{"id":26671117,"url":"https://github.com/scaleapi/launch-python-client","last_synced_at":"2025-04-12T04:13:17.463Z","repository":{"id":37048921,"uuid":"471082413","full_name":"scaleapi/launch-python-client","owner":"scaleapi","description":"developing the official Python SDK for Launch, part of Scale API, the Data Platform for AI","archived":false,"fork":false,"pushed_at":"2025-01-23T02:33:29.000Z","size":4930,"stargazers_count":7,"open_issues_count":10,"forks_count":4,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-04-12T04:13:12.997Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/scaleapi.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":"2022-03-17T17:38:20.000Z","updated_at":"2025-03-25T22:44:45.000Z","dependencies_parsed_at":"2023-02-18T02:01:12.329Z","dependency_job_id":"8edee691-350e-46ce-b296-328992842928","html_url":"https://github.com/scaleapi/launch-python-client","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/scaleapi%2Flaunch-python-client","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scaleapi%2Flaunch-python-client/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scaleapi%2Flaunch-python-client/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scaleapi%2Flaunch-python-client/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/scaleapi","download_url":"https://codeload.github.com/scaleapi/launch-python-client/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248514203,"owners_count":21116903,"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":"2025-03-25T23:43:53.721Z","updated_at":"2025-04-12T04:13:17.427Z","avatar_url":"https://github.com/scaleapi.png","language":"Python","readme":"# Launch Python Client\n```\n██╗      █████╗ ██╗   ██╗███╗   ██╗ ██████╗██╗  ██╗\n██║     ██╔══██╗██║   ██║████╗  ██║██╔════╝██║  ██║\n██║     ███████║██║   ██║██╔██╗ ██║██║     ███████║\n██║     ██╔══██║██║   ██║██║╚██╗██║██║     ██╔══██║\n███████╗██║  ██║╚██████╔╝██║ ╚████║╚██████╗██║  ██║\n╚══════╝╚═╝  ╚═╝ ╚═════╝ ╚═╝  ╚═══╝ ╚═════╝╚═╝  ╚═╝\n```\n\nMoving an ML model from experiment to production requires significant engineering lift.\nScale Launch provides ML engineers a simple Python interface for turning a local code snippet into a production service.\nA ML engineer needs to call a few functions from Scale's SDK, which quickly spins up a production-ready service.\nThe service efficiently utilizes compute resources and automatically scales according to traffic.\n\nLatest API/SDK reference can be found [here](https://scaleapi.github.io/launch-python-client/).\n\n## Deploying your model via Scale Launch\n\nCentral to Scale Launch are the notions of a `ModelBundle` and a `ModelEndpoint`.\nA `ModelBundle` consists of a trained model as well as the surrounding preprocessing and postprocessing code.\nA `ModelEndpoint` is the compute layer that takes in a `ModelBundle`, and is able to carry out inference requests\nby using the `ModelBundle` to carry out predictions. The `ModelEndpoint` also knows infrastructure-level details,\nsuch as how many GPUs are needed, what type they are, how much memory, etc. The `ModelEndpoint` automatically handles\ninfrastructure level details such as autoscaling and task queueing.\n\nSteps to deploy your model via Scale Launch:\n\n1. First, you create and upload a `ModelBundle`.\n\n2. Then, you create a `ModelEndpoint`.\n\n3. Lastly, you make requests to the `ModelEndpoint`.\n\nTODO: link some example colab notebook\n\n\n## For Developers\n\nClone from github and install as editable\n\n```\ngit clone git@github.com:scaleapi/launch-python-client.git\ncd launch-python-client\npip3 install poetry\npoetry install\n```\n\nPlease install the pre-commit hooks by running the following command:\n\n```bash\npoetry run pre-commit install\n```\n\nThe tests can be run with:\n\n```bash\npoetry run pytest\n```\n\n### Documentation\n\n**Updating documentation:**\nWe use [mkdocs](https://www.mkdocs.org/) to autogenerate our API Reference from docstrings and \nmarkdown files.\n\nTo test your local docstring changes, run the following commands from the repository's root directory:\n\n```\npoetry shell\nmkdocs serve\n```\n\nThe above command will spin up a server on localhost (port 8000 by default) that will watch for and\nautomatically rebuild a version of the API reference based on your local docstring and markdown\nchanges.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscaleapi%2Flaunch-python-client","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fscaleapi%2Flaunch-python-client","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscaleapi%2Flaunch-python-client/lists"}