fix(core): skip empty/invalid chunks before embedding; guard OpenAI embeddings

Avoid 400 errors from OpenAI when chunker yields empty strings by filtering
invalid texts in LeannBuilder.build_index. Add validation fail-fast in
OpenAI embedding path to surface upstream issues earlier. Keeps passages and
embeddings aligned during build.

Refs #54

.gitattributes

@@ -0,0 +1 @@
+paper_plot/data/big_graph_degree_data.npz filter=lfs diff=lfs merge=lfs -text

.github/workflows/build-reusable.yml

@@ -87,7 +87,7 @@ jobs:
     runs-on: ${{ matrix.os }}
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v4
         with:
           ref: ${{ inputs.ref }}
           submodules: recursive
@@ -98,23 +98,21 @@ jobs:
           python-version: ${{ matrix.python }}
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v4
 
       - name: Install system dependencies (Ubuntu)
         if: runner.os == 'Linux'
         run: |
           sudo apt-get update
           sudo apt-get install -y libomp-dev libboost-all-dev protobuf-compiler libzmq3-dev \
-            pkg-config libabsl-dev libaio-dev libprotobuf-dev \
+            pkg-config libopenblas-dev patchelf libabsl-dev libaio-dev libprotobuf-dev
-            patchelf
 
           # Install Intel MKL for DiskANN
           wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940.sh
           sudo sh intel-onemkl-2025.0.0.940.sh -a --components intel.oneapi.lin.mkl.devel --action install --eula accept -s
           source /opt/intel/oneapi/setvars.sh
           echo "MKLROOT=/opt/intel/oneapi/mkl/latest" >> $GITHUB_ENV
-          echo "LD_LIBRARY_PATH=/opt/intel/oneapi/compiler/latest/linux/compiler/lib/intel64_lin" >> $GITHUB_ENV
+          echo "LD_LIBRARY_PATH=/opt/intel/oneapi/mkl/latest/lib/intel64:$LD_LIBRARY_PATH" >> $GITHUB_ENV
-          echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV
 
       - name: Install system dependencies (macOS)
         if: runner.os == 'macOS'
@@ -306,53 +304,3 @@ jobs:
         with:
           name: packages-${{ matrix.os }}-py${{ matrix.python }}
           path: packages/*/dist/
-
-
-  arch-smoke:
-    name: Arch Linux smoke test (install & import)
-    needs: build
-    runs-on: ubuntu-latest
-    container:
-      image: archlinux:latest
-
-    steps:
-      - name: Prepare system
-        run: |
-          pacman -Syu --noconfirm
-          pacman -S --noconfirm python python-pip gcc git zlib openssl
-
-      - name: Download ALL wheel artifacts from this run
-        uses: actions/download-artifact@v5
-        with:
-          # Don't specify name, download all artifacts
-          path: ./wheels
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
-
-      - name: Create virtual environment and install wheels
-        run: |
-          uv venv
-          source .venv/bin/activate || source .venv/Scripts/activate
-          uv pip install --find-links wheels leann-core
-          uv pip install --find-links wheels leann-backend-hnsw
-          uv pip install --find-links wheels leann-backend-diskann
-          uv pip install --find-links wheels leann
-
-      - name: Import & tiny runtime check
-        env:
-          OMP_NUM_THREADS: 1
-          MKL_NUM_THREADS: 1
-        run: |
-          source .venv/bin/activate || source .venv/Scripts/activate
-          python - <<'PY'
-          import leann
-          import leann_backend_hnsw as h
-          import leann_backend_diskann as d
-          from leann import LeannBuilder, LeannSearcher
-          b = LeannBuilder(backend_name="hnsw")
-          b.add_text("hello arch")
-          b.build_index("arch_demo.leann")
-          s = LeannSearcher("arch_demo.leann")
-          print("search:", s.search("hello", top_k=1))
-          PY

.github/workflows/link-check.yml

@@ -14,6 +14,6 @@ jobs:
       - uses: actions/checkout@v4
       - uses: lycheeverse/lychee-action@v2
         with:
-          args: --no-progress --insecure --user-agent 'curl/7.68.0' README.md docs/ apps/ examples/ benchmarks/
+          args: --no-progress --insecure README.md docs/ apps/ examples/ benchmarks/
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -18,7 +18,6 @@ demo/experiment_results/**/*.json
 *.eml
 *.emlx
 *.json
-!.vscode/*.json
 *.sh
 *.txt
 !CMakeLists.txt

.vscode/extensions.json

@@ -1,5 +0,0 @@
-{
-    "recommendations": [
-        "charliermarsh.ruff",
-    ]
-}

.vscode/settings.json

@@ -1,22 +0,0 @@
-{
-  "python.defaultInterpreterPath": ".venv/bin/python",
-  "python.terminal.activateEnvironment": true,
-  "[python]": {
-    "editor.defaultFormatter": "charliermarsh.ruff",
-    "editor.formatOnSave": true,
-    "editor.codeActionsOnSave": {
-      "source.organizeImports": "explicit",
-      "source.fixAll": "explicit"
-    },
-    "editor.insertSpaces": true,
-    "editor.tabSize": 4
-  },
-  "ruff.enable": true,
-  "files.watcherExclude": {
-    "**/.venv/**": true,
-    "**/__pycache__/**": true,
-    "**/*.egg-info/**": true,
-    "**/build/**": true,
-    "**/dist/**": true
-  }
-}

README.md

@@ -5,7 +5,7 @@
 <p align="center">
   <img src="https://img.shields.io/badge/Python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue.svg" alt="Python Versions">
   <img src="https://github.com/yichuan-w/LEANN/actions/workflows/build-and-publish.yml/badge.svg" alt="CI Status">
-  <img src="https://img.shields.io/badge/Platform-Ubuntu%20%26%20Arch%20%26%20WSL%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
+  <img src="https://img.shields.io/badge/Platform-Ubuntu%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
   <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="MIT License">
   <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue" alt="MCP Integration">
 </p>
@@ -87,60 +87,15 @@ git submodule update --init --recursive
 ```
 
 **macOS:**
-
-Note: DiskANN requires MacOS 13.3 or later.
-
 ```bash
-brew install libomp boost protobuf zeromq pkgconf
+brew install llvm libomp boost protobuf zeromq pkgconf
-uv sync --extra diskann
+CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
 ```
 
-**Linux (Ubuntu/Debian):**
+**Linux:**
-
-Note: On Ubuntu 20.04, you may need to build a newer Abseil and pin Protobuf (e.g., v3.20.x) for building DiskANN. See [Issue #30](https://github.com/yichuan-w/LEANN/issues/30) for a step-by-step note.
-
-You can manually install [Intel oneAPI MKL](https://www.intel.com/content/www/us/en/developer/tools/oneapi/onemkl.html) instead of `libmkl-full-dev` for DiskANN. You can also use `libopenblas-dev` for building HNSW only, by removing `--extra diskann` in the command below.
-
 ```bash
-sudo apt-get update && sudo apt-get install -y \
+sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
-  libomp-dev libboost-all-dev protobuf-compiler libzmq3-dev \
+uv sync
-  pkg-config libabsl-dev libaio-dev libprotobuf-dev \
-  libmkl-full-dev
-
-uv sync --extra diskann
-```
-
-**Linux (Arch Linux):**
-
-```bash
-sudo pacman -Syu && sudo pacman -S --needed base-devel cmake pkgconf git gcc \
-  boost boost-libs protobuf abseil-cpp libaio zeromq
-
-# For MKL in DiskANN
-sudo pacman -S --needed base-devel git
-git clone https://aur.archlinux.org/paru-bin.git
-cd paru-bin && makepkg -si
-paru -S intel-oneapi-mkl intel-oneapi-compiler
-source /opt/intel/oneapi/setvars.sh
-
-uv sync --extra diskann
-```
-
-**Linux (RHEL / CentOS Stream / Oracle / Rocky / AlmaLinux):**
-
-See [Issue #50](https://github.com/yichuan-w/LEANN/issues/50) for more details.
-
-```bash
-sudo dnf groupinstall -y "Development Tools"
-sudo dnf install -y libomp-devel boost-devel protobuf-compiler protobuf-devel \
-  abseil-cpp-devel libaio-devel zeromq-devel pkgconf-pkg-config
-
-# For MKL in DiskANN
-sudo dnf install -y intel-oneapi-mkl intel-oneapi-mkl-devel \
-  intel-oneapi-openmp || sudo dnf install -y intel-oneapi-compiler
-source /opt/intel/oneapi/setvars.sh
-
-uv sync --extra diskann
 ```
 
 </details>
@@ -527,9 +482,6 @@ leann ask my-docs --interactive
 
 # List all your indexes
 leann list
-
-# Remove an index
-leann remove my-docs
 ```
 
 **Key CLI features:**
@@ -542,7 +494,7 @@ leann remove my-docs
 <details>
 <summary><strong>📋 Click to expand: Complete CLI Reference</strong></summary>
 
-You can use `leann --help`, or `leann build --help`, `leann search --help`, `leann ask --help`, `leann list --help`, `leann remove --help` to get the complete CLI reference.
+You can use `leann --help`, or `leann build --help`, `leann search --help`, `leann ask --help` to get the complete CLI reference.
 
 **Build Command:**
 ```bash
@@ -580,31 +532,6 @@ Options:
   --top-k N                  Retrieval count (default: 20)
 ```
 
-**List Command:**
-```bash
-leann list
-
-# Lists all indexes across all projects with status indicators:
-# ✅ - Index is complete and ready to use
-# ❌ - Index is incomplete or corrupted
-# 📁 - CLI-created index (in .leann/indexes/)
-# 📄 - App-created index (*.leann.meta.json files)
-```
-
-**Remove Command:**
-```bash
-leann remove INDEX_NAME [OPTIONS]
-
-Options:
-  --force, -f    Force removal without confirmation
-
-# Smart removal: automatically finds and safely removes indexes
-# - Shows all matching indexes across projects
-# - Requires confirmation for cross-project removal
-# - Interactive selection when multiple matches found
-# - Supports both CLI and app-created indexes
-```
-
 </details>
 
 ## 🏗️ Architecture & How It Works

apps/base_rag_example.py

@@ -10,7 +10,6 @@ from typing import Any
 
 import dotenv
 from leann.api import LeannBuilder, LeannChat
-from leann.registry import register_project_directory
 from llama_index.core.node_parser import SentenceSplitter
 
 dotenv.load_dotenv()
@@ -215,11 +214,6 @@ class BaseRAGExample(ABC):
         builder.build_index(index_path)
         print(f"Index saved to: {index_path}")
 
-        # Register project directory so leann list can discover this index
-        # The index is saved as args.index_dir/index_name.leann
-        # We want to register the current working directory where the app is run
-        register_project_directory(Path.cwd())
-
         return index_path
 
     async def run_interactive_chat(self, args, index_path: str):

benchmarks/simple_mac_tpt_test.py

@@ -183,9 +183,6 @@ class Benchmark:
         start_time = time.time()
         with torch.no_grad():
             self.model(input_ids=input_ids, attention_mask=attention_mask)
-        # mps sync
-        if torch.backends.mps.is_available():
-            torch.mps.synchronize()
         end_time = time.time()
 
         return end_time - start_time

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.3.2"
+version = "0.2.9"
-dependencies = ["leann-core==0.3.2", "numpy", "protobuf>=3.19.0"]
+dependencies = ["leann-core==0.2.9", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.3.2"
+version = "0.2.9"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.3.2",
+    "leann-core==0.2.9",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.3.2"
+version = "0.2.9"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -46,7 +46,6 @@ def compute_embeddings(
             - "sentence-transformers": Use sentence-transformers library (default)
             - "mlx": Use MLX backend for Apple Silicon
             - "openai": Use OpenAI embedding API
-            - "gemini": Use Google Gemini embedding API
         use_server: Whether to use embedding server (True for search, False for build)
 
     Returns:
@@ -614,7 +613,7 @@ class LeannSearcher:
             zmq_port=zmq_port,
         )
         # logger.info(f"  Generated embedding shape: {query_embedding.shape}")
-        # time.time() - start_time
+        time.time() - start_time
         # logger.info(f"  Embedding time: {embedding_time} seconds")
 
         start_time = time.time()
@@ -680,9 +679,8 @@ class LeannSearcher:
         This method should be called after you're done using the searcher,
         especially in test environments or batch processing scenarios.
         """
-        backend = getattr(self.backend_impl, "embedding_server_manager", None)
+        if hasattr(self.backend_impl, "embedding_server_manager"):
-        if backend is not None:
+            self.backend_impl.embedding_server_manager.stop_server()
-            backend.stop_server()
 
     # Enable automatic cleanup patterns
     def __enter__(self):

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

@@ -680,60 +680,6 @@ class HFChat(LLMInterface):
         return response.strip()
 
 
-class GeminiChat(LLMInterface):
-    """LLM interface for Google Gemini models."""
-
-    def __init__(self, model: str = "gemini-2.5-flash", api_key: Optional[str] = None):
-        self.model = model
-        self.api_key = api_key or os.getenv("GEMINI_API_KEY")
-
-        if not self.api_key:
-            raise ValueError(
-                "Gemini API key is required. Set GEMINI_API_KEY environment variable or pass api_key parameter."
-            )
-
-        logger.info(f"Initializing Gemini Chat with model='{model}'")
-
-        try:
-            import google.genai as genai
-
-            self.client = genai.Client(api_key=self.api_key)
-        except ImportError:
-            raise ImportError(
-                "The 'google-genai' library is required for Gemini models. Please install it with 'uv pip install google-genai'."
-            )
-
-    def ask(self, prompt: str, **kwargs) -> str:
-        logger.info(f"Sending request to Gemini with model {self.model}")
-
-        try:
-            from google.genai.types import GenerateContentConfig
-
-            generation_config = GenerateContentConfig(
-                temperature=kwargs.get("temperature", 0.7),
-                max_output_tokens=kwargs.get("max_tokens", 1000),
-            )
-
-            # Handle top_p parameter
-            if "top_p" in kwargs:
-                generation_config.top_p = kwargs["top_p"]
-
-            response = self.client.models.generate_content(
-                model=self.model,
-                contents=prompt,
-                config=generation_config,
-            )
-            # Handle potential None response text
-            response_text = response.text
-            if response_text is None:
-                logger.warning("Gemini returned None response text")
-                return ""
-            return response_text.strip()
-        except Exception as e:
-            logger.error(f"Error communicating with Gemini: {e}")
-            return f"Error: Could not get a response from Gemini. Details: {e}"
-
-
 class OpenAIChat(LLMInterface):
     """LLM interface for OpenAI models."""
 
@@ -847,8 +793,6 @@ def get_llm(llm_config: Optional[dict[str, Any]] = None) -> LLMInterface:
         return HFChat(model_name=model or "deepseek-ai/deepseek-llm-7b-chat")
     elif llm_type == "openai":
         return OpenAIChat(model=model or "gpt-4o", api_key=llm_config.get("api_key"))
-    elif llm_type == "gemini":
-        return GeminiChat(model=model or "gemini-2.5-flash", api_key=llm_config.get("api_key"))
     elif llm_type == "simulated":
         return SimulatedChat()
     else:

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

@@ -1,14 +1,13 @@
 import argparse
 import asyncio
 from pathlib import Path
-from typing import Optional, Union
+from typing import Union
 
 from llama_index.core import SimpleDirectoryReader
 from llama_index.core.node_parser import SentenceSplitter
 from tqdm import tqdm
 
 from .api import LeannBuilder, LeannChat, LeannSearcher
-from .registry import register_project_directory
 
 
 def extract_pdf_text_with_pymupdf(file_path: str) -> str:
@@ -85,7 +84,6 @@ Examples:
   leann search my-docs "query"                                           # Search in my-docs index
   leann ask my-docs "question"                                           # Ask my-docs index
   leann list                                                             # List all stored indexes
-  leann remove my-docs                                                   # Remove an index (local first, then global)
             """,
         )
 
@@ -150,12 +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,
@@ -206,11 +198,6 @@ Examples:
             default="global",
             help="Pruning strategy (default: global)",
         )
-        search_parser.add_argument(
-            "--non-interactive",
-            action="store_true",
-            help="Non-interactive mode: automatically select index without prompting",
-        )
 
         # Ask command
         ask_parser = subparsers.add_parser("ask", help="Ask questions")
@@ -258,18 +245,35 @@ Examples:
         # List command
         subparsers.add_parser("list", help="List all indexes")
 
-        # Remove command
-        remove_parser = subparsers.add_parser("remove", help="Remove an index")
-        remove_parser.add_argument("index_name", help="Index name to remove")
-        remove_parser.add_argument(
-            "--force", "-f", action="store_true", help="Force removal without confirmation"
-        )
-
         return parser
 
     def register_project_dir(self):
         """Register current project directory in global registry"""
-        register_project_directory()
+        global_registry = Path.home() / ".leann" / "projects.json"
+        global_registry.parent.mkdir(exist_ok=True)
+
+        current_dir = str(Path.cwd())
+
+        # Load existing registry
+        projects = []
+        if global_registry.exists():
+            try:
+                import json
+
+                with open(global_registry) as f:
+                    projects = json.load(f)
+            except Exception:
+                projects = []
+
+        # Add current directory if not already present
+        if current_dir not in projects:
+            projects.append(current_dir)
+
+        # Save registry
+        import json
+
+        with open(global_registry, "w") as f:
+            json.dump(projects, f, indent=2)
 
     def _build_gitignore_parser(self, docs_dir: str):
         """Build gitignore parser using gitignore-parser library."""
@@ -329,6 +333,8 @@ Examples:
             return False
 
     def list_indexes(self):
+        print("Stored LEANN indexes:")
+
         # Get all project directories with .leann
         global_registry = Path.home() / ".leann" / "projects.json"
         all_projects = []
@@ -354,485 +360,58 @@ Examples:
         if (current_path / ".leann" / "indexes").exists() and current_path not in valid_projects:
             valid_projects.append(current_path)
 
-        # Separate current and other projects
+        if not valid_projects:
-        other_projects = []
+            print(
-
+                "No indexes found. Use 'leann build <name> --docs <dir> [<dir2> ...]' to create one."
-        for project_path in valid_projects:
+            )
-            if project_path != current_path:
+            return
-                other_projects.append(project_path)
-
-        print("📚 LEANN Indexes")
-        print("=" * 50)
 
         total_indexes = 0
-        current_indexes_count = 0
+        current_dir = Path.cwd()
 
-        # Show current project first (most important)
+        for project_path in valid_projects:
-        print("\n🏠 Current Project")
+            indexes_dir = project_path / ".leann" / "indexes"
-        print(f"   {current_path}")
+            if not indexes_dir.exists():
-        print("   " + "─" * 45)
-
-        current_indexes = self._discover_indexes_in_project(current_path)
-        if current_indexes:
-            for idx in current_indexes:
-                total_indexes += 1
-                current_indexes_count += 1
-                type_icon = "📁" if idx["type"] == "cli" else "📄"
-                print(f"   {current_indexes_count}. {type_icon} {idx['name']} {idx['status']}")
-                if idx["size_mb"] > 0:
-                    print(f"      📦 Size: {idx['size_mb']:.1f} MB")
-        else:
-            print("   📭 No indexes in current project")
-
-        # Show other projects (reference information)
-        if other_projects:
-            print("\n\n🗂️  Other Projects")
-            print("   " + "─" * 45)
-
-            for project_path in other_projects:
-                project_indexes = self._discover_indexes_in_project(project_path)
-                if not project_indexes:
-                    continue
-
-                print(f"\n   📂 {project_path.name}")
-                print(f"      {project_path}")
-
-                for idx in project_indexes:
-                    total_indexes += 1
-                    type_icon = "📁" if idx["type"] == "cli" else "📄"
-                    print(f"      • {type_icon} {idx['name']} {idx['status']}")
-                    if idx["size_mb"] > 0:
-                        print(f"        📦 {idx['size_mb']:.1f} MB")
-
-        # Summary and usage info
-        print("\n" + "=" * 50)
-        if total_indexes == 0:
-            print("💡 Get started:")
-            print("   leann build my-docs --docs ./documents")
-        else:
-            # Count only projects that have at least one discoverable index
-            projects_count = sum(
-                1 for p in valid_projects if len(self._discover_indexes_in_project(p)) > 0
-            )
-            print(f"📊 Total: {total_indexes} indexes across {projects_count} projects")
-
-            if current_indexes_count > 0:
-                print("\n💫 Quick start (current project):")
-                # Get first index from current project for example
-                current_indexes_dir = current_path / ".leann" / "indexes"
-                if current_indexes_dir.exists():
-                    current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
-                    if current_index_dirs:
-                        example_name = current_index_dirs[0].name
-                        print(f'   leann search {example_name} "your query"')
-                        print(f"   leann ask {example_name} --interactive")
-            else:
-                print("\n💡 Create your first index:")
-                print("   leann build my-docs --docs ./documents")
-
-    def _discover_indexes_in_project(self, project_path: Path):
-        """Discover all indexes in a project directory (both CLI and apps formats)"""
-        indexes = []
-
-        # 1. CLI format: .leann/indexes/index_name/
-        cli_indexes_dir = project_path / ".leann" / "indexes"
-        if cli_indexes_dir.exists():
-            for index_dir in cli_indexes_dir.iterdir():
-                if index_dir.is_dir():
-                    meta_file = index_dir / "documents.leann.meta.json"
-                    status = "✅" if meta_file.exists() else "❌"
-
-                    size_mb = 0
-                    if meta_file.exists():
-                        try:
-                            size_mb = sum(
-                                f.stat().st_size for f in index_dir.iterdir() if f.is_file()
-                            ) / (1024 * 1024)
-                        except (OSError, PermissionError):
-                            pass
-
-                    indexes.append(
-                        {
-                            "name": index_dir.name,
-                            "type": "cli",
-                            "status": status,
-                            "size_mb": size_mb,
-                            "path": index_dir,
-                        }
-                    )
-
-        # 2. Apps format: *.leann.meta.json files anywhere in the project
-        cli_indexes_dir = project_path / ".leann" / "indexes"
-        for meta_file in project_path.rglob("*.leann.meta.json"):
-            if meta_file.is_file():
-                # Skip CLI-built indexes (which store meta under .leann/indexes/<name>/)
-                try:
-                    if cli_indexes_dir.exists() and cli_indexes_dir in meta_file.parents:
-                        continue
-                except Exception:
-                    pass
-                # Use the parent directory name as the app index display name
-                display_name = meta_file.parent.name
-                # Extract file base used to store files
-                file_base = meta_file.name.replace(".leann.meta.json", "")
-
-                # Apps indexes are considered complete if the .leann.meta.json file exists
-                status = "✅"
-
-                # Calculate total size of all related files (use file base)
-                size_mb = 0
-                try:
-                    index_dir = meta_file.parent
-                    for related_file in index_dir.glob(f"{file_base}.leann*"):
-                        size_mb += related_file.stat().st_size / (1024 * 1024)
-                except (OSError, PermissionError):
-                    pass
-
-                indexes.append(
-                    {
-                        "name": display_name,
-                        "type": "app",
-                        "status": status,
-                        "size_mb": size_mb,
-                        "path": meta_file,
-                    }
-                )
-
-        return indexes
-
-    def remove_index(self, index_name: str, force: bool = False):
-        """Safely remove an index - always show all matches for transparency"""
-
-        # Always do a comprehensive search for safety
-        print(f"🔍 Searching for all indexes named '{index_name}'...")
-        all_matches = self._find_all_matching_indexes(index_name)
-
-        if not all_matches:
-            print(f"❌ Index '{index_name}' not found in any project.")
-            return False
-
-        if len(all_matches) == 1:
-            return self._remove_single_match(all_matches[0], index_name, force)
-        else:
-            return self._remove_from_multiple_matches(all_matches, index_name, force)
-
-    def _find_all_matching_indexes(self, index_name: str):
-        """Find all indexes with the given name across all projects"""
-        matches = []
-
-        # Get all registered projects
-        global_registry = Path.home() / ".leann" / "projects.json"
-        all_projects = []
-
-        if global_registry.exists():
-            try:
-                import json
-
-                with open(global_registry) as f:
-                    all_projects = json.load(f)
-            except Exception:
-                pass
-
-        # Always include current project
-        current_path = Path.cwd()
-        if str(current_path) not in all_projects:
-            all_projects.append(str(current_path))
-
-        # Search across all projects
-        for project_dir in all_projects:
-            project_path = Path(project_dir)
-            if not project_path.exists():
                 continue
 
-            # 1) CLI-format index under .leann/indexes/<name>
+            index_dirs = [d for d in indexes_dir.iterdir() if d.is_dir()]
-            index_dir = project_path / ".leann" / "indexes" / index_name
+            if not index_dirs:
-            if index_dir.exists():
+                continue
-                is_current = project_path == current_path
-                matches.append(
-                    {
-                        "project_path": project_path,
-                        "index_dir": index_dir,
-                        "is_current": is_current,
-                        "kind": "cli",
-                    }
-                )
 
-            # 2) App-format indexes
+            # Show project header
-            # We support two ways of addressing apps:
+            if project_path == current_dir:
-            #   a) by the file base (e.g., `pdf_documents`)
+                print(f"\n📁 Current project ({project_path}):")
-            #   b) by the parent directory name (e.g., `new_txt`)
-            seen_app_meta = set()
-
-            # 2a) by file base
-            for meta_file in project_path.rglob(f"{index_name}.leann.meta.json"):
-                if meta_file.is_file():
-                    # Skip CLI-built indexes' meta under .leann/indexes
-                    try:
-                        cli_indexes_dir = project_path / ".leann" / "indexes"
-                        if cli_indexes_dir.exists() and cli_indexes_dir in meta_file.parents:
-                            continue
-                    except Exception:
-                        pass
-                    is_current = project_path == current_path
-                    key = (str(project_path), str(meta_file))
-                    if key in seen_app_meta:
-                        continue
-                    seen_app_meta.add(key)
-                    matches.append(
-                        {
-                            "project_path": project_path,
-                            "files_dir": meta_file.parent,
-                            "meta_file": meta_file,
-                            "is_current": is_current,
-                            "kind": "app",
-                            "display_name": meta_file.parent.name,
-                            "file_base": meta_file.name.replace(".leann.meta.json", ""),
-                        }
-                    )
-
-            # 2b) by parent directory name
-            for meta_file in project_path.rglob("*.leann.meta.json"):
-                if meta_file.is_file() and meta_file.parent.name == index_name:
-                    # Skip CLI-built indexes' meta under .leann/indexes
-                    try:
-                        cli_indexes_dir = project_path / ".leann" / "indexes"
-                        if cli_indexes_dir.exists() and cli_indexes_dir in meta_file.parents:
-                            continue
-                    except Exception:
-                        pass
-                    is_current = project_path == current_path
-                    key = (str(project_path), str(meta_file))
-                    if key in seen_app_meta:
-                        continue
-                    seen_app_meta.add(key)
-                    matches.append(
-                        {
-                            "project_path": project_path,
-                            "files_dir": meta_file.parent,
-                            "meta_file": meta_file,
-                            "is_current": is_current,
-                            "kind": "app",
-                            "display_name": meta_file.parent.name,
-                            "file_base": meta_file.name.replace(".leann.meta.json", ""),
-                        }
-                    )
-
-        # Sort: current project first, then by project name
-        matches.sort(key=lambda x: (not x["is_current"], x["project_path"].name))
-        return matches
-
-    def _remove_single_match(self, match, index_name: str, force: bool):
-        """Handle removal when only one match is found"""
-        project_path = match["project_path"]
-        is_current = match["is_current"]
-        kind = match.get("kind", "cli")
-
-        if is_current:
-            location_info = "current project"
-            emoji = "🏠"
-        else:
-            location_info = f"other project '{project_path.name}'"
-            emoji = "📂"
-
-        print(f"✅ Found 1 index named '{index_name}':")
-        print(f"   {emoji} Location: {location_info}")
-        if kind == "cli":
-            print(f"   📍 Path: {project_path / '.leann' / 'indexes' / index_name}")
-        else:
-            print(f"   📍 Meta: {match['meta_file']}")
-
-        if not force:
-            if not is_current:
-                print("\n⚠️  CROSS-PROJECT REMOVAL!")
-                print("   This will delete the index from another project.")
-
-            response = input(f"   ❓ Confirm removal from {location_info}? (y/N): ").strip().lower()
-            if response not in ["y", "yes"]:
-                print("   ❌ Removal cancelled.")
-                return False
-
-        if kind == "cli":
-            return self._delete_index_directory(
-                match["index_dir"],
-                index_name,
-                project_path if not is_current else None,
-                is_app=False,
-            )
-        else:
-            return self._delete_index_directory(
-                match["files_dir"],
-                match.get("display_name", index_name),
-                project_path if not is_current else None,
-                is_app=True,
-                meta_file=match.get("meta_file"),
-                app_file_base=match.get("file_base"),
-            )
-
-    def _remove_from_multiple_matches(self, matches, index_name: str, force: bool):
-        """Handle removal when multiple matches are found"""
-
-        print(f"⚠️  Found {len(matches)} indexes named '{index_name}':")
-        print("   " + "─" * 50)
-
-        for i, match in enumerate(matches, 1):
-            project_path = match["project_path"]
-            is_current = match["is_current"]
-            kind = match.get("kind", "cli")
-
-            if is_current:
-                print(f"   {i}. 🏠 Current project ({'CLI' if kind == 'cli' else 'APP'})")
             else:
-                print(f"   {i}. 📂 {project_path.name} ({'CLI' if kind == 'cli' else 'APP'})")
+                print(f"\n📂 {project_path}:")
 
-            # Show path details
+            for index_dir in index_dirs:
-            if kind == "cli":
+                total_indexes += 1
-                print(f"      📍 {project_path / '.leann' / 'indexes' / index_name}")
+                index_name = index_dir.name
-            else:
+                meta_file = index_dir / "documents.leann.meta.json"
-                print(f"      📍 {match['meta_file']}")
+                status = "✓" if meta_file.exists() else "✗"
 
-            # Show size info
+                print(f"  {total_indexes}. {index_name} [{status}]")
-            try:
+                if status == "✓":
-                if kind == "cli":
+                    size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
-                    size_mb = sum(
+                        1024 * 1024
-                        f.stat().st_size for f in match["index_dir"].iterdir() if f.is_file()
-                    ) / (1024 * 1024)
-                else:
-                    file_base = match.get("file_base")
-                    size_mb = 0.0
-                    if file_base:
-                        size_mb = sum(
-                            f.stat().st_size
-                            for f in match["files_dir"].glob(f"{file_base}.leann*")
-                            if f.is_file()
-                        ) / (1024 * 1024)
-                print(f"      📦 Size: {size_mb:.1f} MB")
-            except (OSError, PermissionError):
-                pass
-
-        print("   " + "─" * 50)
-
-        if force:
-            print("   ❌ Multiple matches found, but --force specified.")
-            print("   Please run without --force to choose which one to remove.")
-            return False
-
-        try:
-            choice = input(
-                f"   ❓ Which one to remove? (1-{len(matches)}, or 'c' to cancel): "
-            ).strip()
-            if choice.lower() == "c":
-                print("   ❌ Removal cancelled.")
-                return False
-
-            choice_idx = int(choice) - 1
-            if 0 <= choice_idx < len(matches):
-                selected_match = matches[choice_idx]
-                project_path = selected_match["project_path"]
-                is_current = selected_match["is_current"]
-                kind = selected_match.get("kind", "cli")
-
-                location = "current project" if is_current else f"'{project_path.name}' project"
-                print(f"   🎯 Selected: Remove from {location}")
-
-                # Final confirmation for safety
-                confirm = input(
-                    f"   ❓ FINAL CONFIRMATION - Type '{index_name}' to proceed: "
-                ).strip()
-                if confirm != index_name:
-                    print("   ❌ Confirmation failed. Removal cancelled.")
-                    return False
-
-                if kind == "cli":
-                    return self._delete_index_directory(
-                        selected_match["index_dir"],
-                        index_name,
-                        project_path if not is_current else None,
-                        is_app=False,
                     )
-                else:
+                    print(f"     Size: {size_mb:.1f} MB")
-                    return self._delete_index_directory(
-                        selected_match["files_dir"],
-                        selected_match.get("display_name", index_name),
-                        project_path if not is_current else None,
-                        is_app=True,
-                        meta_file=selected_match.get("meta_file"),
-                        app_file_base=selected_match.get("file_base"),
-                    )
-            else:
-                print("   ❌ Invalid choice. Removal cancelled.")
-                return False
 
-        except (ValueError, KeyboardInterrupt):
+        if total_indexes > 0:
-            print("\n   ❌ Invalid input. Removal cancelled.")
+            print(f"\nTotal: {total_indexes} indexes across {len(valid_projects)} projects")
-            return False
+            print("\nUsage (current project only):")
 
-    def _delete_index_directory(
+            # Show example from current project
-        self,
+            current_indexes_dir = current_dir / ".leann" / "indexes"
-        index_dir: Path,
+            if current_indexes_dir.exists():
-        index_display_name: str,
+                current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
-        project_path: Optional[Path] = None,
+                if current_index_dirs:
-        is_app: bool = False,
+                    example_name = current_index_dirs[0].name
-        meta_file: Optional[Path] = None,
+                    print(f'  leann search {example_name} "your query"')
-        app_file_base: Optional[str] = None,
+                    print(f"  leann ask {example_name} --interactive")
-    ):
-        """Delete a CLI index directory or APP index files safely."""
-        try:
-            if is_app:
-                removed = 0
-                errors = 0
-                # Delete only files that belong to this app index (based on file base)
-                pattern_base = app_file_base or ""
-                for f in index_dir.glob(f"{pattern_base}.leann*"):
-                    try:
-                        f.unlink()
-                        removed += 1
-                    except Exception:
-                        errors += 1
-                # Best-effort: also remove the meta file if specified and still exists
-                if meta_file and meta_file.exists():
-                    try:
-                        meta_file.unlink()
-                        removed += 1
-                    except Exception:
-                        errors += 1
-
-                if removed > 0 and errors == 0:
-                    if project_path:
-                        print(
-                            f"✅ App index '{index_display_name}' removed from {project_path.name}"
-                        )
-                    else:
-                        print(f"✅ App index '{index_display_name}' removed successfully")
-                    return True
-                elif removed > 0 and errors > 0:
-                    print(
-                        f"⚠️  App index '{index_display_name}' partially removed (some files couldn't be deleted)"
-                    )
-                    return True
-                else:
-                    print(
-                        f"❌ No files found to remove for app index '{index_display_name}' in {index_dir}"
-                    )
-                    return False
-            else:
-                import shutil
-
-                shutil.rmtree(index_dir)
-
-                if project_path:
-                    print(f"✅ Index '{index_display_name}' removed from {project_path.name}")
-                else:
-                    print(f"✅ Index '{index_display_name}' removed successfully")
-                return True
-        except Exception as e:
-            print(f"❌ Error removing index '{index_display_name}': {e}")
-            return False
 
     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):
@@ -876,10 +455,6 @@ 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 ''}...")
@@ -892,12 +467,8 @@ 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():
@@ -908,7 +479,6 @@ 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)
@@ -1007,8 +577,6 @@ 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:
@@ -1036,7 +604,6 @@ 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()
@@ -1065,7 +632,6 @@ 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)
 
@@ -1215,9 +781,7 @@ Examples:
             paragraph_separator="\n\n",
         )
 
-        all_texts = self.load_documents(
+        all_texts = self.load_documents(docs_paths, args.file_types)
-            docs_paths, args.file_types, include_hidden=args.include_hidden
-        )
         if not all_texts:
             print("No documents found")
             return
@@ -1249,101 +813,13 @@ Examples:
     async def search_documents(self, args):
         index_name = args.index_name
         query = args.query
-
-        # First try to find the index in current project
         index_path = self.get_index_path(index_name)
-        if self.index_exists(index_name):
-            # Found in current project, use it
-            pass
-        else:
-            # Search across all registered projects (like list_indexes does)
-            all_matches = self._find_all_matching_indexes(index_name)
-            if not all_matches:
-                print(
-                    f"Index '{index_name}' not found. Use 'leann build {index_name} --docs <dir> [<dir2> ...]' to create it."
-                )
-                return
-            elif len(all_matches) == 1:
-                # Found exactly one match, use it
-                match = all_matches[0]
-                if match["kind"] == "cli":
-                    index_path = str(match["index_dir"] / "documents.leann")
-                else:
-                    # App format: use the meta file to construct the path
-                    meta_file = match["meta_file"]
-                    file_base = match["file_base"]
-                    index_path = str(meta_file.parent / f"{file_base}.leann")
 
-                project_info = (
+        if not self.index_exists(index_name):
-                    "current project"
+            print(
-                    if match["is_current"]
+                f"Index '{index_name}' not found. Use 'leann build {index_name} --docs <dir> [<dir2> ...]' to create it."
-                    else f"project '{match['project_path'].name}'"
+            )
-                )
+            return
-                print(f"Using index '{index_name}' from {project_info}")
-            else:
-                # Multiple matches found
-                if args.non_interactive:
-                    # Non-interactive mode: automatically select the best match
-                    # Priority: current project first, then first available
-                    current_matches = [m for m in all_matches if m["is_current"]]
-                    if current_matches:
-                        match = current_matches[0]
-                        location_desc = "current project"
-                    else:
-                        match = all_matches[0]
-                        location_desc = f"project '{match['project_path'].name}'"
-
-                    if match["kind"] == "cli":
-                        index_path = str(match["index_dir"] / "documents.leann")
-                    else:
-                        meta_file = match["meta_file"]
-                        file_base = match["file_base"]
-                        index_path = str(meta_file.parent / f"{file_base}.leann")
-
-                    print(
-                        f"Found {len(all_matches)} indexes named '{index_name}', using index from {location_desc}"
-                    )
-                else:
-                    # Interactive mode: ask user to choose
-                    print(f"Found {len(all_matches)} indexes named '{index_name}':")
-                    for i, match in enumerate(all_matches, 1):
-                        project_path = match["project_path"]
-                        is_current = match["is_current"]
-                        kind = match.get("kind", "cli")
-
-                        if is_current:
-                            print(
-                                f"   {i}. 🏠 Current project ({'CLI' if kind == 'cli' else 'APP'})"
-                            )
-                        else:
-                            print(
-                                f"   {i}. 📂 {project_path.name} ({'CLI' if kind == 'cli' else 'APP'})"
-                            )
-
-                    try:
-                        choice = input(f"Which index to search? (1-{len(all_matches)}): ").strip()
-                        choice_idx = int(choice) - 1
-                        if 0 <= choice_idx < len(all_matches):
-                            match = all_matches[choice_idx]
-                            if match["kind"] == "cli":
-                                index_path = str(match["index_dir"] / "documents.leann")
-                            else:
-                                meta_file = match["meta_file"]
-                                file_base = match["file_base"]
-                                index_path = str(meta_file.parent / f"{file_base}.leann")
-
-                            project_info = (
-                                "current project"
-                                if match["is_current"]
-                                else f"project '{match['project_path'].name}'"
-                            )
-                            print(f"Using index '{index_name}' from {project_info}")
-                        else:
-                            print("Invalid choice. Aborting search.")
-                            return
-                    except (ValueError, KeyboardInterrupt):
-                        print("Invalid input. Aborting search.")
-                        return
 
         searcher = LeannSearcher(index_path=index_path)
         results = searcher.search(
@@ -1442,8 +918,6 @@ Examples:
 
         if args.command == "list":
             self.list_indexes()
-        elif args.command == "remove":
-            self.remove_index(args.index_name, args.force)
         elif args.command == "build":
             await self.build_index(args)
         elif args.command == "search":
@@ -1455,15 +929,10 @@ Examples:
 
 
 def main():
-    import logging
-
     import dotenv
 
     dotenv.load_dotenv()
 
-    # Set clean logging for CLI usage
-    logging.getLogger().setLevel(logging.WARNING)  # Only show warnings and errors
-
     cli = LeannCLI()
     asyncio.run(cli.run())
 

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

@@ -57,8 +57,6 @@ def compute_embeddings(
         return compute_embeddings_mlx(texts, model_name)
     elif mode == "ollama":
         return compute_embeddings_ollama(texts, model_name, is_build=is_build)
-    elif mode == "gemini":
-        return compute_embeddings_gemini(texts, model_name, is_build=is_build)
     else:
         raise ValueError(f"Unsupported embedding mode: {mode}")
 
@@ -670,83 +668,3 @@ def compute_embeddings_ollama(
     logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
 
     return embeddings
-
-
-def compute_embeddings_gemini(
-    texts: list[str], model_name: str = "text-embedding-004", is_build: bool = False
-) -> np.ndarray:
-    """
-    Compute embeddings using Google Gemini API.
-
-    Args:
-        texts: List of texts to compute embeddings for
-        model_name: Gemini model name (default: "text-embedding-004")
-        is_build: Whether this is a build operation (shows progress bar)
-
-    Returns:
-        Embeddings array, shape: (len(texts), embedding_dim)
-    """
-    try:
-        import os
-
-        import google.genai as genai
-    except ImportError as e:
-        raise ImportError(f"Google GenAI package not installed: {e}")
-
-    api_key = os.getenv("GEMINI_API_KEY")
-    if not api_key:
-        raise RuntimeError("GEMINI_API_KEY environment variable not set")
-
-    # Cache Gemini client
-    cache_key = "gemini_client"
-    if cache_key in _model_cache:
-        client = _model_cache[cache_key]
-    else:
-        client = genai.Client(api_key=api_key)
-        _model_cache[cache_key] = client
-        logger.info("Gemini client cached")
-
-    logger.info(
-        f"Computing embeddings for {len(texts)} texts using Gemini API, model: '{model_name}'"
-    )
-
-    # Gemini supports batch embedding
-    max_batch_size = 100  # Conservative batch size for Gemini
-    all_embeddings = []
-
-    try:
-        from tqdm import tqdm
-
-        total_batches = (len(texts) + max_batch_size - 1) // max_batch_size
-        batch_range = range(0, len(texts), max_batch_size)
-        batch_iterator = tqdm(
-            batch_range, desc="Computing embeddings", unit="batch", total=total_batches
-        )
-    except ImportError:
-        # Fallback when tqdm is not available
-        batch_iterator = range(0, len(texts), max_batch_size)
-
-    for i in batch_iterator:
-        batch_texts = texts[i : i + max_batch_size]
-
-        try:
-            # Use the embed_content method from the new Google GenAI SDK
-            response = client.models.embed_content(
-                model=model_name,
-                contents=batch_texts,
-                config=genai.types.EmbedContentConfig(
-                    task_type="RETRIEVAL_DOCUMENT"  # For document embedding
-                ),
-            )
-
-            # Extract embeddings from response
-            for embedding_data in response.embeddings:
-                all_embeddings.append(embedding_data.values)
-        except Exception as e:
-            logger.error(f"Batch {i} failed: {e}")
-            raise
-
-    embeddings = np.array(all_embeddings, dtype=np.float32)
-    logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
-
-    return embeddings

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

@@ -94,7 +94,7 @@ def handle_request(request):
                         },
                     }
 
-                # Build simplified command with non-interactive flag for MCP compatibility
+                # Build simplified command
                 cmd = [
                     "leann",
                     "search",
@@ -102,7 +102,6 @@ def handle_request(request):
                     args["query"],
                     f"--top-k={args.get('top_k', 5)}",
                     f"--complexity={args.get('complexity', 32)}",
-                    "--non-interactive",
                 ]
                 result = subprocess.run(cmd, capture_output=True, text=True)
 

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

@@ -2,17 +2,11 @@
 
 import importlib
 import importlib.metadata
-import json
+from typing import TYPE_CHECKING
-import logging
-from pathlib import Path
-from typing import TYPE_CHECKING, Optional, Union
 
 if TYPE_CHECKING:
     from leann.interface import LeannBackendFactoryInterface
 
-# Set up logger for this module
-logger = logging.getLogger(__name__)
-
 BACKEND_REGISTRY: dict[str, "LeannBackendFactoryInterface"] = {}
 
 
@@ -20,7 +14,7 @@ def register_backend(name: str):
     """A decorator to register a new backend class."""
 
     def decorator(cls):
-        logger.debug(f"Registering backend '{name}'")
+        print(f"INFO: Registering backend '{name}'")
         BACKEND_REGISTRY[name] = cls
         return cls
 
@@ -45,54 +39,3 @@ def autodiscover_backends():
             # print(f"WARN: Could not import backend module '{backend_module_name}': {e}")
             pass
     # print("INFO: Backend auto-discovery finished.")
-
-
-def register_project_directory(project_dir: Optional[Union[str, Path]] = None):
-    """
-    Register a project directory in the global LEANN registry.
-
-    This allows `leann list` to discover indexes created by apps or other tools.
-
-    Args:
-        project_dir: Directory to register. If None, uses current working directory.
-    """
-    if project_dir is None:
-        project_dir = Path.cwd()
-    else:
-        project_dir = Path(project_dir)
-
-    # Only register directories that have some kind of LEANN content
-    # Either .leann/indexes/ (CLI format) or *.leann.meta.json files (apps format)
-    has_cli_indexes = (project_dir / ".leann" / "indexes").exists()
-    has_app_indexes = any(project_dir.rglob("*.leann.meta.json"))
-
-    if not (has_cli_indexes or has_app_indexes):
-        # Don't register if there are no LEANN indexes
-        return
-
-    global_registry = Path.home() / ".leann" / "projects.json"
-    global_registry.parent.mkdir(exist_ok=True)
-
-    project_str = str(project_dir.resolve())
-
-    # Load existing registry
-    projects = []
-    if global_registry.exists():
-        try:
-            with open(global_registry) as f:
-                projects = json.load(f)
-        except Exception:
-            logger.debug("Could not load existing project registry")
-            projects = []
-
-    # Add project if not already present
-    if project_str not in projects:
-        projects.append(project_str)
-
-        # Save updated registry
-        try:
-            with open(global_registry, "w") as f:
-                json.dump(projects, f, indent=2)
-            logger.debug(f"Registered project directory: {project_str}")
-        except Exception as e:
-            logger.warning(f"Could not save project registry: {e}")

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.3.2"
+version = "0.2.9"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"

pyproject.toml

@@ -14,6 +14,8 @@ dependencies = [
     "numpy>=1.26.0",
     "torch",
     "tqdm",
+    "flask",
+    "flask_compress",
     "datasets>=2.15.0",
     "evaluate",
     "colorama",
@@ -64,7 +66,9 @@ test = [
     "pytest>=7.0",
     "pytest-timeout>=2.0",
     "llama-index-core>=0.12.0",
+    "llama-index-readers-file>=0.4.0",
     "python-dotenv>=1.0.0",
+    "sentence-transformers>=2.2.0",
 ]
 
 diskann = [
@@ -96,8 +100,13 @@ leann-backend-hnsw = { path = "packages/leann-backend-hnsw", editable = true }
 [tool.ruff]
 target-version = "py39"
 line-length = 100
-extend-exclude = ["third_party"]
+extend-exclude = [
-
+    "third_party",
+    "*.egg-info",
+    "__pycache__",
+    ".git",
+    ".venv",
+]
 
 [tool.ruff.lint]
 select = [
@@ -120,12 +129,21 @@ ignore = [
     "RUF012", # mutable class attributes should be annotated with typing.ClassVar
 ]
 
+[tool.ruff.lint.per-file-ignores]
+"test/**/*.py" = ["E402"]      # module level import not at top of file (common in tests)
+"examples/**/*.py" = ["E402"]  # module level import not at top of file (common in examples)
+
 [tool.ruff.format]
 quote-style = "double"
 indent-style = "space"
 skip-magic-trailing-comma = false
 line-ending = "auto"
 
+[dependency-groups]
+dev = [
+    "ruff>=0.12.4",
+]
+
 [tool.lychee]
 accept = ["200", "403", "429", "503"]
 timeout = 20