skills.rest
Nuwanda04
Nuwanda04COMMUNITY
Explore all skills by this author →
GitHub

RAG Architect

Designs and recommends components for RAG pipelines.

Updated Feb 16, 2026
Search Tags:#information retrieval#llm#rag#vector database#pipeline design#embedding models
One-click install
npx skills add https://github.com/Nuwanda04/Ballen-Fisk --skill rag-architect-nuwanda04
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG Architect
Source: https://github.com/Nuwanda04/Ballen-Fisk/tree/main/.cursor/skills/rag-architect
Command: npx skills add https://github.com/Nuwanda04/Ballen-Fisk --skill rag-architect-nuwanda04

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive toolkit and knowledge base to design, implement, and optimize Retrieval-Augmented Generation (RAG) systems, addressing the complexities of building accurate and scalable AI-powered information retrieval.

Core Features & Use Cases

  • Component Selection: Recommends optimal chunking strategies, embedding models, and vector databases based on project requirements.
  • Pipeline Design: Guides users through retrieval, reranking, and evaluation framework setup.
  • Best Practices & Pitfalls: Offers insights into common challenges and production-ready patterns.
  • Use Case: A developer needs to build a RAG system for customer support documentation. This Skill helps them choose the right chunking method for technical articles, select an embedding model that balances accuracy and cost, and set up an evaluation framework to measure performance.

Quick Start

Design a RAG pipeline for a medium-sized technical documentation corpus with interactive latency requirements.

Frequently Asked Questions about RAG Architect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a production-grade RAG pipeline for technical documentation?▼

Designing a production-grade RAG pipeline involves analyzing document types, scale, latency, and budget to select optimal chunking strategies, embedding models, and vector databases. This approach provides configuration templates and architecture diagrams for implementation.

What is the best way to choose an embedding model for a RAG system?▼

Choosing an embedding model for a RAG system requires balancing accuracy and cost against your specific project requirements. Evaluating document types and latency constraints helps recommend the optimal embedding model for your pipeline.

How do I set up an evaluation framework for Retrieval-Augmented Generation?▼

Setting up an evaluation framework for Retrieval-Augmented Generation involves configuring pipeline design components like retrieval methods and reranking. This guides you through measuring performance to ensure accurate and scalable information retrieval.

Can I use this RAG pipeline design approach for medium-sized corpora with interactive latency?▼

Yes, you can design a RAG pipeline for medium-sized corpora with interactive latency requirements. The process analyzes your specific scale and latency constraints to select appropriate chunking strategies and vector databases.

What chunking strategies should I use for customer support documentation in a RAG pipeline?▼

For customer support documentation in a RAG pipeline, selecting chunking strategies depends on analyzing document types and structure. Optimal chunking ensures the embedding models and retrieval methods can accurately process technical articles.

Why does my RAG pipeline retrieval return irrelevant information?▼

RAG pipeline retrieval returning irrelevant information often stems from suboptimal chunking strategies or mismatched embedding models. Implementing reranking and an evaluation framework helps identify common pitfalls and optimize retrieval methods.

Related Skills

Explore More Software Engineering Skills→
floflo777floflo777
33

rag-eval

Evaluate RAG systems using retrieval, generation, and latency metrics.

Community
Intermediate
Patasse97Patasse97

rag-architect

Design complete RAG pipelines with chunking, embeddings, vector databases, retrieval, reranking, and evaluation.

Community
Advanced
yusufcmgyusufcmg
1

rag-implementation

Implement Retrieval-Augmented Generation systems with vector databases and semantic search.

Community
Advanced
LuisSambranoLuisSambrano
7

rag-mastery

Develop and optimize Retrieval-Augmented Generation systems with chunking, embedding models, vector stores, and retrieval strategies.

Community
Advanced