a85d0ad4a7
* feat: add metadata output to search results - Add --show-metadata flag to display file paths in search results - Preserve document metadata (file_path, file_name, timestamps) during chunking - Update MCP tool schema to support show_metadata parameter - Enhance CLI search output to display metadata when requested - Fix pre-existing bug: args.backend -> args.backend_name Resolves yichuan-w/LEANN#144 * fix: resolve ZMQ linking issues in Python extension - Use pkg_check_modules IMPORTED_TARGET to create PkgConfig::ZMQ - Set PKG_CONFIG_PATH to prioritize ARM64 Homebrew on Apple Silicon - Override macOS -undefined dynamic_lookup to force proper symbol resolution - Use PUBLIC linkage for ZMQ in faiss library for transitive linking - Mark cppzmq includes as SYSTEM to suppress warnings Fixes editable install ZMQ symbol errors while maintaining compatibility across Linux, macOS Intel, and macOS ARM64 platforms. * style: apply ruff formatting * chore: update faiss submodule to use ww2283 fork Use ww2283/faiss fork with fix/zmq-linking branch to resolve CI checkout failures. The ZMQ linking fixes are not yet merged upstream. * feat: implement true batch processing for Ollama embeddings Migrate from deprecated /api/embeddings to modern /api/embed endpoint which supports batch inputs. This reduces HTTP overhead by sending 32 texts per request instead of making individual API calls. Changes: - Update endpoint from /api/embeddings to /api/embed - Change parameter from 'prompt' (single) to 'input' (array) - Update response parsing for batch embeddings array - Increase timeout to 60s for batch processing - Improve error handling for batch requests Performance: - Reduces API calls by 32x (batch size) - Eliminates HTTP connection overhead per text - Note: Ollama still processes batch items sequentially internally Related: #151 * fall back to original faiss as i merge the PR --------- Co-authored-by: yichuan520030910320 <yichuan_wang@berkeley.edu>
105 lines
4.2 KiB
CMake
105 lines
4.2 KiB
CMake
cmake_minimum_required(VERSION 3.24)
|
|
project(leann_backend_hnsw_wrapper)
|
|
set(CMAKE_C_COMPILER_WORKS 1)
|
|
set(CMAKE_CXX_COMPILER_WORKS 1)
|
|
|
|
# Set OpenMP path for macOS
|
|
if(APPLE)
|
|
# Detect Homebrew installation path (Apple Silicon vs Intel)
|
|
if(EXISTS "/opt/homebrew/opt/libomp")
|
|
set(HOMEBREW_PREFIX "/opt/homebrew")
|
|
elseif(EXISTS "/usr/local/opt/libomp")
|
|
set(HOMEBREW_PREFIX "/usr/local")
|
|
else()
|
|
message(FATAL_ERROR "Could not find libomp installation. Please install with: brew install libomp")
|
|
endif()
|
|
|
|
set(OpenMP_C_FLAGS "-Xpreprocessor -fopenmp -I${HOMEBREW_PREFIX}/opt/libomp/include")
|
|
set(OpenMP_CXX_FLAGS "-Xpreprocessor -fopenmp -I${HOMEBREW_PREFIX}/opt/libomp/include")
|
|
set(OpenMP_C_LIB_NAMES "omp")
|
|
set(OpenMP_CXX_LIB_NAMES "omp")
|
|
set(OpenMP_omp_LIBRARY "${HOMEBREW_PREFIX}/opt/libomp/lib/libomp.dylib")
|
|
|
|
# Force use of system libc++ to avoid version mismatch
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
|
|
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -stdlib=libc++")
|
|
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} -stdlib=libc++")
|
|
|
|
# Set minimum macOS version for better compatibility
|
|
set(CMAKE_OSX_DEPLOYMENT_TARGET "11.0" CACHE STRING "Minimum macOS version")
|
|
endif()
|
|
|
|
# Find ZMQ using pkg-config with IMPORTED_TARGET for automatic target creation
|
|
find_package(PkgConfig REQUIRED)
|
|
|
|
# On ARM64 macOS, ensure pkg-config finds ARM64 Homebrew packages first
|
|
if(APPLE AND CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
|
|
set(ENV{PKG_CONFIG_PATH} "/opt/homebrew/lib/pkgconfig:/opt/homebrew/share/pkgconfig:$ENV{PKG_CONFIG_PATH}")
|
|
endif()
|
|
|
|
pkg_check_modules(ZMQ REQUIRED IMPORTED_TARGET libzmq)
|
|
|
|
# This creates PkgConfig::ZMQ target automatically with correct properties
|
|
if(TARGET PkgConfig::ZMQ)
|
|
message(STATUS "Found and configured ZMQ target: PkgConfig::ZMQ")
|
|
else()
|
|
message(FATAL_ERROR "pkg_check_modules did not create IMPORTED target for ZMQ.")
|
|
endif()
|
|
|
|
# Add cppzmq headers
|
|
include_directories(SYSTEM third_party/cppzmq)
|
|
|
|
# Configure msgpack-c - disable boost dependency
|
|
set(MSGPACK_USE_BOOST OFF CACHE BOOL "" FORCE)
|
|
add_compile_definitions(MSGPACK_NO_BOOST)
|
|
include_directories(third_party/msgpack-c/include)
|
|
|
|
# Faiss configuration - streamlined build
|
|
set(FAISS_ENABLE_PYTHON ON CACHE BOOL "" FORCE)
|
|
set(FAISS_ENABLE_GPU OFF CACHE BOOL "" FORCE)
|
|
set(FAISS_ENABLE_EXTRAS OFF CACHE BOOL "" FORCE)
|
|
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 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)
|
|
set(BUILD_SHARED_LIBS OFF CACHE BOOL "" FORCE) # Static library is faster to build
|
|
|
|
# Avoid building demos and benchmarks
|
|
set(BUILD_DEMOS OFF CACHE BOOL "" FORCE)
|
|
set(BUILD_BENCHS OFF CACHE BOOL "" FORCE)
|
|
|
|
# NEW: Tell Faiss to only build the generic version
|
|
set(FAISS_BUILD_GENERIC ON CACHE BOOL "" FORCE)
|
|
set(FAISS_BUILD_AVX2 OFF CACHE BOOL "" FORCE)
|
|
set(FAISS_BUILD_AVX512 OFF CACHE BOOL "" FORCE)
|
|
|
|
# IMPORTANT: Disable building AVX versions to speed up compilation
|
|
set(FAISS_BUILD_AVX_VERSIONS OFF CACHE BOOL "" FORCE)
|
|
|
|
add_subdirectory(third_party/faiss)
|