skills.rest
dieu-donnee
dieu-donneeCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design retrieval-augmented generation pipelines with hybrid search and reranking.

Updated Jan 9, 2026
Search Tags:#embeddings#rag#reranking#system-design#vector-search#retrieval-augmented-generation#hybrid-search
One-click install
npx skills add https://github.com/dieu-donnee/luxtrax --skill rag-architect-dieu-donnee
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/dieu-donnee/luxtrax/tree/main/.agent/skills/rag-architect
Command: npx skills add https://github.com/dieu-donnee/luxtrax --skill rag-architect-dieu-donnee

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality.

Core Features & Use Cases

  • End-to-end RAG architecture design for document-heavy knowledge bases and knowledge graphs.
  • Hybrid search pipelines combining dense embeddings with keyword methods, along with reranking and evaluation to ensure retrieval quality.
  • Practical patterns for production integration, monitoring, and experimentation with reproducible templates.

Quick Start

Provide a complete RAG blueprint and starter templates to deploy a RAG system in a real-world project.

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 retrieval-augmented generation pipeline for high retrieval latency workloads?▼

Designing a production retrieval-augmented generation pipeline involves balancing embedding quality, vector store choices, and retrieval latency through document chunking, hybrid search, and reranking to ensure optimal retrieval quality.

What is hybrid search and reranking in retrieval-augmented generation systems?▼

Hybrid search in retrieval-augmented generation combines dense embeddings with keyword methods to fetch relevant documents, while reranking evaluates and orders those results to ensure high retrieval quality for the final output.

How do I evaluate retrieval quality and mitigate risks in a RAG system?▼

Evaluating retrieval quality in a RAG system involves explanation-worthy evaluation checkpoints and concrete trade-offs analysis, while risk mitigation requires monitoring the end-to-end pipeline during real-world integration to ensure system reliability.

Does this RAG architecture blueprint support integration with existing document-heavy knowledge bases?▼

Yes, this RAG architecture blueprint provides practical patterns and starter templates for production integration, specifically targeting document-heavy knowledge bases and knowledge graphs with reproducible monitoring workflows.

What are the trade-offs when choosing vector stores and embedding models for a RAG system?▼

Choosing vector stores and embedding models for a RAG system involves concrete trade-offs between embedding quality and retrieval latency, requiring checkpoints to evaluate system performance before deploying to production workloads.

Related Skills

Explore More Software Engineering Skills→
Ikram-AlamIkram-Alam

building-rag-systems

Build RAG systems with semantic chunking, incremental indexing, and filtered retrieval.

Community
Advanced
tankpkgtankpkg
1

@tank/rag-production

Design production RAG pipelines with chunking, retrieval, reranking, and context assembly.

Official
Advanced
devMoezdevMoez
1

qdrant-vector-search

Perform vector similarity search with metadata filtering via the qdrant-client API.

Community
Intermediate
fratilanicofratilanico
7

rag-retrieval-patterns

Configure dense, sparse, and hybrid document retrieval for RAG pipelines.

Community
Advanced