fix: Update DiskANN submodule with LAPACKE library linking fix

- Points to commit 19f9603 with explicit LAPACKE library discovery and linking
- Resolves 'undefined symbol: LAPACKE_sgesdd' runtime error on ARM64 Linux
- Completes ARM64 Linux wheel build compatibility for Docker deployments

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

.github/workflows/build-reusable.yml

@@ -54,6 +54,17 @@ jobs:
             python: '3.12'
           - os: ubuntu-22.04
             python: '3.13'
+          # ARM64 Linux builds
+          - os: ubuntu-24.04-arm
+            python: '3.9'
+          - os: ubuntu-24.04-arm
+            python: '3.10'
+          - os: ubuntu-24.04-arm
+            python: '3.11'
+          - os: ubuntu-24.04-arm
+            python: '3.12'
+          - os: ubuntu-24.04-arm
+            python: '3.13'
           - os: macos-14
             python: '3.9'
           - os: macos-14
@@ -108,13 +119,46 @@ jobs:
             pkg-config 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" >> $GITHUB_ENV
-          echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV
+          # Debug: Show system information
+          echo "🔍 System Information:"
+          echo "Architecture: $(uname -m)"
+          echo "OS: $(uname -a)"
+          echo "CPU info: $(lscpu | head -5)"
+
+          # Install math library based on architecture
+          ARCH=$(uname -m)
+          echo "🔍 Setting up math library for architecture: $ARCH"
+
+          if [[ "$ARCH" == "x86_64" ]]; then
+            # Install Intel MKL for DiskANN on x86_64
+            echo "📦 Installing Intel MKL for x86_64..."
+            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" >> $GITHUB_ENV
+            echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV
+            echo "✅ Intel MKL installed for x86_64"
+
+            # Debug: Check MKL installation
+            echo "🔍 MKL Installation Check:"
+            ls -la /opt/intel/oneapi/mkl/latest/ || echo "MKL directory not found"
+            ls -la /opt/intel/oneapi/mkl/latest/lib/ || echo "MKL lib directory not found"
+
+          elif [[ "$ARCH" == "aarch64" ]]; then
+            # Use OpenBLAS for ARM64 (MKL installer not compatible with ARM64)
+            echo "📦 Installing OpenBLAS for ARM64..."
+            sudo apt-get install -y libopenblas-dev liblapack-dev liblapacke-dev
+            echo "✅ OpenBLAS installed for ARM64"
+
+            # Debug: Check OpenBLAS installation
+            echo "🔍 OpenBLAS Installation Check:"
+            dpkg -l | grep openblas || echo "OpenBLAS package not found"
+            ls -la /usr/lib/aarch64-linux-gnu/openblas/ || echo "OpenBLAS directory not found"
+          fi
+
+          # Debug: Show final library paths
+          echo "🔍 Final LD_LIBRARY_PATH: $LD_LIBRARY_PATH"
 
       - name: Install system dependencies (macOS)
         if: runner.os == 'macOS'

packages/leann-backend-hnsw/CMakeLists.txt

@@ -49,9 +49,28 @@ set(BUILD_TESTING OFF CACHE BOOL "" FORCE)
 set(FAISS_ENABLE_C_API OFF CACHE BOOL "" FORCE)
 set(FAISS_OPT_LEVEL "generic" CACHE STRING "" FORCE)
 
-# Disable additional SIMD versions to speed up compilation
+# Disable x86-specific SIMD optimizations (important for ARM64 compatibility)
 set(FAISS_ENABLE_AVX2 OFF CACHE BOOL "" FORCE)
 set(FAISS_ENABLE_AVX512 OFF CACHE BOOL "" FORCE)
+set(FAISS_ENABLE_SSE4_1 OFF CACHE BOOL "" FORCE)
+
+# ARM64-specific configuration
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
+    message(STATUS "Configuring Faiss for ARM64 architecture")
+
+    if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
+        # Use SVE optimization level for ARM64 Linux (as seen in Faiss conda build)
+        set(FAISS_OPT_LEVEL "sve" CACHE STRING "" FORCE)
+        message(STATUS "Setting FAISS_OPT_LEVEL to 'sve' for ARM64 Linux")
+    else()
+        # Use generic optimization for other ARM64 platforms (like macOS)
+        set(FAISS_OPT_LEVEL "generic" CACHE STRING "" FORCE)
+        message(STATUS "Setting FAISS_OPT_LEVEL to 'generic' for ARM64 ${CMAKE_SYSTEM_NAME}")
+    endif()
+
+    # ARM64 compatibility: Faiss submodule has been modified to fix x86 header inclusion
+    message(STATUS "Using ARM64-compatible Faiss submodule")
+endif()
 
 # Additional optimization options from INSTALL.md
 set(CMAKE_BUILD_TYPE "Release" CACHE STRING "" FORCE)

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

@@ -322,17 +322,9 @@ Examples:
 
         return basic_matches
 
-    def _should_exclude_file(self, file_path: Path, gitignore_matches) -> bool:
-        """Check if a file should be excluded using gitignore parser.
-
-        Always match against absolute, posix-style paths for consistency with
-        gitignore_parser expectations.
-        """
-        try:
-            absolute_path = file_path.resolve()
-        except Exception:
-            absolute_path = Path(str(file_path))
-        return gitignore_matches(absolute_path.as_posix())
+    def _should_exclude_file(self, relative_path: Path, gitignore_matches) -> bool:
+        """Check if a file should be excluded using gitignore parser."""
+        return gitignore_matches(str(relative_path))
 
     def _is_git_submodule(self, path: Path) -> bool:
         """Check if a path is a git submodule."""
@@ -404,9 +396,7 @@ Examples:
         print(f"   {current_path}")
         print("   " + "─" * 45)
 
-        current_indexes = self._discover_indexes_in_project(
-            current_path, exclude_dirs=other_projects
-        )
+        current_indexes = self._discover_indexes_in_project(current_path)
         if current_indexes:
             for idx in current_indexes:
                 total_indexes += 1
@@ -445,14 +435,9 @@ Examples:
             print("   leann build my-docs --docs ./documents")
         else:
             # Count only projects that have at least one discoverable index
-            projects_count = 0
-            for p in valid_projects:
-                if p == current_path:
-                    discovered = self._discover_indexes_in_project(p, exclude_dirs=other_projects)
-                else:
-                    discovered = self._discover_indexes_in_project(p)
-                if len(discovered) > 0:
-                    projects_count += 1
+            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:
@@ -469,22 +454,9 @@ Examples:
                 print("\n💡 Create your first index:")
                 print("   leann build my-docs --docs ./documents")
 
-    def _discover_indexes_in_project(
-        self, project_path: Path, exclude_dirs: Optional[list[Path]] = None
-    ):
-        """Discover all indexes in a project directory (both CLI and apps formats)
-
-        exclude_dirs: when provided, skip any APP-format index files that are
-        located under these directories. This prevents duplicates when the
-        current project is a parent directory of other registered projects.
-        """
+    def _discover_indexes_in_project(self, project_path: Path):
+        """Discover all indexes in a project directory (both CLI and apps formats)"""
         indexes = []
-        exclude_dirs = exclude_dirs or []
-        # normalize to resolved paths once for comparison
-        try:
-            exclude_dirs_resolved = [p.resolve() for p in exclude_dirs]
-        except Exception:
-            exclude_dirs_resolved = exclude_dirs
 
         # 1. CLI format: .leann/indexes/index_name/
         cli_indexes_dir = project_path / ".leann" / "indexes"
@@ -523,17 +495,6 @@ Examples:
                         continue
                 except Exception:
                     pass
-                # Skip meta files that live under excluded directories
-                try:
-                    meta_parent_resolved = meta_file.parent.resolve()
-                    if any(
-                        meta_parent_resolved.is_relative_to(ex_dir)
-                        for ex_dir in exclude_dirs_resolved
-                    ):
-                        continue
-                except Exception:
-                    # best effort; if resolve or comparison fails, do not exclude
-                    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
@@ -1061,8 +1022,7 @@ Examples:
 
             # Try to use better PDF parsers first, but only if PDFs are requested
             documents = []
-            # Use resolved absolute paths to avoid mismatches (symlinks, relative vs absolute)
-            docs_path = Path(docs_dir).resolve()
+            docs_path = Path(docs_dir)
 
             # Check if we should process PDFs
             should_process_pdfs = custom_file_types is None or ".pdf" in custom_file_types
@@ -1071,15 +1031,10 @@ Examples:
                 for file_path in docs_path.rglob("*.pdf"):
                     # Check if file matches any exclude pattern
                     try:
-                        # Ensure both paths are resolved before computing relativity
-                        file_path_resolved = file_path.resolve()
-                        # Determine directory scope using the non-resolved path to avoid
-                        # misclassifying symlinked entries as outside the docs directory
                         relative_path = file_path.relative_to(docs_path)
                         if not include_hidden and _path_has_hidden_segment(relative_path):
                             continue
-                        # Use absolute path for gitignore matching
-                        if self._should_exclude_file(file_path_resolved, gitignore_matches):
+                        if self._should_exclude_file(relative_path, gitignore_matches):
                             continue
                     except ValueError:
                         # Skip files that can't be made relative to docs_path
@@ -1122,11 +1077,10 @@ Examples:
                 ) -> bool:
                     """Return True if file should be included (not excluded)"""
                     try:
-                        docs_path_obj = Path(docs_dir).resolve()
-                        file_path_obj = Path(file_path).resolve()
-                        # Use absolute path for gitignore matching
-                        _ = file_path_obj.relative_to(docs_path_obj)  # validate scope
-                        return not self._should_exclude_file(file_path_obj, gitignore_matches)
+                        docs_path_obj = Path(docs_dir)
+                        file_path_obj = Path(file_path)
+                        relative_path = file_path_obj.relative_to(docs_path_obj)
+                        return not self._should_exclude_file(relative_path, gitignore_matches)
                     except (ValueError, OSError):
                         return True  # Include files that can't be processed