rag-architecture

Installation
SKILL.md

RAG Architecture

RAG is search + prompt, not magic. The model can only answer from what retrieval puts in the context window, so 80% of RAG quality is the retrieval system and 20% is the prompt. Most "the LLM hallucinated" bugs are actually "retrieval returned garbage and the model dutifully summarized it." Build the pipeline so the right chunks land in context with citations, and tell the model to say "I don't know" when they don't. This skill is the concrete playbook: numbers, methods, tables, and the failure modes that cost precision.

1. The pipeline — eight stages, two phases

Index time (offline, batch): ingest → chunk → embed → index. Query time (online, latency-bound): retrieve → rerank → assemble → generate.

Stage Job Latency budget (typical)
Ingest Parse source → clean text + metadata offline
Chunk Split into retrievable units offline
Embed Text → vector offline (docs), ~10–50ms (query)
Index Store vectors + metadata for ANN offline
Retrieve top-k candidates (dense + sparse) 10–50ms
Rerank Cross-encoder reorders k→n 50–300ms
Assemble Select, dedup, order, budget, cite <5ms
Generate LLM answers from context 1–10s (dominates)

Do treat each stage as independently measurable and swappable. Don't optimize generation prompts before you've measured retrieval recall — you're polishing the 20%.

Installs
2
GitHub Stars
1
First Seen
Jun 9, 2026
rag-architecture — jpoindexter/design-and-ai-skills