feat: Add Google Gemini API support for chat and embeddings (#57)

- Add GeminiChat class with gemini-2.5-flash model support
- Add compute_embeddings_gemini function with text-embedding-004 model
- Update get_llm factory to support "gemini" type
- Update API documentation to include gemini embedding mode
- Support temperature, max_tokens, top_p parameters for Gemini chat
- Support batch embedding processing with progress bars
- Add proper error handling and API key validation

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%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
+  <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/License-MIT-green.svg" alt="MIT License">
   <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue" alt="MCP Integration">
 </p>
@@ -94,7 +94,9 @@ CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
 
 **Linux:**
 ```bash
-sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
+# Ubuntu/Debian (For Arch Linux: sudo pacman -S blas lapack openblas libaio boost protobuf abseil-cpp zeromq)
+sudo apt-get update && sudo apt-get install -y libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
+
 uv sync
 ```
 

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.2.9"
-dependencies = ["leann-core==0.2.9", "numpy", "protobuf>=3.19.0"]
+version = "0.3.0"
+dependencies = ["leann-core==0.3.0", "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 = "0.2.9"
+version = "0.3.0"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.2.9",
+    "leann-core==0.3.0",
     "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 = "0.2.9"
+version = "0.3.0"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -307,6 +307,23 @@ class LeannBuilder:
     def build_index(self, index_path: str):
         if not self.chunks:
             raise ValueError("No chunks added.")
+
+        # Filter out invalid/empty text chunks early to keep passage and embedding counts aligned
+        valid_chunks: list[dict[str, Any]] = []
+        skipped = 0
+        for chunk in self.chunks:
+            text = chunk.get("text", "")
+            if isinstance(text, str) and text.strip():
+                valid_chunks.append(chunk)
+            else:
+                skipped += 1
+        if skipped > 0:
+            print(
+                f"Warning: Skipping {skipped} empty/invalid text chunk(s). Processing {len(valid_chunks)} valid chunks"
+            )
+            self.chunks = valid_chunks
+            if not self.chunks:
+                raise ValueError("All provided chunks are empty or invalid. Nothing to index.")
         if self.dimensions is None:
             self.dimensions = len(
                 compute_embeddings(

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

@@ -148,6 +148,12 @@ 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,
@@ -411,7 +417,10 @@ Examples:
                     print(f"  leann ask {example_name} --interactive")
 
     def load_documents(
-        self, docs_paths: Union[str, list], custom_file_types: Union[str, None] = None
+        self,
+        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):
@@ -455,6 +464,10 @@ 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 ''}...")
@@ -467,8 +480,12 @@ Examples:
 
                 files_by_dir = defaultdict(list)
                 for file_path in files:
-                    parent_dir = str(Path(file_path).parent)
-                    files_by_dir[parent_dir].append(file_path)
+                    file_path_obj = Path(file_path)
+                    if not include_hidden and _path_has_hidden_segment(file_path_obj):
+                        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():
@@ -479,6 +496,7 @@ 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)
@@ -577,6 +595,8 @@ 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:
@@ -604,6 +624,7 @@ 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()
@@ -632,6 +653,7 @@ 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)
 
@@ -781,7 +803,9 @@ Examples:
             paragraph_separator="\n\n",
         )
 
-        all_texts = self.load_documents(docs_paths, args.file_types)
+        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

@@ -246,6 +246,16 @@ def compute_embeddings_openai(texts: list[str], model_name: str) -> np.ndarray:
     except ImportError as e:
         raise ImportError(f"OpenAI package not installed: {e}")
 
+    # Validate input list
+    if not texts:
+        raise ValueError("Cannot compute embeddings for empty text list")
+    # Extra validation: abort early if any item is empty/whitespace
+    invalid_count = sum(1 for t in texts if not isinstance(t, str) or not t.strip())
+    if invalid_count > 0:
+        raise ValueError(
+            f"Found {invalid_count} empty/invalid text(s) in input. Upstream should filter before calling OpenAI."
+        )
+
     api_key = os.getenv("OPENAI_API_KEY")
     if not api_key:
         raise RuntimeError("OPENAI_API_KEY environment variable not set")

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.2.9"
+version = "0.3.0"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"