Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/codelibs/recotem
An easy to use interface to recommender systems.
https://github.com/codelibs/recotem
recomender-system
Last synced: about 1 month ago
JSON representation
An easy to use interface to recommender systems.
- Host: GitHub
- URL: https://github.com/codelibs/recotem
- Owner: codelibs
- License: apache-2.0
- Created: 2021-04-27T12:23:50.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-04-28T23:50:26.000Z (over 2 years ago)
- Last Synced: 2024-04-16T18:17:31.141Z (9 months ago)
- Topics: recomender-system
- Language: Vue
- Homepage: https://recotem.org
- Size: 461 KB
- Stars: 8
- Watchers: 8
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Recotem
## Overview
Recotem is an easy to use interface to recommender systems;
Recotem can be launched on any platform with Docker.
It ships with a Web-base UI, and you can train and (qualitatively) evaluate the recommendation engine solely using UI.
Recotem is licensed under Apache 2.0.
## Website
[recotem.org](https://recotem.org)
## Issues/Questions
[discuss.codelibs.org](https://discuss.codelibs.org/c/recotemen/11)
## Getting Started
There are two ways to start using Recotem. Both requires [latest docker](https://docs.docker.com/get-docker/).
### 1. Using pre-built image.
1. Visit [latest release](https://github.com/codelibs/recotem/releases/latest)
1. Download "Docker resources to try out" from Assets
1. Unzip it and
- (Windows) Click "recotem-compose" script
- (Linux & MacOS) Run `docker-compose` there.
```sh
docker-compose up`
```
See [https://recotem.org/guide/installation.html]([https://recotem.org/guide/installation.html]) for a friendlier introduction.
### 2. Building the image
1. Clone this repository.
2. In the repository top directory, simply run
```sh
docker-compose up
```
## Development
### Backend & Worker
To run the backend (and worker) in Django development mode, use `docker-compose-dev.yml`.
```
docker-compose -f docker-compose-dev.yml build
docker-compose -f docker-compose-dev.yml up
```
### frontend
To run the frontend webpack-dev-sever, you will need a descent version of yarn.
After `yarn` under `frontend/` directory to install the dependency, run
```sh
cd frontend
yarn serve
```
In order for the frontend to work with the API, you first have to launch the backend following the above instruction.
## Command-line tool
[recotem-cli](https://github.com/codelibs/recotem-cli) allows you to
- tune & train recommender systems
- obtain the recommendation result
via command-line interface.
## Batch execution on ECS
There is [an example project](https://github.com/codelibs/recotem-batch-example) which uses recotem to batch-execute recommendation task on Amazon ECS.