eugeneyan/semantic-ids-llm
Semantic IDs: How to train an LLM-Recommender Hybrid with steerability and reasoning on recommendations.
This helps retail or e-commerce businesses provide more engaging product recommendations. You provide customer preferences or past purchases, and it generates specific product IDs along with natural language explanations. This is for product managers, merchandisers, or customer service teams looking to enhance their recommendation engines.
106 stars. No commits in the last 6 months.
Use this if you want to offer personalized product suggestions through a conversational interface that can explain its reasoning and respond to follow-up questions.
Not ideal if your primary concern is maximizing recommendation accuracy above all else, as specialized recommenders might offer higher precision.
Stars
106
Forks
27
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/eugeneyan/semantic-ids-llm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
snap-research/GRID
GRID: Generative Recommendation with Semantic IDs
HKUDS/XRec
[EMNLP'2024] "XRec: Large Language Models for Explainable Recommendation"
HKUDS/RLMRec
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
HKUDS/EasyRec
[EMNLP'2025] "EasyRec: Simple yet Effective Language Model for Recommendation"
taherfattahi/recommendation-systems-by-llms
Enhancing Recommendation Systems with Large Language Models (RAG - LangChain - OpenAI)