skills.rest
tapanshah
tapanshahCOMMUNITY
Explore all skills by this author →
GitHub

RAG Architect

Design RAG pipeline components including chunking, embedding models, and vector databases.

Updated Mar 7, 2026
Search Tags:#llm#rag#vector database#retrieval#pipeline design#embedding
One-click install
npx skills add https://github.com/tapanshah/Claude-Skills --skill rag-architect-tapanshah
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG Architect
Source: https://github.com/tapanshah/Claude-Skills/tree/main/engineering/rag-architect
Command: npx skills add https://github.com/tapanshah/Claude-Skills --skill rag-architect-tapanshah

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides comprehensive tools and knowledge for designing, implementing, and optimizing production-grade RAG pipelines, addressing the complexities of retrieval and generation.

Core Features & Use Cases

  • End-to-End Design: Covers chunking, embedding, vector DBs, retrieval, reranking, and evaluation.
  • Component Selection: Recommends optimal models and databases based on requirements.
  • Production Patterns: Offers best practices for caching, streaming, and fallbacks.
  • Use Case: A product manager needs to build a Q&A system over internal documentation. This Skill guides them through selecting the right chunking strategy, embedding model, and vector database to ensure accurate and efficient retrieval.

Quick Start

Use the RAG Architect skill to design a RAG pipeline for technical documentation with high accuracy 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 high accuracy requirements?▼

To design a production-grade RAG pipeline, select optimal chunking strategies, embedding models, and vector databases based on your requirements. Include retrieval methods, reranking, and evaluation frameworks to ensure high accuracy and efficient retrieval for production deployment.

What are the best chunking strategies and embedding models for a RAG pipeline?▼

The best chunking strategies and embedding models depend on your specific data and accuracy needs. Evaluating different configurations allows you to balance retrieval efficiency and generation quality, providing tailored recommendations with pros, cons, and cost estimates for your RAG pipeline.

How does reranking improve retrieval in a RAG pipeline?▼

Reranking improves retrieval in a RAG pipeline by reordering retrieved documents to prioritize the most relevant context for the LLM. Integrating reranking methods enhances generation accuracy and optimizes the overall performance of the retrieval-augmented generation process.

Can I get cost estimates and configuration templates for vector databases in RAG?▼

Yes, you can get cost estimates and configuration templates for vector databases in RAG. The design process provides rationale, pros, cons, and cost estimates alongside configuration templates to guide your production deployment of the retrieval pipeline.

What evaluation frameworks should I use for a Retrieval-Augmented Generation system?▼

Evaluation frameworks for a Retrieval-Augmented Generation system measure retrieval accuracy and generation quality. Selecting the right evaluation framework is crucial for validating pipeline performance, testing chunking strategies, and ensuring the RAG system meets production standards.

When should I implement caching and streaming fallbacks in my RAG pipeline?▼

You should implement caching and streaming fallbacks in your RAG pipeline when deploying to production environments. These production patterns offer best practices for maintaining system reliability, optimizing performance, and managing fallback behavior during retrieval and generation.

Related Skills

Explore More Software Engineering Skills→
haxlyshaxlys

embedding-strategies

Select embedding models and configurations for semantic search pipelines.

Community
Advanced
Miosa-osaMiosa-osa
226

eval-rag

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

Official
Advanced
EndUser123EndUser123

ai-nvidia

Route requests to 200+ NVIDIA NIM models via an OpenAI-compatible API.

Community
Advanced
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

rag-implementation

Build retrieval-augmented generation pipelines with vector databases and embedding models.

Community
Advanced