BatsResearch/trove

A Flexible Toolkit for Dense Retrieval

36
/ 100
Emerging

This toolkit helps machine learning engineers and researchers build and evaluate information retrieval systems. It takes queries and documents, and using transformer models, it helps identify the most relevant documents for each query. The toolkit simplifies experimentation with new ideas and integrates well into existing workflows, primarily for those developing search, recommendation, or question-answering systems.

Use this if you are a machine learning engineer or researcher developing dense retrieval models and need a flexible, unified interface for training, evaluation, and data manipulation.

Not ideal if you are looking for a pre-built, off-the-shelf retrieval system without needing to customize or experiment with the underlying models.

information-retrieval dense-retrieval search-systems natural-language-processing machine-learning-research
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

44

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Nov 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/BatsResearch/trove"

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