A lightweight toolkit for evaluating retrieval-augmented generation (RAG) systems: recall@k, precision@k, MRR, answer similarity, and basic hallucination checks.
Project description
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:
pip install benchlite
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file benchlite-0.1.1.tar.gz.
File metadata
- Download URL: benchlite-0.1.1.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
66055cba4fe8792fe8c5888774ade2210e3a16c3110f2377d292b92e32cb88e3
|
|
| MD5 |
0cc7d77226952e3b8eb6d6329be7e371
|
|
| BLAKE2b-256 |
1fd433225ccf3346837c5d183fdfcd5b9579890badb3676ca38782bf7ea155fd
|
File details
Details for the file benchlite-0.1.1-py3-none-any.whl.
File metadata
- Download URL: benchlite-0.1.1-py3-none-any.whl
- Upload date:
- Size: 7.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ec4615ea70a69c868025d34f61413bd283676aff1539c5783c7c4cff28c7b164
|
|
| MD5 |
5ec278794aaf76d3b77155aed6d2fcb8
|
|
| BLAKE2b-256 |
89fa1f5069d9ea173bae96b8117ebc4e2894a3185f684d1a7712993cb09b6b4f
|
