Add docs build GH

.github/workflows/build.yaml

@@ -34,6 +34,17 @@ jobs:
       branch: ${{ inputs.branch }}
       date: ${{ inputs.date }}
       sha: ${{ inputs.sha }}
+  docs-build:
+    if: ${{ startsWith(github.ref, 'refs/heads/branch-') }}
+    needs: [python-build]
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/custom-job.yaml@cuda-118
+    with:
+      build_type: branch
+      node_type: "gpu-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci:latest"
+      run_script: "ci/build_docs.sh"
   python-build:
     needs: [cpp-build]
     secrets: inherit

.github/workflows/pr.yaml

@@ -19,6 +19,7 @@ jobs:
       - conda-python-tests-singlegpu
       - conda-python-tests-dask
       - conda-notebook-tests
+      - docs-build
       - wheel-build-cuml
       - wheel-tests-cuml
     secrets: inherit
@@ -68,6 +69,16 @@ jobs:
       arch: "amd64"
       container_image: "rapidsai/ci:latest"
       run_script: "ci/test_notebooks.sh"
+  docs-build:
+    needs: conda-python-build
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/custom-job.yaml@cuda-118
+    with:
+      build_type: pull-request
+      node_type: "gpu-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci:latest"
+      run_script: "ci/build_docs.sh"
   wheel-build-cuml:
     needs: checks
     secrets: inherit

ci/build_docs.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+set -euo pipefail
+
+rapids-logger "Create test conda environment"
+. /opt/conda/etc/profile.d/conda.sh
+
+rapids-dependency-file-generator \
+  --output conda \
+  --file_key docs \
+  --matrix "cuda=${RAPIDS_CUDA_VERSION%.*};arch=$(arch);py=${RAPIDS_PY_VERSION}" | tee env.yaml
+
+rapids-mamba-retry env create --force -f env.yaml -n docs
+conda activate docs
+
+rapids-print-env
+
+rapids-logger "Downloading artifacts from previous jobs"
+
+CPP_CHANNEL=$(rapids-download-conda-from-s3 cpp)
+PYTHON_CHANNEL=$(rapids-download-conda-from-s3 python)
+VERSION_NUMBER=$(rapids-get-rapids-version-from-git)
+
+rapids-mamba-retry install \
+  --channel "${CPP_CHANNEL}" \
+  --channel "${PYTHON_CHANNEL}" \
+  cuml libcuml
+
+# # Build CPP docs
+rapids-logger "Build cpp docs"
+pushd cpp
+doxygen Doxyfile.in
+popd
+
+# Build Python docs
+rapids-logger "Build Python docs"
+pushd docs
+sphinx-build -b dirhtml ./source _html -W
+sphinx-build -b text ./source _text -W
+popd
+
+if [[ "${RAPIDS_BUILD_TYPE}" == "branch" ]]; then
+  rapids-logger "Upload Docs to S3"
+  aws s3 sync --no-progress --delete cpp/html "s3://rapidsai-docs/libcuml/${VERSION_NUMBER}/html"
+  aws s3 sync --no-progress --delete docs/_html "s3://rapidsai-docs/cuml/${VERSION_NUMBER}/html"
+  aws s3 sync --no-progress --delete docs/_text "s3://rapidsai-docs/cuml/${VERSION_NUMBER}/txt"
+fi

ci/release/update-version.sh

@@ -41,6 +41,9 @@ sed_runner 's/'"branch-.*\/RAPIDS.cmake"'/'"branch-${NEXT_SHORT_TAG}\/RAPIDS.cma
 sed_runner 's/version = .*/version = '"'${NEXT_SHORT_TAG}'"'/g' docs/source/conf.py
 sed_runner 's/release = .*/release = '"'${NEXT_FULL_TAG}'"'/g' docs/source/conf.py
 
+# Update project_number (RAPIDS_VERSION) in the CPP doxygen file
+sed_runner 's/PROJECT_NUMBER         = .*/PROJECT_NUMBER         = '"'${NEXT_SHORT_TAG}'"'/g' Doxyfile.in
+
 for FILE in dependencies.yaml conda/environments/*.yaml; do
    sed_runner "s/cudf=${CURRENT_SHORT_TAG}/cudf=${NEXT_SHORT_TAG}/g" ${FILE};
    sed_runner "s/rmm=${CURRENT_SHORT_TAG}/rmm=${NEXT_SHORT_TAG}/g" ${FILE};

conda/environments/all_cuda-115_arch-x86_64.yaml

@@ -23,8 +23,11 @@ dependencies:
 - doxygen=1.8.20
 - faiss-proc=*=cuda
 - gcc_linux-64=9.*
+- graphviz
 - hdbscan
 - hypothesis>=6.0,<7
+- ipykernel
+- ipython
 - joblib>=0.11
 - libcublas-dev>=11.7.3.1,<=11.7.4.6
 - libcublas>=11.7.3.1,<=11.7.4.6
@@ -41,23 +44,28 @@ dependencies:
 - libraft-distance=23.02.*
 - libraft-headers=23.02.*
 - libraft-nn=23.02.*
+- nbsphinx
 - ninja
 - nltk
 - numpydoc
 - pip
+- pydata-sphinx-theme
 - pylibraft=23.02.*
 - pytest
 - pytest-cases
 - pytest-cov
 - pytest-xdist
 - python>=3.8,<3.10
 - raft-dask=23.02.*
+- recommonmark
 - rmm=23.02.*
 - scikit-build>=0.13.1
 - scikit-learn=0.24
 - seaborn
 - sparse
+- sphinx-copybutton
 - sphinx-markdown-tables
+- sphinx<6
 - statsmodels
 - sysroot_linux-64==2.17
 - treelite=3.1.0

cpp/Doxyfile.in

@@ -38,7 +38,7 @@ PROJECT_NAME           = "cuML C++ API"
 # could be handy for archiving the generated documentation or if some version
 # control system is used.
 
-PROJECT_NUMBER         = @CUML_VERSION@
+PROJECT_NUMBER         = '23.02'
 
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a
@@ -58,7 +58,7 @@ PROJECT_LOGO           =
 # entered, it will be relative to the location where doxygen was started. If
 # left blank the current directory will be used.
 
-OUTPUT_DIRECTORY       = @CMAKE_CURRENT_BINARY_DIR@
+OUTPUT_DIRECTORY       =
 
 # If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub-
 # directories (in 2 levels) under the output directory of each output format and
@@ -737,7 +737,7 @@ WARN_NO_PARAMDOC       = YES
 # a warning is encountered.
 # The default value is: NO.
 
-WARN_AS_ERROR          = YES
+WARN_AS_ERROR          = NO
 
 # The WARN_FORMAT tag determines the format of the warning messages that doxygen
 # can produce. The string should contain the $file, $line, and $text tags, which
@@ -765,9 +765,9 @@ WARN_LOGFILE           =
 # spaces. See also FILE_PATTERNS and EXTENSION_MAPPING
 # Note: If this tag is empty the current directory is searched.
 
-INPUT                  = @CMAKE_CURRENT_SOURCE_DIR@/include \
-                         @CMAKE_CURRENT_SOURCE_DIR@/src \
-                         @CMAKE_CURRENT_SOURCE_DIR@/src_prims
+INPUT                  = include \
+                         src \
+                         src_prims
 
 # This tag can be used to specify the character encoding of the source files
 # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
@@ -866,11 +866,7 @@ EXAMPLE_RECURSIVE      = NO
 # that contain images that are to be included in the documentation (see the
 # \image command).
 
-# IMAGE_PATH             = @CMAKE_CURRENT_SOURCE_DIR@/doxygen/images
-
-# temporarily using cmake_current_source_dir for image path since we don't have images,
-# comment the above whenever images are needed in the doxygen/images folder
-IMAGE_PATH             = @CMAKE_CURRENT_SOURCE_DIR@/
+IMAGE_PATH             =
 
 # The INPUT_FILTER tag can be used to specify a program that doxygen should
 # invoke to filter for each input file. Doxygen will invoke the filter program
@@ -1082,7 +1078,7 @@ HTML_FILE_EXTENSION    = .html
 # of the possible markers and block names see the documentation.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_HEADER            = @CMAKE_CURRENT_SOURCE_DIR@/header.html
+HTML_HEADER            = header.html
 
 # The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each
 # generated HTML page. If the tag is left blank doxygen will generate a standard
@@ -2126,7 +2122,7 @@ HIDE_UNDOC_RELATIONS   = YES
 # set to NO
 # The default value is: YES.
 
-HAVE_DOT               = @DOXYGEN_DOT_FOUND@
+HAVE_DOT               = YES
 
 # The DOT_NUM_THREADS specifies the number of dot invocations doxygen is allowed
 # to run in parallel. When set to 0 doxygen will base this on the number of
@@ -2306,7 +2302,7 @@ INTERACTIVE_SVG        = NO
 # found. If left blank, it is assumed the dot tool can be found in the path.
 # This tag requires that the tag HAVE_DOT is set to YES.
 
-DOT_PATH               = @DOXYGEN_DOT_EXECUTABLE@
+DOT_PATH               =
 
 # The DOTFILE_DIRS tag can be used to specify one or more directories that
 # contain dot files that are included in the documentation (see the \dotfile

dependencies.yaml

@@ -9,7 +9,7 @@ files:
       - common_build
       - cpp_run
       - cudatoolkit
-      - doc
+      - docs
       - py_build
       - py_run
       - py_version
@@ -28,6 +28,12 @@ files:
     includes:
       - checks
       - py_version
+  docs:
+    output: none
+    includes:
+      - cudatoolkit
+      - docs
+      - py_version
   test_cpp:
     output: none
     includes:
@@ -176,10 +182,20 @@ dependencies:
               - *libcusolver114
               - *libcusparse_dev114
               - *libcusparse114
-  doc:
+  docs:
     common:
       - output_types: [conda, requirements]
         packages:
+          - graphviz
+          - ipython
+          - ipykernel
+          - nbsphinx
+          - numpydoc
+          - pydata-sphinx-theme
+          - recommonmark
+          - scikit-learn=0.24
+          - sphinx<6
+          - sphinx-copybutton
           - sphinx-markdown-tables
       - output_types: conda
         packages:

docs/source/conf.py

@@ -24,7 +24,6 @@
 # is relative to the documentation root, use os.path.abspath to make it
 # absolute, like shown here.
 sys.path.insert(0, os.path.abspath('sphinxext'))
-sys.path.insert(0, os.path.abspath('../../python'))
 
 from github_link import make_linkcode_resolve # noqa
 
@@ -179,8 +178,8 @@
 
 # Example configuration for intersphinx: refer to the Python standard library.
 intersphinx_mapping = {
-    "python": ('https://docs.python.org/', None),
-    "scipy": ('https://docs.scipy.org/doc/scipy/reference', None)
+    "python": ("https://docs.python.org/3", None),
+    "scipy": ("https://docs.scipy.org/doc/scipy", None),
 }
 
 # Config numpydoc