PipelineAI: Real-Time Enterprise AI Platform
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
airflow moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
cassandra moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
docs Update README.md Sep 18, 2018
elasticsearch moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
gpu.ml added fp16 flag Dec 11, 2017
hdfs moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
jupyterhub moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
kibana moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
metastore moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
metrics cleaned up, renamed, combined back with source.ml Aug 12, 2017
package bumped version of hdfs Sep 17, 2017
presto moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
redis moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
scripts updated build and push Aug 19, 2017
spark moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
sql moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
zeppelin moved yaml to cli, moved runbooks under docs, renamed keyvalue to redis Nov 28, 2017
.gitignore updated to latest tf and tf serving May 26, 2017
.gitmodules added predict submodule Oct 10, 2017
CODE_OF_CONDUCT.md Create CODE_OF_CONDUCT.md Jun 15, 2017
CONTRIBUTING.md Create CONTRIBUTING.md Jun 15, 2017
LICENSE Initial commit Mar 6, 2017
README.md Update README.md Sep 17, 2018

README.md

PipelineAI Logo

PipelineAI Quick Start (CPU + GPU)

Train and Deploy your ML and AI Models in the Following Environments:

Having Issues? Contact Us Anytime... We're Always Awake.

PipelineAI Community Events

PipelineAI Home

PipelineAI Home PipelineAI Home 1 PipelineAI Home 2

PipelineAI Features

Consistent, Immutable, Reproducible Model Runtimes

Consistent Model Environments

Each model is built into a separate Docker image with the appropriate Python, C++, and Java/Scala Runtime Libraries for training or prediction.

Use the same Docker Image from Local Laptop to Production to avoid dependency surprises.

Sample Machine Learning and AI Models

Click HERE to view model samples for the following:

  • Scikit-Learn
  • TensorFlow
  • Keras
  • Spark ML (formerly called Spark MLlib)
  • XGBoost
  • PyTorch
  • Caffe/2
  • Theano
  • MXNet
  • PMML/PFA
  • Custom Java/Python/C++ Ensembles

Nvidia GPU TensorFlow

Spark ML Scikit-Learn

R PMML

Xgboost Model Ensembles

Supported Model Runtimes (CPU and GPU)

  • Python (Scikit, TensorFlow, etc)
  • Java
  • Scala
  • Spark ML
  • C++
  • Caffe2
  • Theano
  • TensorFlow Serving
  • Nvidia TensorRT (TensorFlow, Caffe2)
  • MXNet
  • CNTK
  • ONNX

Supported Streaming Engines

  • Kafka
  • Kinesis
  • Flink
  • Spark Streaming
  • Heron
  • Storm

Advanced PipelineAI Product Features

  • Click HERE to compare PipelineAI Products.

Drag N' Drop Model Deploy

PipelineAI Drag n' Drop Model Deploy UI

Generate Optimize Model Versions Upon Upload

Automatic Model Optimization and Native Code Generation

Distributed Model Training and Hyper-Parameter Tuning

PipelineAI Advanced Model Training UI

PipelineAI Advanced Model Training UI 2

Continuously Deploy Models to Clusters of PipelineAI Servers

PipelineAI Weavescope Kubernetes Cluster

View Real-Time Prediction Stream

Live Stream Predictions

Compare Both Offline (Batch) and Real-Time Model Performance

PipelineAI Model Comparison

Compare Response Time, Throughput, and Cost-Per-Prediction

PipelineAI Compare Performance and Cost Per Prediction

Shift Live Traffic to Maximize Revenue and Minimize Cost

PipelineAI Traffic Shift Multi-armed Bandit Maxmimize Revenue Minimize Cost

Continuously Fix Borderline Predictions through Crowd Sourcing

Borderline Prediction Fixing and Crowd Sourcing