Python SDK for Merlin
Project description
Merlin SDK
This project contains python library for interacting with Merlin, machine learning model serving component of CaraML. It provides interface to:
- Manage ML project resources
- Track metrics and training performance
- Package and Deploy Model
Installation
pip install merlin-sdk
and authenticate to gcloud
gcloud auth application-default login
Getting Started
The easiest way to get started is to explore example notebook:
- Deploying xgboost model
- Deploying sklearn model
- Deploying tensorflow model
- Deploying pytorch model
- Deploying user defined model
Development
Requirements:
- pipenv (
pip install pipenv
) - swagger code gen (
brew install swagger-codegen
)
Setup development environment:
make setup
Merlin CLI
With the CLI, users can deploy a trained model (serialized model) without touching Python code at all.
To use the CLI:
// to see available subcommands
merlin --help
// to see subcommand options
merlin SUBCOMMAND --help
// deploy existing xgboost model located inside cur_model_dir
merlin deploy --url localhost --model-type xgboost --project sample --model-dir cur_model_dir --model-name xgboost-sample --env staging
// undeploy xgboost-sample version 1
merlin undeploy --url localhost --project sample --model-name xgboost-sample --model-version=1
// generate pyfunc code base
merlin scaffold -p merlin-project -m model-name -e id
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
merlin-sdk-0.26.0rc5.tar.gz
(1.2 MB
view hashes)
Built Distribution
merlin_sdk-0.26.0rc5-py3-none-any.whl
(186.4 kB
view hashes)
Close
Hashes for merlin_sdk-0.26.0rc5-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d4681b1aba57256a3207effd085b6a69bacf97b2210c8e4d1c20c92daf890be6 |
|
MD5 | 95e3eeb4a43175820868f91040317b04 |
|
BLAKE2b-256 | b894356bacb8d095cf6973ebfaa1d82393eaafedfb1f5d785fe26dcf78d5afc6 |