{"id":20594366,"url":"https://github.com/rekcurd/rekcurd-python","last_synced_at":"2025-07-03T08:06:40.314Z","repository":{"id":57424242,"uuid":"141214135","full_name":"rekcurd/rekcurd-python","owner":"rekcurd","description":"Project for serving ML module. This is a gRPC micro-framework.","archived":false,"fork":false,"pushed_at":"2020-10-01T05:14:40.000Z","size":222,"stargazers_count":47,"open_issues_count":3,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-28T11:38:39.808Z","etag":null,"topics":["drucker","grpc","kubernetes","ml","rekcurd"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rekcurd.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-07-17T01:27:51.000Z","updated_at":"2020-09-21T04:04:06.000Z","dependencies_parsed_at":"2022-09-15T21:31:13.661Z","dependency_job_id":null,"html_url":"https://github.com/rekcurd/rekcurd-python","commit_stats":null,"previous_names":["drucker/drucker"],"tags_count":15,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rekcurd%2Frekcurd-python","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rekcurd%2Frekcurd-python/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rekcurd%2Frekcurd-python/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rekcurd%2Frekcurd-python/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rekcurd","download_url":"https://codeload.github.com/rekcurd/rekcurd-python/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248978861,"owners_count":21192862,"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":["drucker","grpc","kubernetes","ml","rekcurd"],"created_at":"2024-11-16T08:08:46.399Z","updated_at":"2025-04-14T23:32:28.115Z","avatar_url":"https://github.com/rekcurd.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Rekcurd\n\n[![Build Status](https://travis-ci.com/rekcurd/rekcurd-python.svg?branch=master)](https://travis-ci.com/rekcurd/rekcurd-python)\n[![PyPI version](https://badge.fury.io/py/rekcurd.svg)](https://badge.fury.io/py/rekcurd)\n[![codecov](https://codecov.io/gh/rekcurd/rekcurd-python/branch/master/graph/badge.svg)](https://codecov.io/gh/rekcurd/rekcurd-python \"Non-generated packages only\")\n[![pypi supported versions](https://img.shields.io/pypi/pyversions/rekcurd.svg)](https://pypi.python.org/pypi/rekcurd)\n\nRekcurd is the Project for serving ML module. This is a gRPC micro-framework and it can be used like [Django](https://docs.djangoproject.com/) and [Flask](http://flask.pocoo.org/).\n\n\n## Parent Project\nhttps://github.com/rekcurd/community\n\n\n## Components\n- [Rekcurd](https://github.com/rekcurd/rekcurd-python): Project for serving ML module.\n- [Rekcurd-dashboard](https://github.com/rekcurd/dashboard): Project for managing ML model and deploying ML module.\n- [Rekcurd-client](https://github.com/rekcurd/python-client): Project for integrating ML module.\n\n\n## Installation\nFrom source:\n\n```bash\n$ git clone --recursive https://github.com/rekcurd/rekcurd-python.git\n$ cd rekcurd-python\n$ pip install -e .\n```\n\nFrom [PyPi](https://pypi.org/project/rekcurd/) directly:\n\n```bash\n$ pip install rekcurd\n```\n\n## How to use\nExample is available [here](https://github.com/rekcurd/rekcurd-example/tree/master/python/sklearn-digits). You can generate Rekcurd template and implement necessary methods.\n\n```bash\n$ rekcurd startapp {Your application name}\n$ cd {Your application name}\n$ vi app.py\n$ python app.py\n```\n\n\n## Unittest\n```\n$ python -m unittest\n```\n\n\n## Kubernetes support\nRekcurd can be run on Kubernetes. See [community repository](https://github.com/rekcurd/community).\n\n\n## Type definition\n### `PredictLabel` type\n*V* is the length of feature vector.\n\n|Field |Type |Description |\n|:---|:---|:---|\n|input \u003cBR\u003e(required) |One of below\u003cBR\u003e- string\u003cBR\u003e- bytes\u003cBR\u003e- string[*V*]\u003cBR\u003e- int[*V*]\u003cBR\u003e- double[*V*] |Input data for inference.\u003cBR\u003e- \"Nice weather.\" for a sentiment analysis.\u003cBR\u003e- PNG file for an image transformation.\u003cBR\u003e- [\"a\", \"b\"] for a text summarization.\u003cBR\u003e- [1, 2] for a sales forcast.\u003cBR\u003e- [0.9, 0.1] for mnist data. |\n|option |string| Option field. Must be json format. |\n\nThe \"option\" field needs to be a json format. Any style is Ok but we have some reserved fields below.\n\n|Field |Type |Description |\n|:---|:---|:---|\n|suppress_log_input |bool |True: NOT print the input and output to the log message. \u003cBR\u003eFalse (default): Print the input and outpu to the log message. |\n|YOUR KEY |any |YOUR VALUE |\n\n### `PredictResult` type\n*M* is the number of classes. If your algorithm is a binary classifier, you set *M* to 1. If your algorithm is a multi-class classifier, you set *M* to the number of classes.\n\n|Field |Type |Description |\n|:---|:---|:---|\n|label\u003cBR\u003e(required) |One of below\u003cBR\u003e -string\u003cBR\u003e -bytes\u003cBR\u003e -string[*M*]\u003cBR\u003e -int[*M*]\u003cBR\u003e -double[*M*] |Result of inference.\u003cBR\u003e -\"positive\" for a sentiment analysis.\u003cBR\u003e -PNG file for an image transformation.\u003cBR\u003e -[\"a\", \"b\"] for a multi-class classification.\u003cBR\u003e -[1, 2] for a multi-class classification.\u003cBR\u003e -[0.9, 0.1] for a multi-class classification. |\n|score\u003cBR\u003e(required) |One of below\u003cBR\u003e -double\u003cBR\u003e -double[*M*] |Score of result.\u003cBR\u003e -0.98 for a binary classification.\u003cBR\u003e -[0.9, 0.1] for a multi-class classification. |\n|option |string |Option field. Must be json format. |\n\n### `EvaluateResult` type\n`EvaluateResult` is the evaluation score. *N* is the number of evaluation data. *M* is the number of classes. If your algorithm is a binary classifier, you set *M* to 1. If your algorithm is a multi-class classifier, you set *M* to the number of classes.\n\n|Field |Type |Description |\n|:---|:---|:---|\n|num\u003cBR\u003e(required)|int |Number of evaluation data. |\n|accuracy\u003cBR\u003e(required) |double |Accuracy. |\n|precision\u003cBR\u003e(required) |double[*M*] |Precision. |\n|recall\u003cBR\u003e(required) |double[*M*] |Recall. |\n|fvalue\u003cBR\u003e(required) |double[*M*] |F1 value. |\n\n### `EvaluateDetail` type\n`EvaluateDetail` is the details of evaluation result.\n\n|Field |Type |Description |\n|:---|:---|:---|\n|result\u003cBR\u003e(required) |PredictResult |Prediction result. |\n|is_correct\u003cBR\u003e(required) |bool |Correct or not. |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frekcurd%2Frekcurd-python","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frekcurd%2Frekcurd-python","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frekcurd%2Frekcurd-python/lists"}