joonsoome / embed-rerankView on GitHub
A Python-based API service built with FastAPI and PyTorch that performs both text embedding and reranking using such as powerful omni-model Qwen3-Embedding-4B. Designed to load a single model instance in memory to efficiently handle embedding & reranking requests simultaneously, enabling fast and resource-effective operations.
17Feb 10, 2026Updated 5 months ago

Alternatives and similar repositories for embed-rerank

Users that are interested in embed-rerank are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?