skills.rest
amanhsn
amanhsnCOMMUNITY
Explore all skills by this author →
GitHub

RAG Architect

Design and optimize production-grade RAG pipelines with retrieval and evaluation strategies.

Updated Feb 27, 2026
Search Tags:#information retrieval#llm#rag#vector database#pipeline design#embedding models
One-click install
npx skills add https://github.com/amanhsn/flyerbuild --skill rag-architect-amanhsn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG Architect
Source: https://github.com/amanhsn/flyerbuild/tree/main/.cursor/skills/rag-architect
Command: npx skills add https://github.com/amanhsn/flyerbuild --skill rag-architect-amanhsn

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the complexity of designing, implementing, and optimizing Retrieval-Augmented Generation (RAG) pipelines, enabling users to build accurate and scalable AI-powered information retrieval systems.

Core Features & Use Cases

  • Comprehensive Guidance: Covers all aspects of RAG, from document chunking and embedding models to vector databases, retrieval strategies, and evaluation frameworks.
  • Best Practice Recommendations: Provides insights into common pitfalls, cost optimization, and production patterns.
  • Use Case: A developer needs to build a chatbot that answers questions based on a large internal knowledge base. This Skill guides them through selecting the right chunking strategy for their technical documents, choosing an appropriate embedding model, setting up a vector database, and implementing an evaluation process to ensure accuracy.

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 build a production-grade RAG pipeline for technical documentation?▼

To build a production-grade RAG pipeline, you need to process documents, select appropriate embedding models, configure a vector database, and implement effective retrieval strategies to ensure high accuracy.

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

Choosing an embedding model for a RAG pipeline depends on your document structure and accuracy requirements, balancing model size and latency against the semantic depth needed for your specific information retrieval tasks.

How does document chunking affect RAG retrieval accuracy?▼

Document chunking directly impacts RAG retrieval accuracy by determining the semantic boundaries of text segments, where properly sized chunks maintain context and prevent vector database searches from returning incomplete or irrelevant information.

Can I optimize RAG pipelines for both cost and high accuracy?▼

You can optimize RAG pipelines for both cost and high accuracy by applying production patterns like query transformation and context optimization, which reduce unnecessary LLM calls while maintaining strict evaluation frameworks.

When do I need query transformation in my RAG architecture?▼

You need query transformation in your RAG architecture when user queries are ambiguous or complex, allowing the system to rewrite inputs before vector database retrieval to improve the relevance of fetched context.

How do I evaluate the performance of a RAG pipeline?▼

You evaluate the performance of a RAG pipeline by implementing specific evaluation frameworks that measure retrieval accuracy and generation quality, ensuring the information retrieval system meets production-grade standards before deployment.

Related Skills

Explore More Software Engineering Skills→
Himanshu040604Himanshu040604

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Advanced
JKhyroJKhyro

serving-llms-vllm

Serve large language models with OpenAI-compatible endpoints and high-throughput inference.

Community
Advanced
fabioc-alohafabioc-aloha
1

RAG Architecture Skill

Build RAG pipelines with document processing, chunking, embedding, and vector storage.

Community
Advanced
bugrabilgebugrabilge
10

rag-engineer

Design and optimize RAG systems for LLM applications.

Community
Advanced