Change serving docs from "mlflow pyfunc serve" to "mlflow models serv…

…e" (mlflow#1321)

* Remove pyfunc server from docs

* Doc tweak

* whitespace

* Hyperlink fixes

README.rst

@@ -98,7 +98,7 @@ MLflow artifacts and then load them again for serving. There is an example train
     Score: 0.666
     Model saved in run <run-id>
 
-    $ mlflow pyfunc serve -r <run-id> -m model
+    $ mlflow models serve --model-uri runs:/<run-id>/model
 
     $ curl -d '{"columns":[0],"index":[0,1],"data":[[1],[-1]]}' -H 'Content-Type: application/json'  localhost:5000/invocations
 

docs/source/models.rst

@@ -455,7 +455,7 @@ Not all deployment methods are available for all model flavors.
   :local:
   :depth: 1
 
-.. _model_deployment:
+.. _local_model_deployment:
 
 Deploy MLflow models locally
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -643,9 +643,8 @@ MLflow provides a default Docker image definition; however, it is up to you to b
 MLflow includes the utility function ``build_and_push_container`` to perform this step. Once built and uploaded, you can use the MLflow container for all MLflow Models. Model webservers deployed using the :py:mod:`mlflow.sagemaker`
 module accept the following data formats as input, depending on the deployment flavor:
 
-* ``python_function``: For this deployment flavor, the endpoint accepts the same formats
-  as the pyfunc server. These formats are described in the
-  :ref:`pyfunc deployment documentation <pyfunc_deployment>`.
+* ``python_function``: For this deployment flavor, the endpoint accepts the same formats described
+  in the :ref:`local model deployment documentation <local_model_deployment>`.
 
 * ``mleap``: For this deployment flavor, the endpoint accepts `only`
   JSON-serialized pandas DataFrames in the ``split`` orientation. For example,

docs/source/quickstart.rst

@@ -162,19 +162,19 @@ simple REST server for python-based models:
 
 .. code-block:: bash
 
-    mlflow pyfunc serve -r <RUN_ID> -m model
+    mlflow models serve -m runs:/<RUN_ID>/model
 
 .. note::
 
     By default the server runs on port 5000. If that port is already in use, use the `--port` option to
-    specify a different port. For example: ``mlflow pyfunc serve --port 1234 -r <RUN_ID> -m model``
+    specify a different port. For example: ``mlflow models serve -m runs:/<RUN_ID>/model --port 1234``
 
 Once you have started the server, you can pass it some sample data and see the
 predictions.
 
 The following example uses ``curl`` to send a JSON-serialized pandas DataFrame with the ``split``
-orientation to the pyfunc server. For more information about the input data formats accepted by
-the pyfunc model server, see the :ref:`MLflow deployment tools documentation <pyfunc_deployment>`.
+orientation to the model server. For more information about the input data formats accepted by
+the pyfunc model server, see the :ref:`MLflow deployment tools documentation <local_model_deployment>`.
 
 .. code-block:: bash
 
@@ -184,15 +184,4 @@ which returns::
 
     {"predictions": [1, 0]}
 
-.. note::
-
-    The ``sklearn_logistic_regression/train.py`` script must be run with the same Python version as
-    the version of Python that runs ``mlflow pyfunc serve``. If they are not the same version,
-    the stacktrace below may appear::
-
-        File "/usr/local/lib/python3.6/site-packages/mlflow/sklearn.py", line 54, in _load_model_from_local_file
-        return pickle.load(f)
-        UnicodeDecodeError: 'ascii' codec can't decode byte 0xc6 in position 0: ordinal not in range(128)
-
-
 For more information, see :doc:`models`.

docs/source/tutorial.rst

@@ -291,7 +291,7 @@ in MLflow saved the model as an artifact within the run.
 
       .. code-block:: bash
 
-          mlflow pyfunc serve -m /Users/mlflow/mlflow-prototype/mlruns/0/7c1a0d5c42844dcdb8f5191146925174/artifacts/model -p 1234
+          mlflow models serve -m /Users/mlflow/mlflow-prototype/mlruns/0/7c1a0d5c42844dcdb8f5191146925174/artifacts/model -p 1234
 
       .. note::
 
@@ -302,9 +302,9 @@ in MLflow saved the model as an artifact within the run.
 
       Once you have deployed the server, you can pass it some sample data and see the
       predictions. The following example uses ``curl`` to send a JSON-serialized pandas DataFrame
-      with the ``split`` orientation to the pyfunc server. For more information about the input data
-      formats accepted by the pyfunc model server, see the
-      :ref:`MLflow deployment tools documentation <pyfunc_deployment>`.
+      with the ``split`` orientation to the model server. For more information about the input data
+      formats accepted by the model server, see the
+      :ref:`MLflow deployment tools documentation <local_model_deployment>`.
 
       .. code-block:: bash
 

examples/flower_classifier/README.rst

@@ -85,12 +85,12 @@ run_id ``101``.
 
 - To test REST api scoring do the following two steps:
 
-  1. Deploy the model as a local REST endpoint by running mlflow pyfunc serve:
+  1. Deploy the model as a local REST endpoint by running ``mlflow models serve``:
 
   .. code-block:: bash
 
       # deploy the model to local REST api endpoint
-      mlflow pyfunc serve -p 54321 -r 101 -m model
+      mlflow models serve --model-uri runs:/101/model --port 54321
 
 
   2. Apply the model to new data using the provided score_images_rest.py script: