skills.rest
lamb92009
lamb92009COMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Designs and implements Retrieval-Augmented Generation architectures with hybrid search and metadata enrichment for scalable pipelines.

Updated Feb 11, 2026
Search Tags:#embeddings#rag#evaluation#retrieval#chunking#vector-databases
One-click install
npx skills add https://github.com/lamb92009/claude-skills --skill rag-architect-lamb92009
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/lamb92009/claude-skills/tree/main/rag-architect
Command: npx skills add https://github.com/lamb92009/claude-skills --skill rag-architect-lamb92009

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The RAG architecture skill helps teams design and deploy retrieval-augmented generation systems by providing a structured blueprint for integrating vector databases, embedding models, chunking strategies, and evaluation pipelines.

Core Features & Use Cases

  • Design and implement end-to-end RAG pipelines with hybrid search, vector databases, and metadata enrichment.
  • Evaluate retrieval quality with established metrics and monitoring dashboards.
  • Real-world use: knowledge-grounded chatbots, enterprise search, and document QA.

Quick Start

Provision a production-ready RAG pipeline by configuring vector stores, embedding models, and chunking strategies.

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 scalable RAG pipeline for enterprise search?▼

To design a scalable RAG pipeline, integrate vector databases, embedding models, and chunking strategies to build end-to-end ingestion, indexing, and retrieval architectures with metadata enrichment and hybrid search.

What are the best chunking strategies for retrieval-augmented generation?▼

Effective chunking strategies for retrieval-augmented generation segment documents into manageable pieces to optimize embedding models, ensuring accurate vector indexing and high retrieval quality for knowledge-grounded chatbots.

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

Evaluate retrieval quality in a RAG system by applying established evaluation metrics and monitoring dashboards to measure retrieval accuracy, track observability, and assess embedding model performance.

Can I implement multi-tenant pipelines using a RAG architecture?▼

Yes, you can implement multi-tenant pipelines within a RAG architecture by configuring vector stores and metadata enrichment to isolate data, ensuring idempotent ingestion and scalable knowledge base management.

Does a production-grade RAG architecture support hybrid search?▼

Yes, a production-grade RAG architecture supports hybrid search by fusing vector databases with metadata enrichment, allowing knowledge-grounded chatbots and document QA systems to retrieve highly relevant context.

Why do I need idempotent ingestion for vector databases in RAG pipelines?▼

You need idempotent ingestion for vector databases in RAG pipelines to prevent duplicate records during indexing, ensuring enterprise search and document QA systems maintain consistent, scalable retrieval performance.

Related Skills

Explore More Software Engineering Skills→
bethanychamberlainbethanychamberlain
2

rag

Configure LibreChat's RAG pipeline for document ingestion and retrieval.

Community
Advanced
lebsrallebsral
11

ai-monitoring

Monitor AI model performance, drift, and cost in production.

Community
Advanced
oakossoakoss
14

rag-implementer

Implements RAG pipelines with hybrid search and re-ranking.

Official
Advanced
Scheune10-codingScheune10-coding

rag-pipeline-architect

Design end-to-end RAG pipelines with vector DB and chunking strategies.

Community
Advanced