Description

Loud ML

Loud ML is meant to be used as a time series inference and AutoML engine for any use case involving large amounts of timestamped data, including DevOps monitoring, application metrics, IoT sensor data, and real-time analytics.

Installation Instructions

Quick reference

• Where to file issues:
  https://github.com/regel/loudml/issues

• Maintained by:
  Sébastien Léger

Using this Image

Running the loudmld service

Configuration

The configuration file named /etc/loudml/config.yml configures service parameters. The example below can be used as a starting point to ensure the service can start, and then can be adapted to the real environment.

---
buckets: []

storage:
  path: /var/lib/loudml

server:
  listen: 0.0.0.0:8077

Running the service

Start the service using:

systemctl start loudmld

Health check

You can query the API to check the service is running properly:

$ curl http://localhost:8077
{"host_id":"86fe1a2bf19f89e83cee363f934d6bbe","tagline":"The Disruptive Machine Learning API","version":"1.5.0"}

Using the Python client library and interactive command line

The loudml-python package available on PyPI is a command line client designed to control the Loud ML model server.

If you’ve installed loudml-python locally, the loudml command should be available via the command line. Executing loudml will start the CLI and automatically connect to your loudml server container. The output should look like this:

$ loudml -A localhost:8077
Connected to localhost:8077 version 1.6.0-577c87de
Loud ML shell 1.6.0-42136d38
>

Active Releases

The following unofficial repositories are provided as-is by owner of this project. Contact the owner directly for bugs or issues (IE: not bugzilla).

Release	Architectures	Repo Download
EPEL 7	x86_64 (83)*	EPEL 7 (114 downloads)
EPEL 8	x86_64 (22)*	EPEL 8 (87 downloads)

* Total number of downloaded packages.