indomee 0.1.1

Python package for evaluation of retrieval-augmented generation (RAG) models

Indomee

Indomee is a Python package designed to simplify the evaluation of retrieval-augmented generation (RAG) models and other retrieval-based systems. With indomee, you can compute common evaluation metrics like recall and mean reciprocal rank (MRR) at various levels of k, all through a straightforward API. Additionally, indomee provides tools for statistical analysis, including t-testing, bootstrapping, and confidence interval (CI) calculations.

---

Features

• Compute Evaluation Metrics: Easily calculate metrics such as recall and mean reciprocal rank.
• Flexible k-Level Analysis: Apply metrics at different levels of k simultaneously.
• Statistical Analysis Tools: Perform t-tests, bootstrapping, and CI calculations effortlessly.
• Configurable with Simple Files: Use a single configuration file to control and customize your evaluations.
• Streamlined Evaluation Code: Reduce the amount of custom code you need to write for evaluation.

Installation

To install indomee, simply use pip:

pip install indomee