https://github.com/vicradon/product-recommendation-argo-workflows

https://github.com/vicradon/product-recommendation-argo-workflows

Last synced: 25 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/vicradon/product-recommendation-argo-workflows
• Owner: vicradon
• Created: 2022-07-04T14:37:06.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-06-13T03:14:46.000Z (7 months ago)
• Last Synced: 2024-06-13T07:11:18.504Z (7 months ago)
• Language: Python
• Size: 22.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Product Recommendation Pipeline with Argo Workflows

This project is a demo of how one can implement product recommendations in a workflow-like engine (like Argo Workflows). The purpose of this workflow is to build a machine-learning pipeline that recommends products based on images in the object storage container and user queries. The steps of the workflow include:

1. Preprocess - prepare the data for training

2. Register - set up a new task on the training pipeline

3. Train - run the training pipeline with VGG16 for cosine similarity

4. Deploy - push the trained model to production. In this case, the storage container with the models and trigger a restart of the product recommendation service