machinelearningZH/hybrid-search-eval
A framework for benchmarking embedding models in hybrid search scenarios (BM25 + vector search) using Weaviate.
This tool helps data scientists and machine learning engineers compare different ways to find information within a large collection of documents. You provide your documents and an optional list of search queries, and it tells you which search methods (like keyword-based, semantic, or a mix) are most effective and efficient. This is for anyone building or improving a search system and needing to objectively measure its performance before deployment.
Use this if you need to objectively evaluate how well different document search strategies perform on your specific data, measuring both search quality and system resources like memory and speed.
Not ideal if you are looking for a plug-and-play search solution, or if your primary goal is to train new embedding models rather than evaluate existing ones.
Stars
38
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/machinelearningZH/hybrid-search-eval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
freedmand/semantra
Multi-tool for semantic search
koursaros-ai/nboost
NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve...
Mubelotix/SimRepo
Shows similar repositories in the sidebar