{"id":20235988,"url":"https://github.com/combust/mleap-docs","last_synced_at":"2025-04-10T19:03:57.202Z","repository":{"id":16040034,"uuid":"79174443","full_name":"combust/mleap-docs","owner":"combust","description":"Documentation for MLeap","archived":false,"fork":false,"pushed_at":"2023-07-19T18:04:16.000Z","size":1709,"stargazers_count":14,"open_issues_count":6,"forks_count":22,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-24T16:44:56.286Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/combust.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-01-17T01:10:02.000Z","updated_at":"2024-02-29T04:49:21.000Z","dependencies_parsed_at":"2024-11-14T08:28:56.974Z","dependency_job_id":null,"html_url":"https://github.com/combust/mleap-docs","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/combust%2Fmleap-docs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/combust%2Fmleap-docs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/combust%2Fmleap-docs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/combust%2Fmleap-docs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/combust","download_url":"https://codeload.github.com/combust/mleap-docs/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248279077,"owners_count":21077379,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-14T08:18:37.656Z","updated_at":"2025-04-10T19:03:57.164Z","avatar_url":"https://github.com/combust.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"assets/images/logo.png\" alt=\"MLeap Logo\" width=\"176\" height=\"70\" /\u003e\n\n#### What is MLeap?\n\nMLeap is a common serialization format and execution engine for machine learning pipelines. It supports Spark, Scikit-learn and Tensorflow for training pipelines and exporting them to an MLeap Bundle. Serialized pipelines (bundles) can be deserialized back into Spark for batch-mode scoring or the MLeap runtime to power realtime API services.\n\n## Why MLeap?\n\nMany companies that use Spark and Scikit-learn have a difficult time\ndeploying their research ML/data pipelines models to production API services. Even using Tensorflow\ncan be difficult to set these services up if a company does not wish to\nuse Python in their API stack or does not use Google ML Cloud. MLeap\nprovides simple interfaces to execute entire ML pipelines, from\nfeature transformers to classifiers, regressions, clustering algorithms,\nand neural networks.\n\n### Portable Models\n\nYour models are your models. Take them with you wherever you go using\nMLeap Bundles. Platforms like Microsoft Azure and Google ML can lock\nyou into their services package. MLeap allows you to take your models\nwith you wherever you go.\n\n### Spark, Scikit-learn and Tensorflow: One Runtime\n\nMixing and matching ML technologies becomes a simple task. Instead of requiring\nan entire team of developers to make research pipelines production ready,\nsimply export to an MLeap Bundle and run your pipeline wherever it is\nneeded.\n\nOther benefits of a unified runtime:\n* Train different pieces of your pipeline using Spark,\nScikit-learn or Tensorflow, then export them to one MLeap Bundle file\nand deploy it anywhere\n* If you're using Scikit for R\u0026D, but Spark comes out with a better algorithm,\nyou can export your Scikit ML pipeline to Spark, train the new model in Spark\nand then deploy to production using the MLeap runtime\n\n\u003cimg src=\"assets/images/single-runtime.jpg\" alt=\"Unified Runtime\"/\u003e\n\n### Common Serialization\n\nIn addition to providing a useful execution engine, MLeap Bundles\nprovide a common serialization format for a large set of ML feature\nextractors and algorithms that are able to be exported and imported\nacross Spark, Scikit-learn, Tensorflow and MLeap. This means you can\neasily convert pipelines between these technologies depending on where\nyou need to execute a pipeline.\n\n### Seamless Integrations\n\nFor the most part, we do not modify any internal code or require custom\nimplementations of transformers in any Spark or Scikit-learn. For\nTensorflow, we use as many builtin ops as we can and implement custom\nops for MLeap when they do not exist. This means that code changes to\nyour existing pipelines are minimal to get up and running with MLeap.\nFor many use cases, no changes will be required and you can simply\nexport to an MLeap Bundle or deploy to a Combust API server to start\ngetting immediate use of your pipeline.\n\n### Open Source\n\nMLeap is entirely open source. Our source code is available at\n[https://github.com/combust/mleap](https://github.com/combust/mleap). We also automate\nour tests and deploys with [travis ci](https://travis-ci.org/combust/mleap).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcombust%2Fmleap-docs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcombust%2Fmleap-docs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcombust%2Fmleap-docs/lists"}