Code upload

.clang-format-ignore

@@ -0,0 +1,7 @@
+# apart from all the .gitignores, what else files should be
+# ignored by the clang formatter
+.git/
+.github/
+third_party/*
+*/generated/*
+build/*

.github/actions/cmake-setup/action.yml

@@ -0,0 +1,69 @@
+name: "Setup CMake"
+description: "Download/cache specific CMake version"
+
+inputs:
+  cmake-version:
+    description: 'CMake version'
+    required: true
+  cmake-cache-path:
+    description: 'Path to cache CMake'
+    required: false
+    default: ~/.cache
+outputs:
+  cmake-path:
+    description: 'Path to the CMake executable'
+    value: ${{ steps.add-cmake-to-path.outputs.cmake-path }}
+
+runs:
+  using: "composite"
+  steps:
+    - name: Setup Variables
+      id: variables
+      run: |
+        CMAKE_VERSION="${{ inputs.cmake-version }}"
+        CMAKE_COMPRESSED="cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz"
+        CMAKE_URL="https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/${CMAKE_COMPRESSED}"
+        CMAKE_SHA256_URL="https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}-SHA-256.txt"
+        CMAKE_CACHE_PATH="${{ inputs.cmake-cache-path }}/cmake-${CMAKE_VERSION}"
+
+        echo "cmake-version=${CMAKE_VERSION}" >> "${GITHUB_OUTPUT}"
+        echo "cmake-compressed=${CMAKE_COMPRESSED}" >> "${GITHUB_OUTPUT}"
+        echo "cmake-url=${CMAKE_URL}" >> "${GITHUB_OUTPUT}"
+        echo "cmake-sha256-url=${CMAKE_SHA256_URL}" >> "${GITHUB_OUTPUT}"
+        echo "cmake-cache-path=${CMAKE_CACHE_PATH}" >> "${GITHUB_OUTPUT}"
+      shell: bash
+
+    - name: Cache CMake
+      id: cache-cmake
+      uses: actions/cache@v3
+      with:
+        path: ${{ steps.variables.outputs.cmake-cache-path }}
+        key: ${{ runner.os }}-cmake-${{ inputs.cmake-version }}
+
+    - name: Download & Extract CMake
+      if: steps.cache-cmake.outputs.cache-hit != 'true'
+      run: |
+        # Download CMake and its SHA256 file
+        curl -L "${{ steps.variables.outputs.cmake-url }}" -o "${{ steps.variables.outputs.cmake-compressed }}"
+        curl -L "${{ steps.variables.outputs.cmake-sha256-url }}" -o cmake.sha256
+
+        # Extract the expected SHA256 from the file
+        EXPECTED_SHA=$(
+          grep "${{ steps.variables.outputs.cmake-compressed }}" "cmake.sha256" |
+          awk '{ print $1 }'
+        )
+
+        # Verify the SHA256 checksum
+        echo "${EXPECTED_SHA} ${{ steps.variables.outputs.cmake-compressed }}" | sha256sum -c -
+
+        # Create the cache directory and extract CMake
+        mkdir -p ${{ steps.variables.outputs.cmake-cache-path }}
+        tar -xzf "${{ steps.variables.outputs.cmake-compressed }}" --strip-components=1 -C ${{ steps.variables.outputs.cmake-cache-path }}
+      shell: bash
+
+    - name: Add CMake to PATH & Export CMake Executable Path
+      id: add-cmake-to-path
+      run: |
+        echo "${{ steps.variables.outputs.cmake-cache-path }}/bin" >> "${GITHUB_PATH}"
+        echo "cmake-path=${{ steps.variables.outputs.cmake-cache-path }}/bin/cmake" >> "${GITHUB_OUTPUT}"
+      shell: bash

.github/workflows/black-format.yml

@@ -0,0 +1,80 @@
+name: Python Format Check
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+env:
+  cmake-version: "3.22.6"
+  python-version: "3.10"
+
+jobs:
+  build:
+    # The CMake configure and build commands are platform agnostic and should work equally well on Windows or Mac.
+    # You can convert this to a matrix build if you need cross-platform coverage.
+    # See: https://docs.github.com/en/free-pro-team@latest/actions/learn-github-actions/managing-complex-workflows#using-a-build-matrix
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    # === Get CMake ===
+    - name: Setup CMake
+      id: setup-cmake
+      uses: ./.github/actions/cmake-setup
+      with:
+        cmake-version: ${{ env.cmake-version }}
+
+    # === Get Python3 ===
+    - name: Set up Python3
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ env.python-version }}
+
+    # === CMake configuration ===
+    - name: Initialize Build System
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        ${{ env.cmake-exe }} -B ${{github.workspace}}/build -DFORMATTING_ONLY=ON
+        ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target help
+
+    # === Check for CMake format check target ===
+    - name: Check CMake Format Target
+      id: check-cmake-format-target
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        # skip download if target is found
+        if ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target help | grep -q "python-check-format"; then
+          echo "black-found=true" >> "${GITHUB_OUTPUT}"
+        else
+          echo "black-found=false" >> "${GITHUB_OUTPUT}"
+        fi
+
+    # === Get Python3 black formatter ===
+    - name: Get Python3 Black Formatter
+      if: steps.check-cmake-format-target.outputs.black-found != 'true'
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        # install_black_py3pkg_requirements target will only be available if the black package is not found
+        ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target install_black_py3pkg_requirements
+
+    # === Redo the CMake configuration ===
+    - name: Initialize Build System Again
+      if: steps.check-cmake-format-target.outputs.black-found != 'true'
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        ${{ env.cmake-exe }} -B ${{github.workspace}}/build -DFORMATTING_ONLY=ON
+        ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target help
+
+    # === Format check ===
+    - name: Python Format Check
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target python-check-format

.github/workflows/clang-format.yml

@@ -0,0 +1,68 @@
+name: C/C++ Format Check
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+env:
+  cmake-version: "3.22.6"
+  clang-format-version: "14"
+
+jobs:
+  build:
+    # The CMake configure and build commands are platform agnostic and should work equally well on Windows or Mac.
+    # You can convert this to a matrix build if you need cross-platform coverage.
+    # See: https://docs.github.com/en/free-pro-team@latest/actions/learn-github-actions/managing-complex-workflows#using-a-build-matrix
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    # === Get CMake ===
+    - name: Setup CMake
+      id: setup-cmake
+      uses: ./.github/actions/cmake-setup
+      with:
+        cmake-version: ${{ env.cmake-version }}
+
+    # === Get clang-format ===
+    - name: Cache clang-format
+      uses: actions/cache@v3
+      id: cache-clang-format
+      with:
+        path: ~/.cache/clang-format-${{ env.clang-format-version }}
+        key: ${{ runner.os }}-clang-format-${{ env.clang-format-version }}
+
+    - name: Download clang-format
+      if: steps.cache-clang-format.outputs.cache-hit != 'true'
+      env:
+        clang-format-url: https://github.com/muttleyxd/clang-tools-static-binaries/releases/download/master-2da3e7b/clang-format-${{ env.clang-format-version }}_linux-amd64
+        clang-format-cache-path: ~/.cache/clang-format-${{ env.clang-format-version }}
+        clang-format-sha256: 5daf48b8331afb85575e11dfd73ffc6bf47af10ccde260b40751df246f1bf1ff
+      run: |
+        curl -L ${{ env.clang-format-url }} -o clang-format
+        echo "${{ env.clang-format-sha256 }} clang-format" | sha256sum -c -
+        chmod +x clang-format
+        mkdir -p ${{ env.clang-format-cache-path }}
+        mv clang-format ${{ env.clang-format-cache-path }}/clang-format-${{ env.clang-format-version }}
+
+    - name: Add clang-format to PATH
+      run: echo ~/.cache/clang-format-${{ env.clang-format-version }} >> "$GITHUB_PATH"
+
+    # === CMake configuration and build ===
+    - name: CMake Setup
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        ${{ env.cmake-exe }} -B ${{github.workspace}}/build -DFORMATTING_ONLY=ON
+        ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target help
+
+    - name: Format Check
+      env:
+        cmake-exe: ${{ steps.setup-cmake.outputs.cmake-path }}
+      run: |
+        which clang-format
+        ${{ env.cmake-exe }} --build ${{github.workspace}}/build --target cpp-check-format
+

.gitignore

@@ -0,0 +1,22 @@
+# editor specific
+.vscode/
+
+# build directory
+build/
+
+# any database
+*.db
+
+# python
+.python_history
+.ptpython_history
+**/__pycache__/
+requirements.txt
+
+# build artifacts
+build/
+
+# dataset data
+*.csv
+*.arrow
+*.json

.gitmodules

@@ -0,0 +1,13 @@
+[submodule "third_party/pybind11"]
+	path = third_party/pybind11
+	url = https://github.com/pybind/pybind11.git
+[submodule "third_party/protobuf"]
+	path = third_party/protobuf
+	url = https://github.com/protocolbuffers/protobuf.git
+[submodule "third_party/date"]
+	path = third_party/date
+	url = https://github.com/HowardHinnant/date.git
+[submodule "third_party/pybind11_mkdoc"]
+	path = third_party/pybind11_mkdoc
+	url = https://github.com/0-EricZhou-0/pybind11_mkdoc.git
+	branch = arg_support

CMakeLists.txt

@@ -0,0 +1,96 @@
+cmake_minimum_required(VERSION 3.22)
+
+project(rag_sys LANGUAGES C CXX)
+
+# === CMake Options ===
+option(FORMATTING_ONLY
+    "Only generate format related targets" OFF)
+option(GENERATE_GLOBAL_PY3_DEPENDENCY
+    "Generate global Python3 package requirements, only asserted when excluding env-specific packages" OFF)
+option(GENERATE_ESSENTIAL_PY3_DEPENDENCY
+    "Generate essential Python3 package requirements (i.e., excluding formatting, QoL, etc.)" OFF)
+
+# === CMake policy ===
+# make CMAKE_INTERPROCEDURAL_OPTIMIZATION applies globally
+set(CMAKE_POLICY_DEFAULT_CMP0069 NEW)
+
+# === C/C++ standard ===
+set(CMAKE_C_STANDARD 17)
+set(CMAKE_CXX_STANDARD 20)
+
+# === Cmake configurations ===
+set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+set(CMAKE_VERBOSE_MAKEFILE OFF)
+# build type & optimization
+set(CMAKE_BUILD_TYPE Release)
+if(CMAKE_BUILD_TYPE STREQUAL "Release")
+    set(CMAKE_INTERPROCEDURAL_OPTIMIZATION TRUE)
+endif()
+
+# === Custom configurations ===
+# Print all target building information formulated using cmake/build_helper.cmake:function(cxx_setup_target)
+set(EXPORT_TARGET_CONFIG OFF)
+
+# === Prioritize executables and libraries in conda environment ===
+# if(DEFINED ENV{CONDA_PREFIX})
+#     execute_process(
+#         COMMAND [=[echo $SHELL; echo "${CONDA_PREFIX:-'$(dirname $(which conda))/../'}"]=]
+#         OUTPUT_VARIABLE CONDA_CMAKE_PREFIX_PATH
+#         COMMAND_ECHO STDOUT
+#         ECHO_OUTPUT_VARIABLE
+#     )
+#     list(APPEND CMAKE_PREFIX_PATH "${CONDA_CMAKE_PREFIX_PATH}")
+# endif()
+
+# === Custom repository-wide variables ===
+set(PYTHON_SRC_DIR ${CMAKE_SOURCE_DIR}/src)
+set(RESOURCE_DIR ${CMAKE_SOURCE_DIR}/resource)
+
+# === Create necessary directories ===
+file(MAKE_DIRECTORY ${RESOURCE_DIR}/generated)
+
+# === Include custom module subdirectories ===
+set(CMAKE_MODULE_PATH
+    ${CMAKE_SOURCE_DIR}/cmake/module
+    ${CMAKE_MODULE_PATH})
+
+# === Include utilities ===
+# cmake utilities
+include(cmake/utils.cmake)
+
+# python utilities
+set(PY3_PKG_EXISTENCE_DIR ${CMAKE_BINARY_DIR}/py3_pkg_info)
+set(PY3_PKGDEP_CHK_SCRIPT ${RESOURCE_DIR}/build_helper/py3_require_package.py)
+set(PY3_EXEMOD_CHK_SCRIPT ${RESOURCE_DIR}/build_helper/py3_require_executable_module.py)
+include(cmake/python_env.cmake)
+
+# === Code Formatting configuration ===
+set(CLANG_FORMAT_DIR ${RESOURCE_DIR}/clang_format)
+set(BLACK_FORMAT_DIR ${RESOURCE_DIR}/black_format)
+include(cmake/clang_format.cmake)
+include(cmake/black_format.cmake)
+if(FORMATTING_ONLY)
+    message(STATUS "Only running clang-format, skipping other configurations.")
+    return()
+endif()
+
+# === Include other predefined cmake files ===
+# c++ build helper
+include(cmake/build_helper.cmake)
+
+# misc
+set(LIBCLANG_FIND_VERSION_SCRIPT ${RESOURCE_DIR}/build_helper/libclang_get_lib_version.py)
+include(cmake/misc.cmake)
+
+# third-party library import
+set(THIRD_PARTY_DIR ${CMAKE_SOURCE_DIR}/third_party)
+include(cmake/third_party.cmake)
+
+# === Custom project-wide variables ===
+
+# === Include subdirectories ===
+add_subdirectory(monitoring_sys)
+add_subdirectory(example)
+
+# === Status report ===
+message(STATUS "Build type: ${CMAKE_BUILD_TYPE}")