Files
the-biergarten-app/tooling/pipeline/CMakeLists.txt
Aaron Po 6a66619c70 Add multithreaded logging infrastructure for preparation for future designs (#225)
* Update class diagrams

* Implement BoundedChannel and multithreaded logging infra

* Integrate logging channel system

* Update string concatenations to use std::format

* Add pretty print log
2026-05-22 22:00:38 -04:00

269 lines
9.2 KiB
CMake

cmake_minimum_required(VERSION 3.31)
project(biergarten-pipeline)
# Set policy to allow FetchContent_Populate for header-only libraries
# that have outdated CMakeLists.txt files
cmake_policy(SET CMP0169 OLD)
# 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)
# Boost (system install — via dnf/brew)
find_package(Boost REQUIRED COMPONENTS json program_options)
# Boost.DI (unofficial Boost extension, must declare separately from main Boost dependency)
# Header-only library, so we only fetch without invoking its CMakeLists.txt
FetchContent_Declare(
boost-di
GIT_REPOSITORY https://github.com/boost-ext/di.git
GIT_TAG v1.3.0
GIT_SHALLOW TRUE
)
FetchContent_GetProperties(boost-di)
if(NOT boost-di_POPULATED)
FetchContent_Populate(boost-di)
endif()
add_library(boost_di INTERFACE)
add_library(boost::di ALIAS boost_di)
target_include_directories(boost_di INTERFACE
$<BUILD_INTERFACE:${boost-di_SOURCE_DIR}/include>
)
# 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 ${sqlite_amalgamation_SOURCE_DIR})
target_compile_definitions(sqlite3 PUBLIC SQLITE_THREADSAFE=1)
endif()
# llama.cpp — skipped for mock-only builds
if(NOT BIERGARTEN_MOCK_ONLY)
find_library(LLAMA_LIB NAMES llama)
find_library(GGML_LIB NAMES ggml)
find_library(GGML_BASE_LIB NAMES ggml-base)
find_path(LLAMA_INC_DIR NAMES llama.h PATH_SUFFIXES include)
if(LLAMA_LIB AND GGML_LIB AND GGML_BASE_LIB AND LLAMA_INC_DIR)
message(STATUS "[biergarten] Found system llama.cpp — skipping FetchContent")
add_library(llama SHARED IMPORTED)
set_target_properties(llama PROPERTIES
IMPORTED_LOCATION "${LLAMA_LIB}"
INTERFACE_INCLUDE_DIRECTORIES "${LLAMA_INC_DIR}"
INTERFACE_LINK_LIBRARIES "${GGML_LIB};${GGML_BASE_LIB}"
)
else()
message(STATUS "[biergarten] System llama.cpp not found — fetching via FetchContent")
FetchContent_Declare(
llama-cpp
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
GIT_TAG b9012
)
FetchContent_MakeAvailable(llama-cpp)
endif()
endif()
# spdlog
FetchContent_Declare(
spdlog
GIT_REPOSITORY https://github.com/gabime/spdlog.git
GIT_TAG v1.15.3
)
FetchContent_MakeAvailable(spdlog)
# cpp-httplib — header-only HTTP/HTTPS client replacing libcurl.
# OpenSSL is required for HTTPS (Wikipedia API). find_package locates
# libssl/libcrypto; HTTPLIB_REQUIRE_OPENSSL causes a hard build failure
# if OpenSSL is absent rather than silently producing an HTTP-only binary.
find_package(OpenSSL REQUIRED)
FetchContent_Declare(
cpp-httplib
GIT_REPOSITORY https://github.com/yhirose/cpp-httplib.git
GIT_TAG v0.43.2
GIT_SHALLOW TRUE
SYSTEM
)
set(HTTPLIB_REQUIRE_OPENSSL ON CACHE BOOL "Require OpenSSL for cpp-httplib" FORCE)
FetchContent_MakeAvailable(cpp-httplib)
# 5. Executable & Sources
add_executable(${PROJECT_NAME}
includes/services/enrichment/mock_enrichment.h
includes/json_handling/pretty_print.h)
# --- 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(${PROJECT_NAME} PRIVATE
src/application_options/parse_arguments.cc
)
# --- biergarten_pipeline_orchestrator ---
target_sources(${PROJECT_NAME} PRIVATE
src/biergarten_pipeline_orchestrator/log_results.cc
src/biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
src/biergarten_pipeline_orchestrator/generate_breweries.cc
src/biergarten_pipeline_orchestrator/run.cc
src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc
)
# --- web_client ---
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(${PROJECT_NAME} PRIVATE
src/services/enrichment/wikipedia/wikipedia_service.cc
src/services/enrichment/wikipedia/fetch_extract.cc
src/services/enrichment/wikipedia/get_summary.cc
)
# --- services: sqlite ---
target_sources(${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: logging ---
target_sources(${PROJECT_NAME} PRIVATE
"src/services/logging/log_producer.cc"
src/services/logging/log_dispatcher.cc
)
# --- services (top-level) ---
target_sources(${PROJECT_NAME} PRIVATE
src/services/prompt_directory.cc
)
# 6. Include Directories, Link Libraries & Compile Definitions
target_include_directories(${PROJECT_NAME} PRIVATE
includes
)
target_link_libraries(${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
)
target_compile_definitions(${PROJECT_NAME} PRIVATE
# Defined when -DBIERGARTEN_MOCK_ONLY=ON — skips llama.cpp entirely.
# Use #ifdef BIERGARTEN_MOCK_ONLY in source to guard llama-specific code.
$<$<BOOL:${BIERGARTEN_MOCK_ONLY}>:BIERGARTEN_MOCK_ONLY>
# Defined for Debug configuration builds.
# Use #ifdef DEBUG in source to enable debug-only behaviour (e.g. verbose logging).
$<$<CONFIG:Debug>:DEBUG>
)
target_compile_options(biergarten-pipeline PRIVATE
-fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
)
# 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
)