Merge branch 'branch-23.01' into 564-doc-helm-chart-reference-names

docs/source/developer_guide/guides/2_real_world_phishing.md

@@ -154,7 +154,7 @@ docker run --rm -ti --gpus=all -p8000:8000 -p8001:8001 -p8002:8002 \
     --strict-readiness=false \
     --disable-auto-complete-config \
     --model-control-mode=explicit \
-    --load-model phishing-bert-onnx
+    --load-model=phishing-bert-onnx
 ```
 
 Once we have Triton running, we can verify that it is healthy using [curl](https://curl.se/). The `/v2/health/live` endpoint should return a 200 status code:

examples/abp_nvsmi_detection/README.md

@@ -27,7 +27,7 @@ In this example, we will be using Morpheus' provided ABP NVSMI Detection model.
 
 ### The Dataset
 
-The dataset that this workflow was designed to process contains NVIDIA GPU metrics at regular time intervals and is extracted by a NetQ agent and serialized into JSON. Each line in the dataset contains much of the same information that is returned by the `nvidia-smi` utility. We won't examine at a full message directly since each line contains 176 different columns, but it's possible to get a idea of how the dataset was generated using the `nvidia-smi dmon` command. If you run this yourself, the output similar to the following:
+The dataset that this workflow was designed to process contains NVIDIA GPU metrics at regular time intervals and is extracted by a NetQ agent and serialized into JSON. Each line in the dataset contains much of the same information that is returned by the `nvidia-smi` utility. We won't examine at a full message directly since each line contains 176 different columns, but it's possible to get an idea of how the dataset was generated using the `nvidia-smi dmon` command. If you run this yourself, the output similar to the following:
 
 ```bash
 $ nvidia-smi dmon
@@ -85,7 +85,7 @@ Once Triton has loaded the model, the following will be displayed:
 +-------------------+---------+--------+
 ```
 
-If this is not present in the output, check the Triton log for any error messages related to loading the model.
+> **Note**: If this is not present in the output, check the Triton log for any error messages related to loading the model.
 
 ## Running the Pipeline
 

examples/gnn_fraud_detection_pipeline/README.md

@@ -1,5 +1,5 @@
 <!--
-SPDX-FileCopyrightText: Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+SPDX-FileCopyrightText: Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 SPDX-License-Identifier: Apache-2.0
 
 Licensed under the Apache License, Version 2.0 (the "License");
@@ -18,14 +18,19 @@ limitations under the License.
 
 ## Requirements
 
-Prior to running the gnn fraud detection pipeline, additional requirements must be installed in to your Conda environment. A supplemental requirements file has been provided in this example directory.
+Prior to running the GNN fraud detection pipeline, additional requirements must be installed in to your Conda environment. A supplemental requirements file has been provided in this example directory.
 
 ```bash
 mamba env update -n ${CONDA_DEFAULT_ENV} -f examples/gnn_fraud_detection_pipeline/requirements.yml
 ```
 
 ## Running
 
+##### Setup Env Variable
+```bash
+export MORPHEUS_ROOT=$(pwd)
+```
+
 Use Morpheus to run the GNN fraud detection Pipeline with the transaction data. A pipeline has been configured in `run.py` with several command line options:
 
 ```bash
@@ -53,7 +58,7 @@ Options:
   --help                          Show this message and exit.
 ```
 
-To launch the configured Morpheus pipeline with the sample data that is provided at `<MORPHEUS_ROOT>/models/dataset`, run the following:
+To launch the configured Morpheus pipeline with the sample data that is provided at `$MORPHEUS_ROOT/models/dataset`, run the following:
 
 ```bash
 

examples/log_parsing/README.md

@@ -25,15 +25,20 @@ Pull Docker image from NGC (https://ngc.nvidia.com/catalog/containers/nvidia:tri
 
 Example:
 
-```
+```bash
 docker pull nvcr.io/nvidia/tritonserver:22.08-py3
 ```
 
-##### Start Triton Inference Server container
+##### Setup Env Variable
+```bash
+export MORPHEUS_ROOT=$(pwd)
 ```
-cd ${MORPHEUS_ROOT}/models
 
-docker run --gpus=1 --rm -p8000:8000 -p8001:8001 -p8002:8002 -v $PWD:/models nvcr.io/nvidia/tritonserver:22.08-py3 tritonserver --model-repository=/models/triton-model-repo --model-control-mode=explicit --load-model log-parsing-onnx
+##### Start Triton Inference Server Container
+From the Morpheus repo root directory, run the following to launch Triton and load the `log-parsing-onnx` model:
+
+```bash
+docker run --rm -ti --gpus=all -p8000:8000 -p8001:8001 -p8002:8002 -v $PWD/models:/models nvcr.io/nvidia/tritonserver:22.08-py3 tritonserver --model-repository=/models/triton-model-repo --exit-on-error=false --model-control-mode=explicit --load-model log-parsing-onnx
 ```
 
 ##### Verify Model Deployment
@@ -47,6 +52,8 @@ Once Triton server finishes starting up, it will display the status of all loade
 +------------------+---------+--------+
 ```
 
+> **Note**: If this is not present in the output, check the Triton log for any error messages related to loading the model.
+
 ### Run Log Parsing Pipeline
 
 Run the following from the `examples/log_parsing` directory to start the log parsing pipeline:
@@ -67,7 +74,7 @@ python run.py \
 Use `--help` to display information about the command line options:
 
 ```bash
-python ./examples/log_parsing/run.py --help
+python run.py --help
 
 Options:
   --num_threads INTEGER RANGE     Number of internal pipeline threads to use
@@ -95,7 +102,7 @@ Options:
 ```
 
 ### CLI Example
-The above example is illustrative of using the Python API to build a custom Morpheus Pipeline. Alternately the Morpheus command line could have been used to accomplish the same goal. To do this we must ensure that the `examples`/log_parsing directory is available in the `PYTHONPATH` and each of the custom stages are registered as plugins.
+The above example is illustrative of using the Python API to build a custom Morpheus Pipeline. Alternately the Morpheus command line could have been used to accomplish the same goal. To do this we must ensure that the `examples/log_parsing` directory is available in the `PYTHONPATH` and each of the custom stages are registered as plugins.
 
 From the root of the Morpheus repo run:
 ```bash

examples/nlp_si_detection/README.md

@@ -21,7 +21,7 @@ This example illustrates how to use Morpheus to automatically detect Sensitive I
 
 ## Background
 
-The goal of this example is to identify potentially sensitive information in network packet data as quickly as possible to limit exposure and take corrective action. Sensitive information is a broad term but can be generalized to any data that should be guarded from unautorized access. Credit card numbers, passwords, authorization keys, and emails are all examples of sensitive information.
+The goal of this example is to identify potentially sensitive information in network packet data as quickly as possible to limit exposure and take corrective action. Sensitive information is a broad term but can be generalized to any data that should be guarded from unauthorized access. Credit card numbers, passwords, authorization keys, and emails are all examples of sensitive information.
 
 In this example, we will be using Morpheus' provided NLP SI Detection model. This model is capable of detecting 10 different categories of sensitive information:
 
@@ -93,7 +93,7 @@ Once Triton has loaded the model, the following should be displayed:
 | sid-minibert-onnx | 1       | READY  |
 +-------------------+---------+--------+
 ```
-
+> **Note**: If this is not present in the output, check the Triton log for any error messages related to loading the model.
 
 ## Running the Pipeline
 
@@ -203,7 +203,7 @@ The output file `detections.jsonlines` will contain the original PCAP messages w
 * secret_keys
 * user
 
-The value for these fields will either be a `1` indicating a decection and a `0` indicating no detection. An example row with a detection is:
+The value for these fields will either be a `1` indicating a detection and a `0` indicating no detection. An example row with a detection is:
 ```json
 {
   "timestamp": 1616381019580,

examples/ransomware_detection/README.md

@@ -26,14 +26,18 @@ Pull Docker image from NGC (https://ngc.nvidia.com/catalog/containers/nvidia:tri
 
 Example:
 
-```
+```bash
 docker pull nvcr.io/nvidia/tritonserver:22.08-py3
 ```
-
-##### Start Triton Inference Server container
+##### Setup Env Variable
 ```bash
-cd ${MORPHEUS_ROOT}/examples/ransomware_detection
+export MORPHEUS_ROOT=$(pwd)
+```
 
+##### Start Triton Inference Server Container
+Run the following from the `examples/ransomware_detection` directory to launch Triton and load the `ransomw-model-short-rf` model:
+
+```bash
 # Run Triton in explicit mode
 docker run --rm -ti --gpus=all -p8000:8000 -p8001:8001 -p8002:8002 -v $PWD/models:/models/triton-model-repo nvcr.io/nvidia/tritonserver:22.08-py3 \
    tritonserver --model-repository=/models/triton-model-repo \
@@ -42,21 +46,30 @@ docker run --rm -ti --gpus=all -p8000:8000 -p8001:8001 -p8002:8002 -v $PWD/model
                 --load-model ransomw-model-short-rf
 ```
 
+##### Verify Model Deployment
+Once Triton server finishes starting up, it will display the status of all loaded models. Successful deployment of the model will show the following:
+
+```
++----------------------------+---------+--------+
+| Model                      | Version | Status |
++----------------------------+---------+--------+
+| ransomw-model-short-rf     | 1       | READY  |
++----------------------------+---------+--------+
+```
+
+> **Note**: If this is not present in the output, check the Triton log for any error messages related to loading the model.
+
 ## Requirements
-**Note**: Make sure `dask` and `distributed` are installed in your Conda environment before running the ransomware detection pipeline. Run the installation command specified below if not.
+> **Note**: Make sure `dask` and `distributed` are installed in your Conda environment before running the ransomware detection pipeline. Run the installation command specified below if not.
 
 ```bash
 conda install dask==2022.7.0 distributed==2022.7.0
 ```
 
-## Run Pipeline
-Launch the example using the following
-
-Input features for a short model can be taken from every three snapshots sequence, such as (1, 2, 3), or (2, 3, 4). The sliding window represents the number of subsequent snapshots that need to be taken into consideration when generating the input for a model. Sliding window for the medium model is `5` and for the long model it is `10`.
+## Run Ransomware Detection Pipeline
+Run the following from the `examples/ransomware_detection` directory to start the ransomware detection pipeline:
 
 ```bash
-cd ${MORPHEUS_ROOT}/examples/ransomware_detection
-
 python run.py --server_url=localhost:8001 \
               --sliding_window=3 \
               --model_name=ransomw-model-short-rf \
@@ -65,6 +78,8 @@ python run.py --server_url=localhost:8001 \
               --output_file=./ransomware_detection_output.jsonlines
 ```
 
+Input features for a short model can be taken from every three snapshots sequence, such as (1, 2, 3), or (2, 3, 4). The sliding window represents the number of subsequent snapshots that need to be taken into consideration when generating the input for a model. Sliding window for the medium model is `5` and for the long model it is `10`.
+
 The configuration options for this example can be queried with:
 
 ```bash

examples/root_cause_analysis/README.md

@@ -23,7 +23,7 @@ These examples illustrate how to use Morpheus to build a binary sequence classif
 
 Like any other Linux based machine, DGX's generate a vast amount of logs. Analysts spend hours trying to identify the root causes of each failure. There could be infinitely many types of root causes of the failures. Some patterns might help to narrow it down; however, regular expressions can only help to identify previously known patterns. Moreover, this creates another manual task of maintaining a search script.
 
-In this example, we show how we can use Morpheus to accelerate the analysis of the enormous amount of logs using machine learning. Another benefit of analyzing in a probabilistic way is that we can pin down previously undetected root causes. To achieve this, we will fine-tune a pre-trained BERT[^1] model with a classification layer using HuggingFace library.
+In this example, we demonstrate how using Morpheus can accelerate the analysis of the enormous amount of logs using machine learning. Another benefit of analyzing in a probabilistic way is that we can pin down previously undetected root causes. To achieve this, we will fine-tune a pre-trained BERT[^1] model with a classification layer using HuggingFace library.
 
 Once the model is capable of identifying even the new root causes, it can also be deployed as a process running in the machines to predict failures before they happen.
 
@@ -63,10 +63,11 @@ Once Triton has loaded the model, the following should be displayed:
 +------------------------+---------+--------+
 
 ```
+> **Note**: If this is not present in the output, check the Triton log for any error messages related to loading the model.
 
 #### ONNX->TensorRT Model Conversion
 
-To achieve optimized inference performance, Triton Inference Server provides option to convert our ONNX model to TensorRT. Simply add the following to the end of your `config.pbtxt`:
+To achieve optimized inference performance, Triton Inference Server provides an option to convert our ONNX model to TensorRT. Simply add the following to the end of your `config.pbtxt`:
 ```
 dynamic_batching {
   preferred_batch_size: [ 1, 4, 8, 16, 32 ]