Add initial documentation (#224)

.gitignore

@@ -42,3 +42,6 @@ _bundle
 # Conda-packed environment
 old-sklearn.tar.gz
 mlruns
+
+# Sphinx documentation
+docs/_build/

.readthedocs.yaml

@@ -0,0 +1,20 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally build your docs in additional formats such as PDF
+formats:
+  - pdf
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: 3.7
+  install:
+    - requirements: docs/requirements.txt

Makefile

@@ -62,7 +62,7 @@ lint: generate
 		mypy $$_runtime; \
 	done
 	mypy ./benchmarking
-	mypy ./examples
+	mypy ./docs/examples
 	# Check if something has changed after generation
 	git \
 		--no-pager diff \

README.md

@@ -1,8 +1,6 @@
 # MLServer
 
-An open source inference server to serve your machine learning models.
-
-> :warning: **This is a Work in Progress**.
+An open source inference server for your machine learning models.
 
 ## Overview
 
@@ -32,55 +30,54 @@ pip install mlserver-sklearn
 ```
 
 For further information on how to use MLServer, you can check any of the
-[available examples](#Examples).
+[available examples](#examples).
 
 ## Inference Runtimes
 
 Inference runtimes allow you to define how your model should be used within
 MLServer.
+You can think of them as the **backend glue** between MLServer and your machine
+learning framework of choice.
+You can read more about [inference runtimes in their documentation
+page](./docs/runtimes/index.md).
+
 Out of the box, MLServer comes with a set of pre-packaged runtimes which let
-you interact with a subset of common ML frameworks.
+you interact with a subset of common frameworks.
 This allows you to start serving models saved in these frameworks straight
 away.
 
-To avoid bringing in dependencies for frameworks that you don't need to use,
-these runtimes are implemented as independent optional packages.
-This mechanism also allows you to rollout your [own custom runtimes]( very easily.
-
-To pick which runtime you want to use for your model, you just need to make
-sure that the right package is installed, and then point to the correct runtime
-class in your `model-settings.json` file.
-
-The included runtimes are:
+Out of the box, MLServer provides support for:
 
-| Framework    | Package Name        | Implementation Class              | Example                                              | Source Code                                                      |
-| ------------ | ------------------- | --------------------------------- | ---------------------------------------------------- | ---------------------------------------------------------------- |
-| Scikit-Learn | `mlserver-sklearn`  | `mlserver_sklearn.SKLearnModel`   | [Scikit-Learn example](./examples/sklearn/README.md) | [`./runtimes/sklearn`](./runtimes/sklearn)                       |
-| XGBoost      | `mlserver-xgboost`  | `mlserver_xgboost.XGBoostModel`   | [XGBoost example](./examples/xgboost/README.md)      | [`./runtimes/xgboost`](./runtimes/xgboost)                       |
-| Spark MLlib  | `mlserver-mllib`    | `mlserver_mllib.MLlibModel`       | Coming Soon                                          | [`./runtimes/mllib`](./runtimes/mllib)                           |
-| LightGBM     | `mlserver-lightgbm` | `mlserver_lightgbm.LightGBMModel` | [LightGBM example](./examples/lightgbm/README.md)                                          | [`./runtimes/lightgbm`](./runtimes/lightgbm)                     |
-| Tempo        | `tempo`             | `tempo.mlserver.InferenceRuntime` | [Tempo example](./examples/tempo/README.md)          | [`github.com/SeldonIO/tempo`](https://github.com/SeldonIO/tempo) |
-| MLflow       | `mlserver-mlflow`   | `mlserver_mlflow.MLflowRuntime`   | [MLflow example](./examples/mlflow/README.md)        | [`./runtimes/mlflow`](./runtimes/mlflow)                         |
+| Framework    | Supported | Documentation                                                    |
+| ------------ | --------- | ---------------------------------------------------------------- |
+| Scikit-Learn | :+1:      | [MLServer SKLearn](./runtimes/sklearn)                           |
+| XGBoost      | :+1:      | [MLServer XGBoost](./runtimes/xgboost)                           |
+| Spark MLlib  | :+1:      | [MLServer MLlib](./runtimes/mllib)                               |
+| LightGBM     | :+1:      | [MLServer LightGBM](./runtimes/lightgbm)                         |
+| Tempo        | :+1:      | [`github.com/SeldonIO/tempo`](https://github.com/SeldonIO/tempo) |
+| MLflow       | :+1:      | [MLServer MLflow](./runtimes/mlflow)                             |
 
 ## Examples
 
-On the list below, you can find a few examples on how you can leverage
-`mlserver` to start serving your machine learning models.
+To see MLServer in action, check out [our full list of
+examples](./docs/examples/index.md).
+You can find below a few selected examples showcasing how you can leverage
+MLServer to start serving your machine learning models.
 
-- [Serving a `scikit-learn` model](./examples/sklearn/README.md)
-- [Serving a `xgboost` model](./examples/xgboost/README.md)
-- [Serving a `lightgbm` model](./examples/lightgbm/README.md)
-- [Serving a `tempo` pipeline](./examples/tempo/README.md)
-- [Serving a custom model](./examples/custom/README.md)
-- [Multi-Model Serving with multiple frameworks](./examples/mms/README.md)
-- [Loading / unloading models from a model repository](./examples/model-repository/README.md)
+- [Serving a `scikit-learn` model](./docs/examples/sklearn/README.md)
+- [Serving a `xgboost` model](./docs/examples/xgboost/README.md)
+- [Serving a `lightgbm` model](./docs/examples/lightgbm/README.md)
+- [Serving a `tempo` pipeline](./docs/examples/tempo/README.md)
+- [Serving a custom model](./docs/examples/custom/README.md)
+- [Multi-Model Serving with multiple frameworks](./docs/examples/mms/README.md)
+- [Loading / unloading models from a model repository](./docs/examples/model-repository/README.md)
 
 ## Developer Guide
 
 ### Versioning
 
 Both the main `mlserver` package and the [inference runtimes
-packages](./runtimes) try to follow the same versioning schema.
+packages](./docs/runtimes/index.md) try to follow the same versioning schema.
 To bump the version across all of them, you can use the
 [`./hack/update-version.sh`](./hack/update-version.sh) script.
 For example:

docs/Makefile

@@ -0,0 +1,23 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile install-dev
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+install-dev:
+	pip install -r ./requirements.txt

docs/_static/css/custom.css

@@ -0,0 +1,20 @@
+
+/* Hide first elem of nav bar */
+.md-tabs__list > li:first-child {
+    display: none;
+}
+
+dt {
+    display: table;
+    margin: 6px 0;
+    margin-top: 6px;
+    font-size: 90%;
+    line-height: normal;
+    background: #e7f2fa;
+    color: #2980B9;
+    border-top: solid 3px #6ab0de;
+    padding: 6px;
+    position: relative;
+}
+
+

docs/conf.py

@@ -0,0 +1,180 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+
+# -- Project information -----------------------------------------------------
+import sphinx_material
+
+project = "MLServer"
+copyright = "2021, Seldon Technologies"
+html_title = "MLServer"
+author = "Seldon Technologies"
+
+# The full version, including alpha/beta/rc tags
+release = "0.4.0.dev1"
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    #  "sphinx.ext.autodoc",
+    # Creates .nojekyll config
+    #  "sphinx.ext.githubpages",
+    # Converts markdown to rst
+    "myst_parser",
+    #  "sphinx.ext.napoleon",
+    # automatically generate API docs
+    # see https://github.com/rtfd/readthedocs.org/issues/1139
+    #  "sphinxcontrib.apidoc",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+
+# apidoc settings
+apidoc_module_dir = "../mlserver"
+apidoc_output_dir = "api"
+apidoc_excluded_paths = ["**/*test*"]
+apidoc_module_first = True
+apidoc_separate_modules = True
+apidoc_extra_args = ["-d 6"]
+
+# mock imports
+autodoc_mock_imports = [
+    "pandas",
+    "sklearn",
+    "skimage",
+    "requests",
+    "cv2",
+    "bs4",
+    "keras",
+    "seaborn",
+    "PIL",
+    "tensorflow",
+    "spacy",
+    "numpy",
+    "tensorflow_probability",
+    "scipy",
+    "matplotlib",
+    "creme",
+    "cloudpickle",
+    "fbprophet",
+    "dask",
+    "transformers",
+]
+
+
+# Napoleon settings
+napoleon_google_docstring = True
+napoleon_numpy_docstring = True
+napoleon_include_init_with_doc = True
+napoleon_include_private_with_doc = False
+napoleon_include_special_with_doc = True
+napoleon_use_admonition_for_examples = False
+napoleon_use_admonition_for_notes = False
+napoleon_use_admonition_for_references = False
+napoleon_use_ivar = False
+napoleon_use_param = True
+napoleon_use_rtype = False
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+# Chosen Themes:
+# * https://github.com/bashtage/sphinx-material/
+# * https://github.com/myyasuda/sphinx_materialdesign_theme
+html_theme = "sphinx_material"
+
+if html_theme == "sphinx_material":
+    html_theme_options = {
+        "google_analytics_account": "",
+        "base_url": "https://mlserver.readthedocs.io",
+        "color_primary": "teal",
+        "color_accent": "light-blue",
+        "repo_url": "https://github.com/SeldonIO/MLServer/",
+        "repo_name": "MLServer",
+        "globaltoc_depth": 2,
+        "globaltoc_collapse": False,
+        "globaltoc_includehidden": True,
+        "repo_type": "github",
+        "nav_links": [
+            {
+                "href": "https://docs.seldon.io",
+                "internal": False,
+                "title": "🚀 Our Other Projects & Products:",
+            },
+            {
+                "href": "https://docs.seldon.io/projects/seldon-core/en/latest/",
+                "internal": False,
+                "title": "Seldon Core",
+            },
+            {
+                "href": "https://docs.seldon.io/projects/alibi/en/stable/",
+                "internal": False,
+                "title": "Alibi Explain",
+            },
+            {
+                "href": "https://docs.seldon.io/projects/alibi-detect/en/stable/",
+                "internal": False,
+                "title": "Alibi Detect",
+            },
+            {
+                "href": "https://tempo.readthedocs.io/en/latest/",
+                "internal": False,
+                "title": "Tempo SDK",
+            },
+            {
+                "href": "https://deploy.seldon.io/",
+                "internal": False,
+                "title": "Seldon Deploy (Enterprise)",
+            },
+            {
+                "href": (
+                    "https://github.com/SeldonIO/seldon-deploy-sdk#seldon-deploy-sdk"
+                ),
+                "internal": False,
+                "title": "Seldon Deploy SDK (Enterprise)",
+            },
+        ],
+    }
+
+    extensions.append("sphinx_material")
+    html_theme_path = sphinx_material.html_theme_path()
+    html_context = sphinx_material.get_html_context()
+
+html_sidebars = {
+    "**": ["logo-text.html", "globaltoc.html", "localtoc.html", "searchbox.html"]
+}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+html_css_files = [
+    "css/custom.css",
+]

examples/conda/README.ipynb → docs/examples/conda/README.ipynb

@@ -4,10 +4,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Custom environments in MLServer\n",
+    "# Custom Conda environments in MLServer\n",
     "\n",
     "It's not unusual that model runtimes require extra dependencies that are not direct dependencies of MLServer.\n",
-    "This is the case when we want to use [custom runtimes](../custom), but also when our model artifacts are the output of older versions of a toolkit (e.g. models trained with an older version of SKLearn).\n",
+    "This is the case when we want to use [custom runtimes](../custom/README), but also when our model artifacts are the output of older versions of a toolkit (e.g. models trained with an older version of SKLearn).\n",
     "\n",
     "In these cases, since these dependencies (or dependency versions) are not known in advance by MLServer, they **won't be included in the default `seldonio/mlserver` Docker image**.\n",
     "To cover these cases, the **`seldonio/mlserver` Docker image allows you to load custom environments** before starting the server itself.\n",
@@ -76,7 +76,7 @@
     "We can now train and save a Scikit-Learn model using the older version of our environment.\n",
     "This model will be serialised as `model.joblib`.\n",
     "\n",
-    "You can find more details of this process in the [Scikit-Learn example](../sklearn)."
+    "You can find more details of this process in the [Scikit-Learn example](../sklearn/README)."
    ]
   },
   {
@@ -257,7 +257,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.0"
+   "version": "3.7.8"
   }
  },
  "nbformat": 4,