NVIDIA

Question Answering Notebook

Resource

NVIDIA

Question Answering Notebook

End to End workflow for question answering starting with training in TAO Toolkit and deployment using Riva.

Back to File Browser

question-answering-deployment.ipynb

Deploying a Question Answering Model in Riva

Train Adapt Optimize (TAO) Toolkit provides the capability to export your model in a format that can deployed using NVIDIA Riva, a highly performant application framework for multi-modal conversational AI services using GPUs.

This tutorial explores taking a .riva model, the result of tao question_answering export command, and leveraging the Riva ServiceMaker framework to aggregate all the necessary artifacts for Riva deployment to a target environment. Once the model is deployed in Riva, you can issue inference requests to the server. We will demonstrate how quick and straightforward this whole process is.

Learning Objectives

In this notebook, you will learn how to:

Use Riva ServiceMaker to take a TAO exported .riva and generate a model resources
Deploy the model(s) locally on the Riva Server
Send inference requests from a demo client using Riva API bindings.

Pre-requisites

To follow along, please make sure:

You have access to NVIDIA NGC, and are able to download the Riva Quickstart resources
Have a .riva model file that you wish to deploy. You can obtain this from tao <task> export (with export_format=RIVA). Please refer the tutorial on Question Answering using Train Adapt Optimize (TAO) Toolkit for more details on training and exporting a .riva model.

Riva ServiceMaker

Servicemaker is the set of tools that aggregates all the necessary artifacts (models, files, configurations, and user settings) for Riva deployment to a target environment. It has two main components as shown below:

1. Riva-build

This step helps build a Riva-ready version of the model. It’s only output is an intermediate format (called a RMIR) of an end to end pipeline for the supported services within Riva. We are taking a QA model in consideration

riva-build is responsible for the combination of one or more exported models (.riva files) into a single file containing an intermediate format called Riva Model Intermediate Representation (.rmir). This file contains a deployment-agnostic specification of the whole end-to-end pipeline along with all the assets required for the final deployment and inference. Please check out the documentation to find out more.

In [ ]:

# IMPORTANT: Set the following variables

# Name of ServiceMaker Docker Image
RIVA_SM_CONTAINER = "<add container name>"

# Directory where the .riva model is stored $MODEL_LOC/*.riva
MODEL_LOC = "<add path to model directory>"

# Name of the .riva file
MODEL_NAME = "<add model name>"

# Key that model is encrypted with
KEY = "<add encryption key used for trained model>"

In [ ]:

# Get the ServiceMaker docker
!docker pull $RIVA_SM_CONTAINER

In [ ]:

# Syntax: riva-build <task-name> output-dir-for-rmir/model.rmir:key dir-for-riva/model.riva:key
!docker run --rm --gpus 1 -v $MODEL_LOC:/data $RIVA_SM_CONTAINER -- \
            riva-build qa /data/question-answering.rmir:$KEY /data/$MODEL_NAME:$KEY

NOTE: Above, qa-model.riva is the qa model obtained from tao question_answering export

2. Riva-deploy

The deployment tool takes as input one or more Riva Model Intermediate Representation (RMIR) files and a target model repository directory. It creates an ensemble configuration specifying the pipeline for the execution and finally writes all those assets to the output model repository directory.

In [ ]:

# Syntax: riva-deploy -f dir-for-rmir/model.rmir:key output-dir-for-repository
!docker run --rm --gpus 1 -v $MODEL_LOC:/data $RIVA_SM_CONTAINER -- \
            riva-deploy -f /data/question-answering.rmir:$KEY /data/models

Start Riva Server

Once the model repository is generated, we are ready to start the Riva server. From this step onwards you need to download the Riva QuickStart Resource from NGC. Set the path to the directory here:

In [ ]:

 ### Set the Riva QuickStart directory
RIVA_DIR = <path_to_riva_quickstart>

Next, we modify config.sh to enable relevant Riva services (nlp for Question Answering model), provide the encryption key, and path to the model repository (riva_model_loc) generated in the previous step among other configurations.

For instance, if above the model repository is generated at $MODEL_LOC/models, then you can specify riva_model_loc as the same directory as MODEL_LOC

Pretrained versions of models specified in models_asr/nlp/tts are fetched from NGC. Since we are using our custom model, we can comment it in models_nlp (and any others that are not relevant to your use case).

NOTE: You can perform this step of editing config.sh from outside this notebook.

config.sh snipet

# Enable or Disable Riva Services 
service_enabled_asr=false                                 ## MAKE CHANGES HERE
service_enabled_nlp=true                                  ## MAKE CHANGES HERE
service_enabled_tts=false                                 ## MAKE CHANGES HERE

# Specify one or more GPUs to use
# specifying more than one GPU is currently an experimental feature, and may result in undefined behaviours.
gpus_to_use="device=0"

# Specify the encryption key to use to deploy models
MODEL_DEPLOY_KEY="tlt_encode"                             ## Set the model encryption key

# Locations to use for storing models artifacts
...
riva_model_loc="<add path>"                              ## Replace with MODEL_LOC

# The default RMIRs are downloaded from NGC by default in the above $riva_rmir_loc directory
# If you'd like to skip the download from NGC and use the existing RMIRs in the $riva_rmir_loc
# then set the below $use_existing_rmirs flag to true.
...
use_existing_rmirs=true                                  ## Set to True

In [ ]:

# Ensure you have permission to execute these scripts
!cd $RIVA_DIR && chmod +x ./riva_init.sh && chmod +x ./riva_start.sh

In [ ]:

# Run Riva Init. This will fetch the containers/models
# YOU CAN SKIP THIS STEP IF YOU DID RIVA DEPLOY
!cd $RIVA_DIR && ./riva_init.sh config.sh

In [ ]:

# Run Riva Start. This will deploy your model(s).
!cd $RIVA_DIR && ./riva_start.sh config.sh

Run Inference

Once the Riva server is up and running with your models, you can send inference requests querying the server.

To send GRPC requests, you can install Riva Python API bindings for client. This is available as a pip .whl with the QuickStart.

In [ ]:

# IMPORTANT: Set the name of the whl file
RIVA_API_WHL = "<add riva api .whl file name>"

In [ ]:

# Install client API bindings
!cd $RIVA_DIR && pip install $RIVA_API_WHL

The following code sample shows how you can perform inference using Riva Python API gRPC bindings:

In [ ]:

import grpc
import riva_api.riva_nlp_pb2 as rnlp
import riva_api.riva_nlp_pb2_grpc as rnlp_srv


grpc_server =  "localhost:50051"
channel = grpc.insecure_channel(grpc_server)
riva_nlp = rnlp_srv.RivaLanguageUnderstandingStub(channel)

req = rnlp.NaturalQueryRequest()

test_context = "In 2010 the Amazon rainforest experienced another severe drought, in some ways more extreme than the 2005 drought."\
                "The affected region was approximate 1,160,000 square miles (3,000,000 km2) of rainforest, compared to 734,000 square miles (1,900,000 km2)" \
                " in 2005. The 2010 drought had three epicenters where vegetation died off, whereas in 2005 the drought was focused on the southwestern part." \
                " The findings were published in the journal Science. In a typical year the Amazon absorbs 1.5 gigatons of carbon dioxide; during 2005" \
                "instead 5 gigatons were released and in 2010 8 gigatons were released."
req.query = "How many tons of carbon are absorbed the Amazon in a typical year?"
req.context = test_context
resp = riva_nlp.NaturalQuery(req)
print(resp)

NOTE: You could also run the above inference code from inside the Riva Client container. The QuickStart provides a script riva_start_client.sh to run the container. It has more examples for different services.

You can stop all docker container before shutting down the jupyter kernel. Caution: The following command will stop all running containers

In [ ]:

!docker stop $(docker ps -a -q)

What's next?

You could train your own custom models in TAO and deploy them in Riva! You could scale up your deployment using Kubernetes with the Riva AI Services Helm Chart, which will pull the relevant Images and download model artifacts from NGC, generate the model repository, start and expose the Riva speech services.