make the email wonderful format

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=1
 export NCCL_NET_PLUGIN=none
 export 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)
+
 
 ## 📈 Roadmap
 

examples/email_data/LEANN_email_reader.py

@@ -96,14 +96,12 @@ class EmlxReader(BaseReader):
                                 
                                 # Create document content with metadata embedded in text
                                 doc_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}
 """
                                 

examples/mail_reader_leann.py

@@ -74,10 +74,10 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_pa
             print("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 them
         all_texts = []
@@ -85,9 +85,11 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_pa
             # Split the document into chunks
             nodes = 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)')

examples/wechat_history_reader_leann.py

@@ -74,7 +74,7 @@ def create_leann_index_from_multiple_wechat_exports(
             return None
 
         print(
-            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 directory