ssisOneTeam/Korean-Embedding-Model-Performance-Benchmark-for-Retriever

Korean Sentence Embedding Model Performance Benchmark for RAG

23
/ 100
Experimental

This project helps improve the accuracy of RAG (Retrieval Augmented Generation) systems designed for Korean public welfare services. It takes Korean welfare policy documents and generates specialized question-and-answer datasets, then uses them to evaluate and fine-tune various Korean embedding models. The output is a benchmark of which Korean embedding models perform best for retrieving relevant information within the welfare domain. This is for RAG system developers, AI researchers, or data scientists working on Korean natural language processing applications, specifically in the public service sector.

No commits in the last 6 months.

Use this if you are building a Korean RAG system for public welfare information and need to identify the best performing embedding models to ensure accurate retrieval of answers.

Not ideal if your RAG system is not focused on Korean language, public welfare, or if you are not interested in benchmarking different embedding model performances.

Korean NLP Public Welfare RAG System Information Retrieval Semantic Search
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

50

Forks

3

Language

Jupyter Notebook

License

Last pushed

Jan 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ssisOneTeam/Korean-Embedding-Model-Performance-Benchmark-for-Retriever"

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