Metadata-Version: 2.4
Name: benchlite
Version: 0.1.1
Summary: A lightweight toolkit for evaluating retrieval-augmented generation (RAG) systems: recall@k, precision@k, MRR, answer similarity, and basic hallucination checks.
Author-email: Aditya Yadav <adityayadav130305@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/adityayadav13/benchlite
Project-URL: Repository, https://github.com/adityayadav13/benchlite
Project-URL: Issues, https://github.com/adityayadav13/benchlite/issues
Keywords: RAG,evaluation,metrics,NLP,retrieval,LLMs
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: sentence-transformers
Requires-Dist: tqdm

# BenchLite

A lightweight and modular toolkit for evaluating **Retrieval-Augmented Generation (RAG)** systems.  
BenchLite provides essential retrieval and answer evaluation metrics, including:

- **Recall@K**
- **Precision@K**
- **Mean Reciprocal Rank (MRR)**
- **Embedding-based Answer Similarity**
- **Basic Hallucination Detection**

Published on **PyPI** → https://pypi.org/project/benchlite/

---

## 🔧 Installation

Install the latest version using pip:

```bash
pip install benchlite
