Ragrank 🎯

Ragrank is a user-friendly Python library created to make evaluating Retrieval Augmented Generation (RAG) models easier 🔥.

With Ragrank, you can:

• Evaluate, monitor, and troubleshoot LLM applications 🛠

• Plug-and-use 5+ LLM-evaluated metrics, most with research backing 💡

• Custom metrics are simple to personalize and create 📐

• Define evaluation datasets in Python code 📦

Key Features:

• Easy to Use: Designed for developers new to RAG models 📘

• Customizable: Tailor the evaluation process to your data and metrics 🛠️

• Open Source: The source code is publically available 🌟

---

🚀 Quick Start

Master the basics of ragrank with a strong step. Evaluate RAG pipelines, generate test sets, and set up online monitoring for RAG apps — all with a few lines of code.

🪩 Core concepts

Discover the main ideas and concepts of ragrank. Learn how to check how well models work using the tools in the library with fundamentals.

🛠 The Evaluation

Head over to the comprehensive evaluation with ragrank. Explore the various aspects of evaluating Language Model (LLM) and Retrieval Augmented Generation (RAG) models.

📏 Metrics

Discover different metrics and create custom ones using ragrank. Dive into a variety of measurement methods to analyze and improve the performance of your models effectively.