Files
the-biergarten-app/tooling/pipeline/CMakeLists.txt
2026-05-03 04:07:25 -04:00

239 lines
7.9 KiB
CMake

# CMakeLists.txt (project root)
cmake_minimum_required(VERSION 3.31)
project(biergarten-pipeline)
# 1. Build Options
option(BIERGARTEN_MOCK_ONLY "Build with mock data generators only — skips llama.cpp" OFF)
if (BIERGARTEN_MOCK_ONLY)
message(STATUS "[biergarten] MOCK_ONLY build — llama.cpp will not be compiled.")
endif ()
# 2. Platform & GPU Detection
if (NOT UNIX)
message(FATAL_ERROR "[biergarten] Windows is not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
endif ()
if (APPLE)
if (CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
else ()
message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
endif ()
else ()
find_package(CUDAToolkit QUIET)
find_package(hip CONFIG QUIET)
if (CUDAToolkit_FOUND)
message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
set(CMAKE_CUDA_ARCHITECTURES native)
elseif (hip_FOUND OR DEFINED ENV{ROCM_PATH} OR EXISTS "/opt/rocm")
message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
else ()
message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
endif ()
endif ()
# 3. Project-wide Settings
set(CMAKE_CXX_STANDARD 20)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3 -march=native -flto")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og -g")
# 4. Dependencies
include(FetchContent)
# DEPRECATED: libcurl — to be removed once all usages are migrated to cpp-httplib.
# Tracked in: web_client/curl_web_client_get.cc, web_client/curl_web_client_url_encode.cc,
# web_client/curl_global_state.cc
find_package(CURL QUIET)
if (NOT CURL_FOUND)
message(FATAL_ERROR "[biergarten] libcurl not found. Install it (e.g. 'sudo dnf install libcurl-devel').")
endif ()
find_package(Boost REQUIRED COMPONENTS json program_options)
# SQLite amalgamation
FetchContent_Declare(
sqlite_amalgamation
URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
EXCLUDE_FROM_ALL
)
FetchContent_MakeAvailable(sqlite_amalgamation)
if (NOT TARGET sqlite3)
add_library(sqlite3 STATIC ${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c)
target_include_directories(sqlite3 PUBLIC ${sqlite_amalgamation_SOURCE_DIR})
target_compile_definitions(sqlite3 PUBLIC SQLITE_THREADSAFE=1)
endif ()
# llama.cpp — skipped for mock-only builds
if (NOT BIERGARTEN_MOCK_ONLY)
FetchContent_Declare(
llama-cpp
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
GIT_TAG b8742
)
FetchContent_MakeAvailable(llama-cpp)
endif ()
# Boost.DI (unofficial Boost extension, must declare separately from main Boost dependency)
FetchContent_Declare(
boost-di
GIT_REPOSITORY https://github.com/boost-ext/di.git
GIT_TAG v1.3.0
)
FetchContent_MakeAvailable(boost-di)
if (TARGET Boost.DI AND NOT TARGET boost::di)
add_library(boost::di ALIAS Boost.DI)
endif ()
# spdlog
FetchContent_Declare(
spdlog
GIT_REPOSITORY https://github.com/gabime/spdlog.git
GIT_TAG v1.15.3
)
FetchContent_MakeAvailable(spdlog)
# cpp-httplib — replaces direct libcurl usage in web_client.
# OpenSSL is required for HTTPS (Wikipedia). find_package is called first so
# CMake can locate libssl/libcrypto; cpp-httplib itself is header-only so the
# CPPHTTPLIB_OPENSSL_SUPPORT compile definition is propagated via the target.
find_package(OpenSSL REQUIRED)
FetchContent_Declare(
cpp-httplib
GIT_REPOSITORY https://github.com/yhirose/cpp-httplib.git
GIT_TAG v0.41.0
GIT_SHALLOW TRUE
SYSTEM
)
set(HTTPLIB_REQUIRE_OPENSSL ON CACHE BOOL "Require OpenSSL for cpp-httplib" FORCE)
FetchContent_MakeAvailable(cpp-httplib)
# 5. Executable & Sources
add_executable(${PROJECT_NAME})
# --- Entry point ---
target_sources(${PROJECT_NAME} PRIVATE
src/main.cc
)
# --- json_handling ---
target_sources(${PROJECT_NAME} PRIVATE
src/json_handling/json_loader.cc
)
# --- application_options ---
target_sources(${PROJECT_NAME} PRIVATE
src/application_options/parse_arguments.cc
)
# --- biergarten_data_generator ---
target_sources(${PROJECT_NAME} PRIVATE
src/biergarten_data_generator/log_results.cc
src/biergarten_data_generator/biergarten_data_generator.cc
src/biergarten_data_generator/generate_breweries.cc
src/biergarten_data_generator/run.cc
src/biergarten_data_generator/query_cities_with_countries.cc
)
# --- web_client ---
# DEPRECATED: curl_web_client_* — to be replaced with cpp-httplib equivalents.
target_sources(${PROJECT_NAME} PRIVATE
src/web_client/curl_web_client_url_encode.cc
src/web_client/curl_web_client_get.cc
src/web_client/curl_global_state.cc
)
target_sources(${PROJECT_NAME} PRIVATE
src/web_client/http_web_client.cc
)
# --- data_generation: prompt_formatting ---
target_sources(${PROJECT_NAME} PRIVATE
src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
)
# --- data_generation: mock ---
target_sources(${PROJECT_NAME} PRIVATE
src/data_generation/mock/generate_brewery.cc
src/data_generation/mock/generate_user.cc
src/data_generation/mock/deterministic_hash.cc
)
# --- data_generation: llama (skipped for mock-only builds) ---
if (NOT BIERGARTEN_MOCK_ONLY)
target_sources(${PROJECT_NAME} PRIVATE
src/data_generation/llama/load.cc
src/data_generation/llama/helpers.cc
src/data_generation/llama/generate_brewery.cc
src/data_generation/llama/infer.cc
src/data_generation/llama/llama_generator.cc
src/data_generation/llama/generate_user.cc
)
endif ()
# --- services: wikipedia ---
target_sources(${PROJECT_NAME} PRIVATE
src/services/wikipedia/wikipedia_service.cc
src/services/wikipedia/fetch_extract.cc
src/services/wikipedia/get_summary.cc
)
# --- services: sqlite ---
target_sources(${PROJECT_NAME} PRIVATE
src/services/sqlite/process_record.cc
src/services/sqlite/sqlite_export_service.cc
src/services/sqlite/finalize.cc
src/services/sqlite/initialize.cc
src/services/sqlite/helpers/sqlite_connection_helpers.cc
src/services/sqlite/helpers/sqlite_statement_helpers.cc
)
# --- services (top-level) ---
target_sources(${PROJECT_NAME} PRIVATE
src/services/prompt_directory.cc
)
# 6. Include Directories & Link Libraries
target_include_directories(${PROJECT_NAME} PRIVATE
includes
$<$<NOT:$<BOOL:${BIERGARTEN_MOCK_ONLY}>>:${llama-cpp_SOURCE_DIR}/include>
$<$<NOT:$<BOOL:${BIERGARTEN_MOCK_ONLY}>>:${llama-cpp_SOURCE_DIR}/common>
)
target_link_libraries(${PROJECT_NAME} PRIVATE
$<$<NOT:$<BOOL:${BIERGARTEN_MOCK_ONLY}>>:llama>
boost::di
Boost::json
Boost::program_options
spdlog::spdlog
sqlite3
httplib::httplib
OpenSSL::SSL
OpenSSL::Crypto
CURL::libcurl # DEPRECATED: remove once web_client is migrated to cpp-httplib
)
if (BIERGARTEN_MOCK_ONLY)
target_compile_definitions(${PROJECT_NAME} PRIVATE BIERGARTEN_MOCK_ONLY)
endif ()
# 7. Runtime Assets
configure_file(
${CMAKE_SOURCE_DIR}/locations.json
${CMAKE_BINARY_DIR}/locations.json
COPYONLY
)
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
COMMAND ${CMAKE_COMMAND} -E copy_directory
${CMAKE_SOURCE_DIR}/prompts
${CMAKE_BINARY_DIR}/prompts
)