docs: align cli args and README

README.md

@@ -31,7 +31,7 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg
   <img src="assets/effects.png" alt="LEANN vs Traditional Vector DB Storage Comparison" width="70%">
 </p>
 
-> **The numbers speak for themselves:** Index 60 million text chunks in just 6GB instead of 201GB. From emails to browser history, everything fits on your laptop. [See detailed benchmarks for different applications below ↓](#-storage-comparison)
+> **The numbers speak for themselves:** Index 60 million text chunks in just 6GB instead of 201GB. From emails to browser history, everything fits on your laptop. [See detailed benchmarks for different applications below ↓](#storage-comparison)
 
 
 🔒 **Privacy:** Your data never leaves your laptop. No OpenAI, no cloud, no "terms of service".
@@ -70,8 +70,8 @@ uv venv
 source .venv/bin/activate
 uv pip install leann
 ```
-<!--
+
-> Low-resource? See “Low-resource setups” in the [Configuration Guide](docs/configuration-guide.md#low-resource-setups). -->
+> Low-resource? See “Low-resource setups” in the [Configuration Guide](docs/configuration-guide.md#low-resource-setups).
 
 <details>
 <summary>

packages/leann-core/src/leann/cli.py

@@ -148,36 +148,6 @@ Examples:
             type=str,
             help="Comma-separated list of file extensions to include (e.g., '.txt,.pdf,.pptx'). If not specified, uses default supported types.",
         )
-        build_parser.add_argument(
-            "--include-hidden",
-            action=argparse.BooleanOptionalAction,
-            default=False,
-            help="Include hidden files and directories (paths starting with '.') during indexing (default: false)",
-        )
-        build_parser.add_argument(
-            "--doc-chunk-size",
-            type=int,
-            default=256,
-            help="Document chunk size in tokens/characters (default: 256)",
-        )
-        build_parser.add_argument(
-            "--doc-chunk-overlap",
-            type=int,
-            default=128,
-            help="Document chunk overlap (default: 128)",
-        )
-        build_parser.add_argument(
-            "--code-chunk-size",
-            type=int,
-            default=512,
-            help="Code chunk size in tokens/lines (default: 512)",
-        )
-        build_parser.add_argument(
-            "--code-chunk-overlap",
-            type=int,
-            default=50,
-            help="Code chunk overlap (default: 50)",
-        )
 
         # Search command
         search_parser = subparsers.add_parser("search", help="Search documents")
@@ -417,10 +387,7 @@ Examples:
                     print(f"  leann ask {example_name} --interactive")
 
     def load_documents(
-        self,
+        self, docs_paths: Union[str, list], custom_file_types: Union[str, None] = None
-        docs_paths: Union[str, list],
-        custom_file_types: Union[str, None] = None,
-        include_hidden: bool = False,
     ):
         # Handle both single path (string) and multiple paths (list) for backward compatibility
         if isinstance(docs_paths, str):
@@ -464,10 +431,6 @@ Examples:
 
         all_documents = []
 
-        # Helper to detect hidden path components
-        def _path_has_hidden_segment(p: Path) -> bool:
-            return any(part.startswith(".") and part not in [".", ".."] for part in p.parts)
-
         # First, process individual files if any
         if files:
             print(f"\n🔄 Processing {len(files)} individual file{'s' if len(files) > 1 else ''}...")
@@ -480,12 +443,8 @@ Examples:
 
                 files_by_dir = defaultdict(list)
                 for file_path in files:
-                    file_path_obj = Path(file_path)
+                    parent_dir = str(Path(file_path).parent)
-                    if not include_hidden and _path_has_hidden_segment(file_path_obj):
+                    files_by_dir[parent_dir].append(file_path)
-                        print(f"  ⚠️  Skipping hidden file: {file_path}")
-                        continue
-                    parent_dir = str(file_path_obj.parent)
-                    files_by_dir[parent_dir].append(str(file_path_obj))
 
                 # Load files from each parent directory
                 for parent_dir, file_list in files_by_dir.items():
@@ -496,7 +455,6 @@ Examples:
                         file_docs = SimpleDirectoryReader(
                             parent_dir,
                             input_files=file_list,
-                            # exclude_hidden only affects directory scans; input_files are explicit
                             filename_as_id=True,
                         ).load_data()
                         all_documents.extend(file_docs)
@@ -595,8 +553,6 @@ Examples:
                     # Check if file matches any exclude pattern
                     try:
                         relative_path = file_path.relative_to(docs_path)
-                        if not include_hidden and _path_has_hidden_segment(relative_path):
-                            continue
                         if self._should_exclude_file(relative_path, gitignore_matches):
                             continue
                     except ValueError:
@@ -624,7 +580,6 @@ Examples:
                         try:
                             default_docs = SimpleDirectoryReader(
                                 str(file_path.parent),
-                                exclude_hidden=not include_hidden,
                                 filename_as_id=True,
                                 required_exts=[file_path.suffix],
                             ).load_data()
@@ -653,7 +608,6 @@ Examples:
                     encoding="utf-8",
                     required_exts=code_extensions,
                     file_extractor={},  # Use default extractors
-                    exclude_hidden=not include_hidden,
                     filename_as_id=True,
                 ).load_data(show_progress=True)
 
@@ -772,40 +726,7 @@ Examples:
             print(f"Index '{index_name}' already exists. Use --force to rebuild.")
             return
 
-        # Configure chunking based on CLI args before loading documents
+        all_texts = self.load_documents(docs_paths, args.file_types)
-        # Guard against invalid configurations
-        doc_chunk_size = max(1, int(args.doc_chunk_size))
-        doc_chunk_overlap = max(0, int(args.doc_chunk_overlap))
-        if doc_chunk_overlap >= doc_chunk_size:
-            print(
-                f"⚠️  Adjusting doc chunk overlap from {doc_chunk_overlap} to {doc_chunk_size - 1} (must be < chunk size)"
-            )
-            doc_chunk_overlap = doc_chunk_size - 1
-
-        code_chunk_size = max(1, int(args.code_chunk_size))
-        code_chunk_overlap = max(0, int(args.code_chunk_overlap))
-        if code_chunk_overlap >= code_chunk_size:
-            print(
-                f"⚠️  Adjusting code chunk overlap from {code_chunk_overlap} to {code_chunk_size - 1} (must be < chunk size)"
-            )
-            code_chunk_overlap = code_chunk_size - 1
-
-        self.node_parser = SentenceSplitter(
-            chunk_size=doc_chunk_size,
-            chunk_overlap=doc_chunk_overlap,
-            separator=" ",
-            paragraph_separator="\n\n",
-        )
-        self.code_parser = SentenceSplitter(
-            chunk_size=code_chunk_size,
-            chunk_overlap=code_chunk_overlap,
-            separator="\n",
-            paragraph_separator="\n\n",
-        )
-
-        all_texts = self.load_documents(
-            docs_paths, args.file_types, include_hidden=args.include_hidden
-        )
         if not all_texts:
             print("No documents found")
             return

packages/leann-core/src/leann/embedding_compute.py

@@ -263,16 +263,8 @@ def compute_embeddings_openai(texts: list[str], model_name: str) -> np.ndarray:
     print(f"len of texts: {len(texts)}")
 
     # OpenAI has limits on batch size and input length
-    max_batch_size = 800  # Conservative batch size because the token limit is 300K
+    max_batch_size = 1000  # Conservative batch size
     all_embeddings = []
-    # get the avg len of texts
-    avg_len = sum(len(text) for text in texts) / len(texts)
-    print(f"avg len of texts: {avg_len}")
-    # if avg len is less than 1000, use the max batch size
-    if avg_len > 300:
-        max_batch_size = 500
-
-    # if avg len is less than 1000, use the max batch size
 
     try:
         from tqdm import tqdm

packages/leann-core/src/leann/mcp.py

@@ -64,6 +64,19 @@ def handle_request(request):
                             "required": ["index_name", "query"],
                         },
                     },
+                    {
+                        "name": "leann_status",
+                        "description": "📊 Check the health and stats of your code indexes - like a medical checkup for your codebase knowledge!",
+                        "inputSchema": {
+                            "type": "object",
+                            "properties": {
+                                "index_name": {
+                                    "type": "string",
+                                    "description": "Optional: Name of specific index to check. If not provided, shows status of all indexes.",
+                                }
+                            },
+                        },
+                    },
                     {
                         "name": "leann_list",
                         "description": "📋 Show all your indexed codebases - your personal code library! Use this to see what's available for search.",
@@ -105,6 +118,15 @@ def handle_request(request):
                 ]
                 result = subprocess.run(cmd, capture_output=True, text=True)
 
+            elif tool_name == "leann_status":
+                if args.get("index_name"):
+                    # Check specific index status - for now, we'll use leann list and filter
+                    result = subprocess.run(["leann", "list"], capture_output=True, text=True)
+                    # We could enhance this to show more detailed status per index
+                else:
+                    # Show all indexes status
+                    result = subprocess.run(["leann", "list"], capture_output=True, text=True)
+
             elif tool_name == "leann_list":
                 result = subprocess.run(["leann", "list"], capture_output=True, text=True)
 

packages/leann-mcp/README.md

@@ -13,20 +13,10 @@ This installs the `leann` CLI into an isolated tool environment and includes bot
 
 ## 🚀 Quick Setup
 
-Add the LEANN MCP server to Claude Code. Choose the scope based on how widely you want it available. Below is the command to install it globally; if you prefer a local install, skip this step:
+Add the LEANN MCP server to Claude Code:
 
 ```bash
-# Global (recommended): available in all projects for your user
+claude mcp add leann-server -- leann_mcp
-claude mcp add --scope user leann-server -- leann_mcp
-```
-
-- `leann-server`: the display name of the MCP server in Claude Code (you can change it).
-- `leann_mcp`: the Python entry point installed with LEANN that starts the MCP server.
-
-Verify it is registered globally:
-
-```bash
-claude mcp list | cat
 ```
 
 ## 🛠️ Available Tools
@@ -35,36 +25,27 @@ Once connected, you'll have access to these powerful semantic search tools in Cl
 
 - **`leann_list`** - List all available indexes across your projects
 - **`leann_search`** - Perform semantic searches across code and documents
-
+- **`leann_ask`** - Ask natural language questions and get AI-powered answers from your codebase
 
 ## 🎯 Quick Start Example
 
 ```bash
-# Add locally if you did not add it globally (current folder only; default if --scope is omitted)
-claude mcp add leann-server -- leann_mcp
-
 # Build an index for your project (change to your actual path)
-# See the advanced examples below for more ways to configure indexing
+leann build my-project --docs ./
-# Set the index name (replace 'my-project' with your own)
-leann build my-project --docs $(git ls-files)
 
 # Start Claude Code
 claude
 ```
 
-## 🚀 Advanced Usage Examples to build the index
+## 🚀 Advanced Usage Examples
 
 ### Index Entire Git Repository
 ```bash
-# Index all tracked files in your Git repository.
+# Index all tracked files in your git repository, note right now we will skip submodules, but we can add it back easily if you want
-# Note: submodules are currently skipped; we can add them back if needed.
 leann build my-repo --docs $(git ls-files) --embedding-mode sentence-transformers --embedding-model all-MiniLM-L6-v2 --backend hnsw
 
-# Index only tracked Python files from Git.
+# Index only specific file types from git
 leann build my-python-code --docs $(git ls-files "*.py") --embedding-mode sentence-transformers --embedding-model all-MiniLM-L6-v2 --backend hnsw
-
-# If you encounter empty requests caused by empty files (e.g., __init__.py), exclude zero-byte files. Thanks @ww2283 for pointing [that](https://github.com/yichuan-w/LEANN/issues/48) out
-leann build leann-prospec-lig --docs $(find ./src -name "*.py" -not -empty) --embedding-mode openai --embedding-model text-embedding-3-small
 ```
 
 ### Multiple Directories and Files
@@ -101,7 +82,6 @@ Help me understand this codebase. List available indexes and search for authenti
   <img src="../../assets/claude_code_leann.png" alt="LEANN in Claude Code" width="80%">
 </p>
 
-If you see a prompt asking whether to proceed with LEANN, you can now use it in your chat!
 
 ## 🧠 How It Works
 
@@ -137,11 +117,3 @@ To remove LEANN
 ```
 uv pip uninstall leann leann-backend-hnsw leann-core
 ```
-
-To globally remove LEANN (for version update)
-```
-uv tool list | cat
-uv tool uninstall leann-core
-command -v leann || echo "leann gone"
-command -v leann_mcp || echo "leann_mcp gone"
-```

packages/wechat-exporter/__init__.py

@@ -1 +0,0 @@
-__all__ = []

packages/wechat-exporter/main.py

@@ -136,9 +136,5 @@ def export_sqlite(
     connection.commit()
 
 
-def main():
-    app()
-
-
 if __name__ == "__main__":
-    main()
+    app()

pyproject.toml

@@ -10,7 +10,6 @@ requires-python = ">=3.9"
 dependencies = [
     "leann-core",
     "leann-backend-hnsw",
-    "typer>=0.12.3",
     "numpy>=1.26.0",
     "torch",
     "tqdm",
@@ -85,11 +84,6 @@ documents = [
 
 [tool.setuptools]
 py-modules = []
-packages = ["wechat_exporter"]
-package-dir = { "wechat_exporter" = "packages/wechat-exporter" }
-
-[project.scripts]
-wechat-exporter = "wechat_exporter.main:main"
 
 
 [tool.uv.sources]