koursaros-ai/nboost
NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)
Acts as a proxy between search clients and search engines, intercepting queries to rerank results using fine-tuned transformer models (TinyBERT, BERT-base, BioBERT) before returning them to users. Supports both PyTorch and TensorFlow backends with domain-specific models trained on MS Marco, achieving 45-77% MRR improvements over BM25 baselines. Deployable via Docker, pip, or Kubernetes with built-in support for Elasticsearch and other search platforms.
674 stars and 316 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
674
Forks
70
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 30, 2020
Monthly downloads
316
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/koursaros-ai/nboost"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
freedmand/semantra
Multi-tool for semantic search
patrickfrank1/chesspos
Embedding based chess position search and embedding learning for chess positions
alexklibisz/elastiknn
Elasticsearch plugin for nearest neighbor search. Store vectors and run similarity search using...
Mubelotix/SimRepo
Shows similar repositories in the sidebar
md-experiments/elastic_transformers
Making BERT stretchy. Semantic Elasticsearch with Sentence Transformers