skills.rest
Tonybleything76
Tonybleything76COMMUNITY
Explore all skills by this author →
GitHub

RAG Architect - POWERFUL

Design RAG pipeline components with chunking, embeddings, and vector databases.

Updated Mar 4, 2026
Search Tags:#llm#rag#vector database#retrieval#pipeline design#embedding
One-click install
npx skills add https://github.com/Tonybleything76/more-claude-skills --skill rag-architect-powerful-tonybleything76
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RAG Architect - POWERFUL
Source: https://github.com/Tonybleything76/more-claude-skills/tree/main/engineering/rag-architect
Command: npx skills add https://github.com/Tonybleything76/more-claude-skills --skill rag-architect-powerful-tonybleything76

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, enabling the creation of scalable, efficient, and accurate retrieval systems.

Core Features & Use Cases

  • Document Processing & Chunking: Explore various strategies like fixed-size, sentence-based, paragraph-based, and semantic chunking.
  • Embedding Model Selection: Guidance on choosing models based on dimensions, speed, quality, and domain.
  • Vector Database Comparison: Detailed pros and cons of Pinecone, Weaviate, Qdrant, Chroma, and pgvector.
  • Retrieval Strategies: Understand dense, sparse, hybrid retrieval, and reranking techniques.
  • Evaluation Frameworks: Implement metrics for faithfulness, relevance, precision, recall, and end-to-end quality.
  • Use Case: Design a RAG system for a large enterprise knowledge base, ensuring high accuracy and low latency by selecting optimal chunking, embedding, and retrieval components.

Quick Start

Design a RAG pipeline for a technical documentation use case with high accuracy requirements.

Frequently Asked Questions about RAG Architect - POWERFUL

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a RAG pipeline for a large enterprise knowledge base?▼

Designing a RAG pipeline for an enterprise knowledge base requires analyzing document type, scale, latency, and budget to select tailored chunking, embedding, vector database, and retrieval configurations.

What is the best way to choose an embedding model for retrieval-augmented generation?▼

Choosing an embedding model for retrieval-augmented generation involves evaluating model dimensions, speed, quality, and domain specificity to match your document processing and accuracy requirements.

How does chunking strategy affect RAG pipeline accuracy?▼

Chunking strategy affects RAG pipeline accuracy by determining how source documents are segmented, with options including fixed-size, sentence-based, paragraph-based, and semantic chunking to optimize retrieval relevance.

Pinecone vs Weaviate vs Qdrant: which vector database fits my RAG architecture?▼

Comparing Pinecone, Weaviate, Qdrant, Chroma, and pgvector for your RAG architecture involves weighing detailed pros and cons regarding scale, latency, and budget to find the optimal vector database.

How do I evaluate RAG pipeline performance and retrieval quality?▼

Evaluating RAG pipeline performance requires implementing an evaluation framework that measures metrics for faithfulness, relevance, precision, recall, and overall end-to-end quality.

When should I use hybrid retrieval and reranking in a RAG system?▼

Hybrid retrieval and reranking in a RAG system should be used when you need to combine dense and sparse retrieval methods to improve search accuracy beyond standard single-method retrieval approaches.

Related Skills

Explore More Software Engineering Skills→
patricio0312revpatricio0312rev
5

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets for embeddings.

Community
Advanced
MrOwaisAbdullahMrOwaisAbdullah
1

chatbot-widget-creator

Create a React/TypeScript chat widget with SSE streaming and RAG retrieval.

Community
Advanced
zilliztechzilliztech
3

multi-hop-rag

Decompose questions, retrieve across documents, and synthesize cited answers.

Official
Advanced
VYRE-StudiosVYRE-Studios

peft-fine-tuning

Fine-tune 7B to 70B language models with LoRA or QLoRA adapters.

Official
Advanced