skills.rest
camelranchentertainment
camelranchentertainmentCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design production-grade retrieval augmented generation systems with chunking, embeddings, and vector stores.

1|Updated Jan 19, 2026
Search Tags:#architecture#monitoring#rag#embedding#vector-search#retrieval-augmented#hybrid-search
One-click install
npx skills add https://github.com/camelranchentertainment/Booking-Platform --skill rag-architect-camelranchentertainment
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/camelranchentertainment/Booking-Platform/tree/main/.claude/skills/rag-architect
Command: npx skills add https://github.com/camelranchentertainment/Booking-Platform --skill rag-architect-camelranchentertainment

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

RAG-Architect addresses the complexity of building scalable retrieval augmented generation systems by providing a comprehensive blueprint that coordinates data ingestion, document chunking, embedding strategies, vector store design, retrieval pipelines, reranking, and evaluation.

Core Features & Use Cases

  • Comprehensive architecture blueprint covering ingestion, embedding, indexing, retrieval, reranking, and monitoring for RAG workloads.
  • Supports multi-tenant and metadata-driven filtering, latency budgeting, and observability.
  • Use cases include knowledge bases, knowledge-grounded assistants, and semantic search across large document repositories.

Quick Start

Provide a ready-to-deploy RAG architecture blueprint for a medium-scale knowledge base, including recommended chunking, embeddings, indexing, and evaluation steps.

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 architecture for a large knowledge base?▼

To design a production-grade RAG architecture, blueprint the pipeline from document chunking and embedding strategies to vector store indexing and retrieval. Include multi-tenant metadata filtering, latency budgeting, and monitoring checkpoints to ensure scalable knowledge base deployment.

What's the best way to handle document chunking and embeddings for retrieval augmented generation?▼

Handling document chunking and embeddings for retrieval augmented generation requires coordinating data ingestion with indexing strategies. Apply architectural guardrails like idempotent ingestion to maintain retrieval quality and ensure context augmentation across large document repositories.

Does this RAG architecture support multi-tenant metadata filtering and hybrid search?▼

Yes, this RAG architecture supports multi-tenant metadata filtering and hybrid search. It enforces end-to-end architectural guardrails and observability, enabling semantic search and knowledge-grounded assistants to scale securely across distinct tenants.

How do I add evaluation checkpoints and monitoring to a RAG pipeline?▼

Add evaluation checkpoints and monitoring to a RAG pipeline by integrating observability throughout the retrieval and reranking stages. This enforces latency budgeting and tracks retrieval quality, ensuring the context augmentation process meets production deployment standards.

When do I need architectural guardrails for idempotent ingestion in vector search systems?▼

You need architectural guardrails for idempotent ingestion in vector search systems when building scalable knowledge bases. Idempotent ingestion prevents duplicate document embeddings, maintaining retrieval quality and ensuring consistent semantic search results during continuous data updates.

Related Skills

Explore More Software Engineering Skills→
NelkitNelkit
1

chromadb-embed

Embed text data into ChromaDB with deterministic IDs and chunking.

Community
Intermediate
hainamchunghainamchung
54

rag-architect

Design and implement Retrieval-Augmented Generation architectures with hybrid search and vector databases.

Community
Advanced
shalevaminshalevamin

rag-architect

Designs and implements RAG systems with chunking, embedding generation, vector stores, hybrid search, reranking, and evaluation.

Community
Advanced
fableindigo-giffableindigo-gif

AgentDB Vector Search

Perform semantic vector search against AgentDB stores with HNSW indexing.

Community
Advanced