default: 1000)')+ parser.add_argument('--query', type=str, default=None,+ help='Single query to run (default: runs example queries)')+ parser.add_argument('--auto-find-profiles', action='store_true', default=True,+ help='Automatically find all Chrome profiles (default: True)')++ args = parser.parse_args()- INDEX_DIR = Path("./chrome_history_index_leann_test")+ INDEX_DIR = Path(args.index_dir)INDEX_PATH = str(INDEX_DIR / "chrome_history.leann")- # Find all Chrome profile directories+ print(f"Using Chrome profile: {args.chrome_profile}")+ print(f"Index directory: {INDEX_DIR}")+ print(f"Max entries: {args.max_entries}")++ # Find Chrome profile directoriesfrom history_data.history import ChromeHistoryReader- profile_dirs = ChromeHistoryReader.find_chrome_profiles()- if not profile_dirs:- print("No Chrome profiles found. Exiting.")- return+ if args.auto_find_profiles:+ profile_dirs = ChromeHistoryReader.find_chrome_profiles()+ if not profile_dirs:+ print("No Chrome profiles found automatically. Exiting.")+ return+ else:+ # Use single specified profile+ profile_path = Path(args.chrome_profile)+ if not profile_path.exists():+ print(f"Chrome profile not found: {profile_path}")+ return+ profile_dirs = [profile_path]# Create or load the LEANN index from all sources- index_path = create_leann_index_from_multiple_chrome_profiles(profile_dirs, INDEX_PATH,1000)+ index_path = create_leann_index_from_multiple_chrome_profiles(profile_dirs, INDEX_PATH, args.max_entries)if index_path:- # Example queries- queries = [- "What websites did I visit about machine learning?",- ]-- 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 = [+ "What websites did I visit about machine learning?",+ "Show me my recent shopping history",+ "What news sites did I visit this week?",+ "Find my search history about programming"+ ]++ 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