[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
make the email wonderful format
yichuan520030910320aa9a14a917ae
diff --git a/README.md b/README.mdindex edfd77f..e4c597b 100755--- a/README.md+++ b/README.md@@ -292,7 +292,7 @@ Once the index is built, you can ask questions like:</details>-Slack supporting soon! Stay tuned!+## 🖥️ Command Line Interface@@ -503,6 +503,17 @@ export NCCL_IB_DISABLE=1export NCCL_NET_PLUGIN=noneexport NCCL_SOCKET_IFNAME=ens5``` -->+## FAQ++### 1. My building time seems long++You can speed up the process by using a lightweight embedding model. Add this to your arguments:++```bash+--embedding-model sentence-transformers/all-MiniLM-L6-v2+```+**Model sizes:** `all-MiniLM-L6-v2` (30M parameters), `facebook/contriever` (~100M parameters), `Qwen3-0.6B` (600M parameters)+## 📈 Roadmapdiff --git a/examples/email_data/LEANN_email_reader.py b/examples/email_data/LEANN_email_reader.pyindex 2c79108..ba441f9 100644--- a/examples/email_data/LEANN_email_reader.py+++ b/examples/email_data/LEANN_email_reader.py@@ -96,14 +96,12 @@ class EmlxReader(BaseReader):# Create document content with metadata embedded in textdoc_content = f"""-[EMAIL METADATA]-File: {filename}-From: {from_addr}-To: {to_addr}-Subject: {subject}-Date: {date}-[END METADATA]-+[File]: {filename}+[From]: {from_addr}+[To]: {to_addr}+[Subject]: {subject}+[Date]: {date}+[EMAIL BODY Start]:{body}"""diff --git a/examples/mail_reader_leann.py b/examples/mail_reader_leann.pyindex fbdde1b..5a22bf3 100644--- a/examples/mail_reader_leann.py+++ b/examples/mail_reader_leann.py@@ -74,10 +74,10 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_paprint("No documents loaded from any source. Exiting.")return None- print(f"\nTotal loaded {len(all_documents)} email documents from {len(messages_dirs)} directories")+ print(f"\nTotal loaded {len(all_documents)} email documents from {len(messages_dirs)} directories and starting to split them into chunks")# Create text splitter with 256 chunk size- text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=25)+ text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=128)# Convert Documents to text strings and chunk themall_texts = []@@ -85,9 +85,11 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_pa# Split the document into chunksnodes = text_splitter.get_nodes_from_documents([doc])for node in nodes:- all_texts.append(node.get_content())+ text = node.get_content()+ # text = '[subject] ' + doc.metadata["subject"] + '\n' + text+ all_texts.append(text)- print(f"Created {len(all_texts)} text chunks from {len(all_documents)} documents")+ print(f"Finished splitting {len(all_documents)} documents into {len(all_texts)} text chunks")# Create LEANN index directory@@ -231,7 +233,7 @@ async def main():parser = argparse.ArgumentParser(description='LEANN Mail Reader - Create and query email index')# Remove --mail-path argument and auto-detect all Messages directories# Remove DEFAULT_MAIL_PATH- parser.add_argument('--index-dir', type=str, default="./mail_index_leann_raw_text_all_dicts",+ parser.add_argument('--index-dir', type=str, default="./mail_index_leann_debug",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)')diff --git a/examples/wechat_history_reader_leann.py b/examples/wechat_history_reader_leann.pyindex 624b596..971ea74 100644--- a/examples/wechat_history_reader_leann.py+++ b/examples/wechat_history_reader_leann.py@@ -74,7 +74,7 @@ def create_leann_index_from_multiple_wechat_exports(return Noneprint(- f"\nTotal loaded {len(all_documents)} chat documents from {len(export_dirs)} exports"+ f"\nTotal loaded {len(all_documents)} chat documents from {len(export_dirs)} exports and starting to split them into chunks")# Create text splitter with 256 chunk size@@ -90,7 +90,7 @@ def create_leann_index_from_multiple_wechat_exports(all_texts.append(text)print(- f"Created {len(all_texts)} text chunks from {len(all_documents)} documents"+ f"Finished splitting {len(all_documents)} documents into {len(all_texts)} text chunks")# Create LEANN index directorydiff --git a/packages/leann-backend-diskann/third_party/DiskANN b/packages/leann-backend-diskann/third_party/DiskANNindex 25339b0..af2a264 160000--- a/packages/leann-backend-diskann/third_party/DiskANN+++ b/packages/leann-backend-diskann/third_party/DiskANN@@ -1 +1 @@-Subproject commit 25339b03413b5067c25b6092ea3e0f77ef8515c8+Subproject commit af2a26481e65232b57b82d96e68833cdee9f7635