Reference
RAG evaluation metrics explained →
The cornerstone: the four RAG metrics, and how they tell a retrieval bug from a generation bug.
02 · Pillar
RAG & Retrieval Quality
Why your retrieval-augmented app hallucinates — and how to catch it. Evaluating retrieval-augmented generation end to end: faithfulness, context precision and recall, chunking, reranking, and citation accuracy.
Guide
RAG evaluation guide →
How to evaluate a retrieval-augmented pipeline end to end, metric by metric.
Service
AI product build (service) →
Building RAG-powered products with evaluation wired in from day one.
Tutorial
Evaluate a RAG Pipeline End-to-End with RAGAS →
Score a RAG pipeline end to end with RAGAS metrics.
Tutorial
Detect Hallucinations Automatically in Production Logs →
Detect hallucinations in production by grounding answers against sources.
Guide
Why Your RAG Pipeline Hallucinates and How to Fix It →
The real causes of RAG hallucination and how to fix each one.
Guide
Chunking Strategies for RAG, Compared →
Fixed, sentence, and semantic chunking compared for RAG retrieval quality.
Guide
Hybrid Search vs Pure Vector Search for RAG →
When hybrid search beats pure vector search for RAG, and why.
Guide
RAG vs Fine-Tuning: When to Use Each →
A decision framework for choosing RAG, fine-tuning, or both.
Continue across the library
Need this on your product, not just in theory?
Book a 15-minute call and we'll scope the smallest useful next step.