Pushing changes to GitHub Pages.

main/_sources/README.md

@@ -0,0 +1,143 @@
+# [Merlin Systems](https://github.com/NVIDIA-Merlin/systems)
+
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/merlin-systems)
+[![PyPI version shields.io](https://img.shields.io/pypi/v/merlin-systems.svg)](https://pypi.python.org/pypi/merlin-systems/)
+![GitHub License](https://img.shields.io/github/license/NVIDIA-Merlin/systems)
+[![Documentation](https://img.shields.io/badge/documentation-blue.svg)](https://nvidia-merlin.github.io/systems/stable/README.html)
+
+Merlin Systems provides tools for combining recommendation models with other elements of production recommender systems like feature stores, nearest neighbor search, and exploration strategies into end-to-end recommendation pipelines that can be served with [Triton Inference Server](https://github.com/triton-inference-server/server).
+
+## Quickstart
+
+Merlin Systems uses the Merlin Operator DAG API, the same API used in [NVTabular](https://github.com/NVIDIA-Merlin/NVTabular) for feature engineering, to create serving ensembles. To combine a feature engineering workflow and a Tensorflow model into an inference pipeline:
+
+```python
+import tensorflow as tf
+
+from merlin.systems.dag import Ensemble
+from merlin.systems.dag.ops import PredictTensorflow, TransformWorkflow
+from nvtabular.workflow import Workflow
+
+# Load saved NVTabular workflow and TensorFlow model
+workflow = Workflow.load(nvtabular_workflow_path)
+model = tf.keras.models.load_model(tf_model_path)
+
+# Remove target/label columns from feature processing workflowk
+workflow = workflow.remove_inputs([<target_columns>])
+
+# Define ensemble pipeline
+pipeline = (
+	workflow.input_schema.column_names >>
+	TransformWorkflow(workflow) >>
+	PredictTensorflow(model)
+)
+
+# Export artifacts to disk
+ensemble = Ensemble(pipeline, workflow.input_schema)
+ensemble.export(export_path)
+```
+
+After you export your ensemble, you reference the directory to run an instance of Triton Inference Server to host your ensemble.
+
+```shell
+tritonserver --model-repository=/export_path/
+```
+
+Refer to the [Merlin Example Notebooks](https://github.com/NVIDIA-Merlin/Merlin/tree/main/examples/ranking) for exploring notebooks that demonstrate
+how to train and evaluate a ranking model with Merlin Models and then how to serve it as an ensemble on [Triton Inference Server](https://github.com/triton-inference-server/server).
+
+For training models with XGBoost and Implicit, and then serving with Systems, you can visit these [examples](https://github.com/NVIDIA-Merlin/Merlin/tree/main/examples/traditional-ml).
+
+## Building a Four-Stage Recommender Pipeline
+
+Merlin Systems can also build more complex serving pipelines that integrate multiple models and external tools (like feature stores and nearest neighbor search):
+
+```python
+# Load artifacts for the pipeline
+retrieval_model = tf.keras.models.load_model(retrieval_model_path)
+ranking_model = tf.keras.models.load_model(ranking_model_path)
+feature_store = feast.FeatureStore(feast_repo_path)
+
+# Define the fields expected in requests
+request_schema = Schema([
+    ColumnSchema("user_id", dtype=np.int32),
+])
+
+# Fetch user features, use them to a compute user vector with retrieval model,
+# and find candidate items closest to the user vector with nearest neighbor search
+user_features = request_schema.column_names >> QueryFeast.from_feature_view(
+    store=feature_store, view="user_features", column="user_id"
+)
+
+retrieval = (
+    user_features
+    >> PredictTensorflow(retrieval_model_path)
+    >> QueryFaiss(faiss_index_path, topk=100)
+)
+
+# Filter out candidate items that have already interacted with
+# in the current session and fetch item features for the rest
+filtering = retrieval["candidate_ids"] >> FilterCandidates(
+    filter_out=user_features["movie_ids"]
+)
+
+item_features = filtering >> QueryFeast.from_feature_view(
+    store=feature_store, view="movie_features", column="filtered_ids",
+)
+
+# Join user and item features for the candidates and use them to predict relevance scores
+combined_features = item_features >> UnrollFeatures(
+    "movie_id", user_features, unrolled_prefix="user"
+)
+
+ranking = combined_features >> PredictTensorflow(ranking_model_path)
+
+# Sort candidate items by relevance score with some randomized exploration
+ordering = combined_features["movie_id"] >> SoftmaxSampling(
+    relevance_col=ranking["output"], topk=10, temperature=20.0
+)
+
+# Create and export the ensemble
+ensemble = Ensemble(ordering, request_schema)
+ensemble.export("./ensemble")
+```
+
+Refer to the [Example Notebooks](https://github.com/NVIDIA-Merlin/Merlin/tree/main/examples/Building-and-deploying-multi-stage-RecSys) for exploring
+`building-and-deploying-multi-stage-RecSys` notebooks with Merlin Models and Systems.
+
+## Installation
+
+Merlin Systems requires Triton Inference Server and Tensorflow. The simplest setup is to use the [Merlin Tensorflow Inference Docker container](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/merlin/containers/merlin-tensorflow-inference), which has both pre-installed.
+
+### Installing Merlin Systems Using Pip
+
+You can install Merlin Systems with `pip`:
+
+```shell
+pip install merlin-systems
+```
+
+### Installing Merlin Systems from Source
+
+Merlin Systems can be installed from source by cloning the GitHub repository and running `setup.py`
+
+```shell
+git clone https://github.com/NVIDIA-Merlin/systems.git
+cd systems && python setup.py develop
+```
+
+### Running Merlin Systems from Docker
+
+Merlin Systems is installed on multiple Docker containers that are available from the NVIDIA GPU Cloud (NGC) catalog.
+The following table lists the containers that include Triton Inference Server for use with Merlin.
+
+| Container Name      | Container Location                                                                     | Functionality                                                                      |
+| ------------------- | -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
+| `merlin-hugectr`    | <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/merlin/containers/merlin-hugectr>    | Merlin frameworks, HugeCTR, and Triton Inference Server                            |
+| `merlin-tensorflow` | <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/merlin/containers/merlin-tensorflow> | Merlin frameworks selected for only Tensorflow support and Triton Inference Server |
+
+If you want to add support for GPU-accelerated workflows, you will first need to install the [NVIDIA Container Toolkit](https://github.com/NVIDIA/nvidia-docker) to provide GPU support for Docker. You can use the NGC links referenced in the table above to obtain more information about how to launch and run these containers.
+
+## Feedback and Support
+
+To report bugs or get help, please [open an issue](https://github.com/NVIDIA-Merlin/Systems/issues/new/choose).

main/_sources/api.rst

@@ -0,0 +1,47 @@
+*****************
+API Documentation
+*****************
+
+.. currentmodule:: merlin.systems
+
+
+Ensemble Graph Constructors
+---------------------------
+
+.. currentmodule:: merlin.systems.dag
+
+.. autosummary::
+   :toctree: generated
+
+   Ensemble
+
+Ensemble Operator Constructors
+------------------------------
+
+.. currentmodule:: merlin.systems.dag.ops
+
+.. autosummary::
+   :toctree: generated
+
+   workflow.TransformWorkflow
+   tensorflow.PredictTensorflow
+   fil.PredictForest
+   implicit.PredictImplicit
+   softmax_sampling.SoftmaxSampling
+   session_filter.FilterCandidates
+   unroll_features.UnrollFeatures
+
+.. faiss.QueryFaiss
+.. feast.QueryFeast
+
+
+Conversion Functions for Triton Inference Server
+------------------------------------------------
+
+.. currentmodule:: merlin.systems.triton
+
+.. autosummary::
+   :toctree: generated
+
+   convert_df_to_triton_input
+   convert_triton_output_to_df

main/_sources/generated/merlin.systems.dag.Ensemble.rst

@@ -0,0 +1,33 @@
+merlin.systems.dag.Ensemble
+===========================
+
+.. currentmodule:: merlin.systems.dag
+
+.. autoclass:: Ensemble
+
+
+   .. automethod:: __init__
+
+
+   .. rubric:: Methods
+
+   .. autosummary::
+
+      ~Ensemble.__init__
+      ~Ensemble.export
+      ~Ensemble.load
+      ~Ensemble.save
+      ~Ensemble.transform
+
+
+
+
+
+   .. rubric:: Attributes
+
+   .. autosummary::
+
+      ~Ensemble.input_schema
+      ~Ensemble.output_schema
+
+

main/_sources/generated/merlin.systems.dag.ops.fil.PredictForest.rst

@@ -0,0 +1,49 @@
+merlin.systems.dag.ops.fil.PredictForest
+========================================
+
+.. currentmodule:: merlin.systems.dag.ops.fil
+
+.. autoclass:: PredictForest
+
+
+   .. automethod:: __init__
+
+
+   .. rubric:: Methods
+
+   .. autosummary::
+
+      ~PredictForest.__init__
+      ~PredictForest.column_mapping
+      ~PredictForest.compute_column_schema
+      ~PredictForest.compute_input_schema
+      ~PredictForest.compute_output_schema
+      ~PredictForest.compute_selector
+      ~PredictForest.create_node
+      ~PredictForest.export
+      ~PredictForest.load_artifacts
+      ~PredictForest.output_column_names
+      ~PredictForest.save_artifacts
+      ~PredictForest.transform
+      ~PredictForest.validate_schemas
+
+
+
+
+
+   .. rubric:: Attributes
+
+   .. autosummary::
+
+      ~PredictForest.dependencies
+      ~PredictForest.dynamic_dtypes
+      ~PredictForest.export_name
+      ~PredictForest.is_subgraph
+      ~PredictForest.label
+      ~PredictForest.output_dtype
+      ~PredictForest.output_properties
+      ~PredictForest.output_tags
+      ~PredictForest.supported_formats
+      ~PredictForest.supports
+
+

main/_sources/generated/merlin.systems.dag.ops.implicit.PredictImplicit.rst

@@ -0,0 +1,49 @@
+merlin.systems.dag.ops.implicit.PredictImplicit
+===============================================
+
+.. currentmodule:: merlin.systems.dag.ops.implicit
+
+.. autoclass:: PredictImplicit
+
+
+   .. automethod:: __init__
+
+
+   .. rubric:: Methods
+
+   .. autosummary::
+
+      ~PredictImplicit.__init__
+      ~PredictImplicit.column_mapping
+      ~PredictImplicit.compute_column_schema
+      ~PredictImplicit.compute_input_schema
+      ~PredictImplicit.compute_output_schema
+      ~PredictImplicit.compute_selector
+      ~PredictImplicit.create_node
+      ~PredictImplicit.export
+      ~PredictImplicit.load_artifacts
+      ~PredictImplicit.output_column_names
+      ~PredictImplicit.save_artifacts
+      ~PredictImplicit.transform
+      ~PredictImplicit.validate_schemas
+
+
+
+
+
+   .. rubric:: Attributes
+
+   .. autosummary::
+
+      ~PredictImplicit.dependencies
+      ~PredictImplicit.dynamic_dtypes
+      ~PredictImplicit.export_name
+      ~PredictImplicit.is_subgraph
+      ~PredictImplicit.label
+      ~PredictImplicit.output_dtype
+      ~PredictImplicit.output_properties
+      ~PredictImplicit.output_tags
+      ~PredictImplicit.supported_formats
+      ~PredictImplicit.supports
+
+

main/_sources/generated/merlin.systems.dag.ops.session_filter.FilterCandidates.rst

@@ -0,0 +1,49 @@
+merlin.systems.dag.ops.session\_filter.FilterCandidates
+=======================================================
+
+.. currentmodule:: merlin.systems.dag.ops.session_filter
+
+.. autoclass:: FilterCandidates
+
+
+   .. automethod:: __init__
+
+
+   .. rubric:: Methods
+
+   .. autosummary::
+
+      ~FilterCandidates.__init__
+      ~FilterCandidates.column_mapping
+      ~FilterCandidates.compute_column_schema
+      ~FilterCandidates.compute_input_schema
+      ~FilterCandidates.compute_output_schema
+      ~FilterCandidates.compute_selector
+      ~FilterCandidates.create_node
+      ~FilterCandidates.export
+      ~FilterCandidates.load_artifacts
+      ~FilterCandidates.output_column_names
+      ~FilterCandidates.save_artifacts
+      ~FilterCandidates.transform
+      ~FilterCandidates.validate_schemas
+
+
+
+
+
+   .. rubric:: Attributes
+
+   .. autosummary::
+
+      ~FilterCandidates.dependencies
+      ~FilterCandidates.dynamic_dtypes
+      ~FilterCandidates.export_name
+      ~FilterCandidates.is_subgraph
+      ~FilterCandidates.label
+      ~FilterCandidates.output_dtype
+      ~FilterCandidates.output_properties
+      ~FilterCandidates.output_tags
+      ~FilterCandidates.supported_formats
+      ~FilterCandidates.supports
+
+