What RAGAS Doesn’t Tell You — RAG Evaluation From Scratch With Ollama
Last Updated on March 3, 2026 by Editorial Team
Author(s): Vikram Bhat
Originally published on Towards AI.
Evaluating a RAG Pipeline From Scratch — No RAGAS, No OpenAI, Fully Local
How to build a reusable RAG evaluator using Ollama and LLM-as-judge that actually tells you where your pipeline breaks
This article provides a detailed guide on building a reusable RAG evaluator using Ollama and LLM-as-judge, addressing the common issues faced by RAG practitioners, particularly focusing on the importance of measurement in evaluating RAG pipelines. It highlights various metrics that should be implemented to ensure effective evaluation, discusses the components of the RAG system, and offers coded examples while emphasizing the significance of layer-specific metrics in pinpointing issues within the RAG process. The author also hints at future parts of the series, which will delve deeper into advanced evaluation techniques and statistical methods for comparing different retrieval strategies.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
