reorganize sqlite3 user guide example

cookbook/docs/conf.py

@@ -238,9 +238,8 @@ def __call__(self, filename):
     "../deployment/cluster",
     # "../deployment/guides",  # TODO: add content to this section
     # "../control_plane",  # TODO: add content to this section
-    # "../integrations/flytekit_plugins/sqllite3",  # TODO: add content to this section
+    "../integrations/flytekit_plugins/sql",
     "../integrations/flytekit_plugins/papermilltasks",
-    # "../integrations/flytekit_plugins/sqlalchemy",  # TODO: add content to this section
     "../integrations/flytekit_plugins/pandera",
     "../integrations/flytekit_plugins/dolt",
     "../integrations/kubernetes/pod",
@@ -267,9 +266,8 @@ def __call__(self, filename):
     "auto/deployment/cluster",
     # "auto/deployment/guides",  # TODO: add content to this section
     # "auto/control_plane",  # TODO: add content to this section
-    # "auto/integrations/flytekit_plugins/sqllite3",  # TODO: add content to this section
+    "auto/integrations/flytekit_plugins/sql",
     "auto/integrations/flytekit_plugins/papermilltasks",
-    # "auto/integrations/flytekit_plugins/sqlalchemy",  # TODO: add content to this section
     "auto/integrations/flytekit_plugins/pandera",
     "auto/integrations/flytekit_plugins/dolt",
     "auto/integrations/kubernetes/pod",

cookbook/docs/flytekit_plugins.rst

@@ -18,6 +18,15 @@ You can find the plugins maintained by the core flyte team `here <https://github
 .. panels::
    :header: text-center
 
+   .. link-button:: auto/integrations/flytekit_plugins/sql/index
+      :type: ref
+      :text: SQL
+      :classes: btn-block stretched-link
+   ^^^^^^^^^^^^
+   Execute SQL queries as tasks.
+
+   ---
+
    .. link-button:: auto/integrations/flytekit_plugins/papermilltasks/index
       :type: ref
       :text: Papermill
@@ -34,16 +43,22 @@ You can find the plugins maintained by the core flyte team `here <https://github
    ^^^^^^^^^^^^
    Validate pandas dataframes with ``pandera``.
 
+   ---
+
+   .. link-button:: auto/integrations/flytekit_plugins/dolt/index
+      :type: ref
+      :text: Dolt
+      :classes: btn-block stretched-link
+   ^^^^^^^^^^^^
+   Version your SQL database with ``dolt``.
 
-.. TODO: add the following items to the TOC when the content is written.
-.. - auto/integrations/flytekit_plugins/sqllite3/index
-.. - auto/integrations/flytekit_plugins/sqlalchemy/index
 
 .. toctree::
    :maxdepth: -1
    :caption: Contents
    :hidden:
 
+   auto/integrations/flytekit_plugins/sql/index
    auto/integrations/flytekit_plugins/papermilltasks/index
    auto/integrations/flytekit_plugins/pandera/index
    auto/integrations/flytekit_plugins/dolt/index

cookbook/integrations/flytekit_plugins/sql/Dockerfile

@@ -0,0 +1,31 @@
+FROM python:3.8-buster
+
+WORKDIR /root
+ENV VENV /opt/venv
+ENV LANG C.UTF-8
+ENV LC_ALL C.UTF-8
+ENV PYTHONPATH /root
+
+# Install the AWS cli separately to prevent issues with boto being written over
+RUN pip3 install awscli
+
+ENV VENV /opt/venv
+# Virtual environment
+RUN python3 -m venv ${VENV}
+ENV PATH="${VENV}/bin:$PATH"
+
+# Install Python dependencies
+COPY sql/requirements.txt /root/.
+RUN pip install -r /root/requirements.txt
+
+# Copy the makefile targets to expose on the container. This makes it easier to register.
+COPY in_container.mk /root/Makefile
+COPY sql/sandbox.config /root
+
+# Copy the actual code
+COPY sql/ /root/sql/
+
+# This tag is supplied by the build script and will be used to determine the version
+# when registering tasks, workflows, and launch plans
+ARG tag
+ENV FLYTE_INTERNAL_IMAGE $tag

cookbook/integrations/flytekit_plugins/sql/Makefile

@@ -0,0 +1,3 @@
+PREFIX=sql
+include ../../../common/Makefile
+include ../../../common/leaf.mk

cookbook/integrations/flytekit_plugins/sql/README.rst

@@ -0,0 +1,7 @@
+###
+SQL
+###
+
+Flyte tasks are not always restricted to running user-supplied containers, nor even containers at all. Indeed, this is
+one of the most important design decisions in Flyte. Non-container tasks can have arbitrary targets for execution -- 
+an API that executes SQL queries like SnowFlake, BigQuery, a synchronous WebAPI, etc.

cookbook/integrations/flytekit_plugins/sql/requirements.in

@@ -0,0 +1,2 @@
+-r ../../../common/requirements-common.in
+flytekitplugins-sqlalchemy>=0.20.1

cookbook/integrations/flytekit_plugins/sql/requirements.txt

@@ -0,0 +1,146 @@
+#
+# This file is autogenerated by pip-compile with python 3.8
+# To update, run:
+#
+#    /Library/Developer/CommandLineTools/usr/bin/make requirements.txt
+#
+attrs==21.2.0
+    # via scantree
+certifi==2021.5.30
+    # via requests
+charset-normalizer==2.0.2
+    # via requests
+click==7.1.2
+    # via flytekit
+croniter==1.0.15
+    # via flytekit
+cycler==0.10.0
+    # via matplotlib
+dataclasses-json==0.5.4
+    # via flytekit
+decorator==5.0.9
+    # via retry
+deprecated==1.2.12
+    # via flytekit
+dirhash==0.2.1
+    # via flytekit
+docker-image-py==0.1.10
+    # via flytekit
+flyteidl==0.19.13
+    # via flytekit
+flytekit==0.20.1
+    # via
+    #   -r ../../../common/requirements-common.in
+    #   flytekitplugins-sqlalchemy
+flytekitplugins-sqlalchemy==0.20.1
+    # via -r requirements.in
+greenlet==1.1.0
+    # via sqlalchemy
+grpcio==1.38.1
+    # via flytekit
+idna==3.2
+    # via requests
+importlib-metadata==4.6.1
+    # via keyring
+keyring==23.0.1
+    # via flytekit
+kiwisolver==1.3.1
+    # via matplotlib
+marshmallow==3.12.2
+    # via
+    #   dataclasses-json
+    #   marshmallow-enum
+    #   marshmallow-jsonschema
+marshmallow-enum==1.5.1
+    # via dataclasses-json
+marshmallow-jsonschema==0.12.0
+    # via flytekit
+matplotlib==3.4.2
+    # via -r ../../../common/requirements-common.in
+mypy-extensions==0.4.3
+    # via typing-inspect
+natsort==7.1.1
+    # via flytekit
+numpy==1.21.0
+    # via
+    #   matplotlib
+    #   pandas
+    #   pyarrow
+pandas==1.3.0
+    # via flytekit
+pathspec==0.8.1
+    # via scantree
+pillow==8.3.1
+    # via matplotlib
+protobuf==3.17.3
+    # via
+    #   flyteidl
+    #   flytekit
+py==1.10.0
+    # via retry
+pyarrow==3.0.0
+    # via flytekit
+pyparsing==2.4.7
+    # via matplotlib
+python-dateutil==2.8.1
+    # via
+    #   croniter
+    #   flytekit
+    #   matplotlib
+    #   pandas
+python-json-logger==2.0.1
+    # via flytekit
+pytimeparse==1.1.8
+    # via flytekit
+pytz==2018.4
+    # via
+    #   flytekit
+    #   pandas
+regex==2021.7.6
+    # via docker-image-py
+requests==2.26.0
+    # via
+    #   flytekit
+    #   responses
+responses==0.13.3
+    # via flytekit
+retry==0.9.2
+    # via flytekit
+scantree==0.0.1
+    # via dirhash
+six==1.16.0
+    # via
+    #   cycler
+    #   flytekit
+    #   grpcio
+    #   protobuf
+    #   python-dateutil
+    #   responses
+    #   scantree
+sortedcontainers==2.4.0
+    # via flytekit
+sqlalchemy==1.4.21
+    # via flytekitplugins-sqlalchemy
+statsd==3.3.0
+    # via flytekit
+stringcase==1.2.0
+    # via dataclasses-json
+typing-extensions==3.10.0.0
+    # via typing-inspect
+typing-inspect==0.7.1
+    # via dataclasses-json
+urllib3==1.26.6
+    # via
+    #   flytekit
+    #   requests
+    #   responses
+wheel==0.36.2
+    # via
+    #   -r ../../../common/requirements-common.in
+    #   flytekit
+wrapt==1.12.1
+    # via
+    #   deprecated
+    #   flytekit
+zipp==3.5.0
+    # via importlib-metadata

cookbook/integrations/flytekit_plugins/sql/sandbox.config

@@ -0,0 +1,3 @@
+[sdk]
+workflow_packages=sql
+python_venv=flytekit_venv

cookbook/integrations/flytekit_plugins/sql/sql-alchemy-remote.py

@@ -0,0 +1,45 @@
+"""
+SQLAlchemy
+----------
+
+SQLAlchemy is the Python SQL toolkit and Object Relational Mapper that gives application developers the full power and flexibility of SQL.
+
+That being said, Flyte provides an easy-to-use interface to utilize SQLAlchemy to connect to various SQL Databases.
+
+The SQLAlchemy task will run with a pre-built container, and thus users needn't build one.
+"""
+
+# %%
+# Let's import the libraries.
+import pandas
+from flytekit import kwtypes, task, workflow
+from flytekitplugins.sqlalchemy import SQLAlchemyConfig, SQLAlchemyTask
+
+
+# %%
+# We define an SQLAlchemyTask to fetch limited records from a table. Finally, we return the length of the returned DataFrame.
+#
+# .. note::
+#
+#   The output of SQLAlchemyTask is a :py:class:`~flytekit.types.schema.FlyteSchema` by default.
+@task
+def get_length(df: pandas.DataFrame) -> int:
+    return len(df)
+
+
+sql_task = SQLAlchemyTask(
+    name="sqlalchemy_task",
+    query_template="select * from <table> limit {{.inputs.limit}}",
+    inputs=kwtypes(limit=int),
+    task_config=SQLAlchemyConfig(uri="<uri>"),
+)
+
+
+@workflow
+def my_wf(limit: int) -> int:
+    return get_length(df=sql_task(limit=limit))
+
+
+if __name__ == "__main__":
+    print(f"Running {__file__} main...")
+    print(my_wf(limit=3))