akiragy/recsys_pipeline

Build Recommender System with PyTorch + Redis + Elasticsearch + Feast + Triton + Flask. Vector Recall, DeepFM Ranking and Web Application.

34
/ 100
Emerging

This project helps e-commerce or media companies build and deploy a personalized recommendation system. It takes user interaction data (like movie ratings or product clicks) and generates relevant item suggestions. This is for product managers, data scientists, or machine learning engineers who need to understand or implement a full recommender system pipeline, from data preparation to a deployed web application.

No commits in the last 6 months.

Use this if you need a comprehensive, end-to-end example of building a recommender system with real-world complexities, from offline model training to online serving.

Not ideal if you're looking for a simple, single-script solution for basic recommendations without deploying multiple components.

e-commerce media-recommendations personalization machine-learning-deployment data-science
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

63

Forks

15

Language

Python

License

Last pushed

Sep 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/akiragy/recsys_pipeline"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.