yuniko-software/bge-m3-qdrant-sample

A demonstration of hybrid search with reranking using Qdrant and BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results

40
/ 100
Emerging

This project helps you build a highly accurate product search system for an e-commerce platform or catalog. You provide product descriptions from a CSV file, and it outputs a search engine that combines understanding the meaning of your query with precise keyword matching. This is for developers or data scientists looking to implement advanced search capabilities.

No commits in the last 6 months.

Use this if you need to create a search engine that can understand both the semantic meaning and exact keywords of a user's query for product discovery.

Not ideal if you're looking for a simple keyword search or an out-of-the-box solution that doesn't require technical setup.

e-commerce product-search information-retrieval vector-databases search-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

28

Forks

8

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Apr 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/yuniko-software/bge-m3-qdrant-sample"

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