What is the RAG Architect skill?

It is a specialized capability for Claude Code that provides deep expertise in designing, building, and optimizing Retrieval-Augmented Generation systems.

How does it handle large documents?

It offers various chunking strategies—including recursive and semantic chunking—to ensure document context is preserved while fitting within LLM context windows.

Can it improve the accuracy of my AI's answers?

Absolutely, by implementing advanced retrieval strategies like reranking and hybrid search, and using evaluation frameworks like RAGAS to measure faithfulness.

Does this skill help with vector database selection?

Yes, it provides detailed comparisons and implementation guidance for popular vector databases including Pinecone, Weaviate, Qdrant, and pgvector.

RAG Architect

Name: RAG Architect
Author: zhangzhang-111-i

byzhangzhang-111-i

0•

Ciencia de Datos y ML

Designs and optimizes production-grade Retrieval-Augmented Generation (RAG) pipelines with advanced chunking, retrieval, and evaluation strategies.

The RAG Architect skill transforms Claude into a specialized consultant for building high-performance retrieval systems, covering the entire lifecycle from document ingestion to production monitoring. It provides deep expertise in sophisticated chunking methods, embedding model selection, and the nuances of various vector databases like Pinecone and Weaviate. By implementing advanced retrieval patterns such as HyDE, hybrid search, and reranking, this skill ensures your AI applications deliver accurate, grounded, and cost-effective responses even when working with massive, complex datasets.

Características Principales

01Hybrid retrieval and reranking strategy implementation

020 GitHub stars

03Comprehensive RAG evaluation using frameworks like RAGAS

04Vector database selection and optimization (Pinecone, Weaviate, pgvector)

05Cost optimization and context window management techniques

06Advanced document chunking (semantic, recursive, and hierarchical)

Casos de Uso

01Building an enterprise-grade knowledge base with multi-source document retrieval

02Optimizing existing RAG systems for better accuracy and reduced latency

03Implementing domain-specific search for technical or medical documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add zhangzhang-111-i/claude-skills111 rag-architect

For use in Claude.ai and ChatGPT

Características Principales

01Hybrid retrieval and reranking strategy implementation

020 GitHub stars

03Comprehensive RAG evaluation using frameworks like RAGAS

04Vector database selection and optimization (Pinecone, Weaviate, pgvector)

05Cost optimization and context window management techniques

06Advanced document chunking (semantic, recursive, and hierarchical)

Casos de Uso

01Building an enterprise-grade knowledge base with multi-source document retrieval

02Optimizing existing RAG systems for better accuracy and reduced latency

03Implementing domain-specific search for technical or medical documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add zhangzhang-111-i/claude-skills111 rag-architect

For use in Claude.ai and ChatGPT