edit

PipelineAI APIs

Install Pre-Requisites

Docker

Python3

Setup pipeline-ai-cli

Note: This command line interface requires Python3 and Docker. (See Pre-Requisites above.)

pip install --ignore-installed --no-cache -U pipeline-ai-cli

Supported Model Types

scikit, tensorflow, python, keras, pmml, spark, xgboost, r

More samples coming soon for r.

Clone this Repo

This may take a few minutes...

git clone https://github.com/fluxcapacitor/pipeline

Change to pipeline/predict Directory within Cloned Repo

cd pipeline/predict

Build Model into Docker Image

Note: The --model-path currently must be relative to the pipeline/predict directory.

pipeline model-build --model-type=tensorflow \
                     --model-name=mnist \
                     --model-tag=master \
                     --model-path=./models/tensorflow/mnist

Start Docker-based Model

pipeline model-start --model-type=tensorflow \
                     --model-name=mnist \
                     --model-tag=master \
                     --memory-limit=2G
Note: If you see docker: Error response from daemon: ... failed: port is already allocated., you likely have another Docker container running. Use docker ps to find the container-id, then docker rm -f <container-id> to remove the other Docker container.

Monitor Model Training and Hyper-Parameter Tuning

View the logs and wait for them to settle down.

pipeline model-logs --model-type=tensorflow \
                    --model-name=mnist \
                    --model-tag=master

View PipelineAI Model UI (TensorFlow Models Only)

This UI sometimes requires a couple refreshes. We are working to stabilize the UI.

Note: This UI currently works only with TensorFlow Models

http://localhost:6333/

PipelineAI Model UI

PipelineAI Model UI

Predict Model

CLI

Perform Single Image Prediction

Note: This first call will take 10-20x longer than subsequent calls. Lazy init, warm-up, etc.

pipeline model-predict --model-type=tensorflow \
                       --model-name=mnist \
                       --model-tag=master \
                       --model-server-url=http://localhost:6969 \
                       --model-test-request-path=./models/tensorflow/mnist/data/test_request.json

Perform 100 Predictions in Parallel

pipeline model-predict --model-type=tensorflow \
                       --model-name=mnist \
                       --model-tag=master \
                       --model-server-url=http://localhost:6969 \
                       --model-test-request-path=./models/tensorflow/mnist/data/test_request.json \
                       --model-test-request-concurrency=100

REST API

Prediction Inputs

JSON representation of gray-scale values for a given digit (5).

curl -X POST -H "Content-Type: application/json" \
  -d '{"image": [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.05098039656877518, 0.529411792755127, 0.3960784673690796, 0.572549045085907, 0.572549045085907, 0.847058892250061, 0.8156863451004028, 0.9960784912109375, 1.0, 1.0, 0.9960784912109375, 0.5960784554481506, 0.027450982481241226, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32156863808631897, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.7882353663444519, 0.11764706671237946, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32156863808631897, 0.9921569228172302, 0.988235354423523, 0.7921569347381592, 0.9450981020927429, 0.545098066329956, 0.21568629145622253, 0.3450980484485626, 0.45098042488098145, 0.125490203499794, 0.125490203499794, 0.03921568766236305, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32156863808631897, 0.9921569228172302, 0.803921639919281, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6352941393852234, 0.9921569228172302, 0.803921639919281, 0.24705883860588074, 0.3490196168422699, 0.6509804129600525, 0.32156863808631897, 0.32156863808631897, 0.1098039299249649, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.007843137718737125, 0.7529412508010864, 0.9921569228172302, 0.9725490808486938, 0.9686275124549866, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.8274510502815247, 0.29019609093666077, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2549019753932953, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.847058892250061, 0.027450982481241226, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5921568870544434, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.7333333492279053, 0.44705885648727417, 0.23137256503105164, 0.23137256503105164, 0.4784314036369324, 0.9921569228172302, 0.9921569228172302, 0.03921568766236305, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5568627715110779, 0.9568628072738647, 0.7098039388656616, 0.08235294371843338, 0.019607843831181526, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.43137258291244507, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15294118225574493, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.1882353127002716, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6705882549285889, 0.9921569228172302, 0.9921569228172302, 0.12156863510608673, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2392157018184662, 0.9647059440612793, 0.9921569228172302, 0.6274510025978088, 0.003921568859368563, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08235294371843338, 0.44705885648727417, 0.16470588743686676, 0.0, 0.0, 0.2549019753932953, 0.9294118285179138, 0.9921569228172302, 0.9333333969116211, 0.27450981736183167, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4941176772117615, 0.9529412388801575, 0.0, 0.0, 0.5803921818733215, 0.9333333969116211, 0.9921569228172302, 0.9921569228172302, 0.4078431725502014, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.7411764860153198, 0.9764706492424011, 0.5529412031173706, 0.8784314393997192, 0.9921569228172302, 0.9921569228172302, 0.9490196704864502, 0.43529415130615234, 0.007843137718737125, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6235294342041016, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9764706492424011, 0.6274510025978088, 0.1882353127002716, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.18431372940540314, 0.5882353186607361, 0.729411780834198, 0.5686274766921997, 0.3529411852359772, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]}' \
  http://localhost:6969/api/v1/model/predict/tensorflow/mnist \
  -w "\n\n"

### EXPECTED OUTPUT ###

{"outputs": [0.0022526539396494627, 2.63791100074684e-10, 0.4638307988643646, 0.21909376978874207, 3.2985670372909226e-07, 0.29357224702835083, 0.00019597385835368186, 5.230629176367074e-05, 0.020996594801545143, 5.426473762781825e-06]}

Prediction Outputs

Digit  Confidence
=====  ==========
0      0.0022526539396494627
1      2.63791100074684e-10
2      0.4638307988643646
3      0.21909376978874207
4      3.2985670372909226e-07
5      0.29357224702835083 
6      0.00019597385835368186
7      5.230629176367074e-05
8      0.020996594801545143
9      5.426473762781825e-06

Monitor Model Predictions

Note: These dashboards will be rolled into the PipelineAI Model UI soon! Username/Password: admin/admin

Use http://localhost:9090 for the Prometheus data source within your Grafana Dashboard.

http://localhost:3000/

Stop Docker-based Model

pipeline model-stop --model-type=tensorflow \
                    --model-name=mnist \
                    --model-tag=master

Extras

Shell into Docker-based Model

pipeline model-shell --model-type=tensorflow \
                     --model-name=mnist \
                     --model-tag=master

Push Image to Docker

pipeline model-push --model-type=tensorflow \
                    --model-name=mnist \
                    --model-tag=master

Create Kubernetes YAML for the Model

pipeline model-yaml --model-type=tensorflow \
                    --model-name=mnist \
                    --model-tag=master

### EXPECTED OUTPUT ###
Using templates in '/Users/cfregly/workspace-fluxcapacitor/pipeline/predict/templates'.
(Specify --template-path if the templates live elsewhere.)

'predict-deploy.yaml.template' -> './tensorflow-mnist-cpu-master-deploy.yaml'.
'predict-svc.yaml.template' -> './tensorflow-mnist-cpu-master-svc.yaml'.
...

Deploy Model to Kubernetes Using Generated YAML Above

Create the Kubernetes Deployment

pipeline kube-create ./tensorflow-mnist-cpu-master-deploy.yaml

Create the Kubernetes Service (Load Balancer)

pipeline kube-create ./tensorflow-mnist-cpu-master-svc.yaml


Try our Free Community Edition!

Click HERE to get started with our basic Community Edition

Register for PipelineAI Advanced Edition


Take a Quick Tour!


Help Us Improve

Option 1: Edit the documentation directly.

Option 2: Create a GitHub issue.

More Resources