skills.rest
xleliberty
xlelibertyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-architect

Design and optimize Retrieval-Augmented Generation pipelines for document corpora.

Updated Nov 3, 2016
Search Tags:#embeddings#rag#retrieval#vector search#pipeline design#ai architecture
One-click install
npx skills add https://github.com/xleliberty/mydotfiles --skill rag-architect-xleliberty
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/xleliberty/mydotfiles/tree/main/.config/.claude/plugins/cache/claude-code-skills/engineering-advanced-skills/2.1.2/rag-architect
Command: npx skills add https://github.com/xleliberty/mydotfiles --skill rag-architect-xleliberty

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the complexity of building Retrieval-Augmented Generation (RAG) systems by providing a structured framework for chunking, embedding, retrieval, and evaluation, ensuring your AI applications are accurate and scalable.

Core Features & Use Cases

  • Pipeline Design: Expert guidance on selecting embedding models, vector databases, and retrieval strategies (dense, sparse, hybrid).
  • Optimization Tools: Includes built-in scripts to analyze document corpora and recommend the most effective chunking strategy.
  • Use Case: If you are building a technical support bot, use this Skill to determine whether to use semantic chunking for your documentation and how to configure a hybrid retrieval strategy to improve answer accuracy.

Quick Start

Use the rag-architect skill to analyze the documents in the ./docs directory and recommend the optimal chunking strategy.

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 RAG pipeline for diverse document corpora?▼

To design a production RAG pipeline, evaluate and select appropriate chunking strategies, embedding models, and vector database architectures based on your specific scale and latency requirements.

What is the best chunking strategy for my RAG system's document corpus?▼

The best chunking strategy is determined by analyzing your document corpus using built-in scripts that recommend the most effective approach, such as semantic chunking for technical documentation.

Can I use a hybrid retrieval strategy to improve RAG answer accuracy?▼

Yes, you can configure a hybrid retrieval strategy that combines dense and sparse retrieval methods to improve answer accuracy and relevance in your RAG pipeline.

How do I evaluate faithfulness and relevance in Retrieval-Augmented Generation?▼

You evaluate faithfulness and relevance by implementing comprehensive evaluation frameworks within your RAG pipeline, ensuring generated responses meet high accuracy standards for your specific use case.

Does rag-architect recommend the right embedding models and vector databases for my scale?▼

The rag-architect skill provides expert guidance on selecting embedding models and vector database architectures tailored to your specific scale and latency requirements for production RAG systems.

Related Skills

Explore More Software Engineering Skills→
emilneuraz-aiemilneuraz-ai

embedding-strategies

Identify and compare embedding models to optimize semantic search performance for RAG pipelines and multilingual data.

Community
Advanced
MantisWareMantisWare

eval-rag

Evaluate RAG pipelines with retrieval and generation metrics and bottleneck analysis.

Community
Advanced
rizaldiemrizaldiem

rag

Build retrieval-augmented generation pipelines with vector databases and document chunking.

Community
Advanced
sixscripts-aisixscripts-ai

rag-engineer

Optimize retrieval-augmented generation pipelines for LLM-powered tasks.

Community
Advanced