skills.rest
metaarchetech
metaarchetechCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design and optimize RAG pipelines for knowledge retrieval in AI systems.

Updated Apr 12, 2026
Search Tags:#knowledge retrieval#rag#machine learning#ai systems#retrieval-augmented generation
One-click install
npx skills add https://github.com/metaarchetech/metaarchetech.github.io --skill rag-architect-metaarchetech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/metaarchetech/metaarchetech.github.io/tree/main/content/05%20Claude%20Skills/rag-architect
Command: npx skills add https://github.com/metaarchetech/metaarchetech.github.io --skill rag-architect-metaarchetech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sentence-transformers, pgvector, chroma, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenges of designing and optimizing RAG (Retrieval-Augmented Generation) pipelines, ensuring efficient knowledge retrieval and AI system performance.

Core Features & Use Cases

  • RAG Pipeline Design: Offers comprehensive guidance on embedding models, chunking strategies, and vector database choices.
  • Retrieval Strategies: Implements semantic and hybrid retrieval strategies for various knowledge scopes.
  • Evaluation Frameworks: Provides evaluation metrics for faithfulness, relevance, and completeness.
  • Cost Optimization: Focuses on embedding cost, vector database storage, and query optimization.
  • Use Case: Ideal for engineers and data scientists working on knowledge systems, vault knowledge retrieval, and BIM model search optimization.

Quick Start

To start using the rag-architect skill, execute the following command: 'Design a RAG pipeline for a customer BIM model search.'

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 RAG pipeline for knowledge retrieval?▼

To design a RAG pipeline for knowledge retrieval, select appropriate embedding models, define chunking strategies, choose a vector database, and implement semantic or hybrid retrieval strategies tailored to your data scope.

What's the best way to choose a vector database for retrieval-augmented generation?▼

Choosing a vector database for retrieval-augmented generation depends on your storage requirements and query optimization goals, comparing options like pgvector for relational integration or Chroma for lightweight AI systems.

How do embedding models and chunking strategies affect AI systems?▼

Embedding models and chunking strategies directly affect AI systems by determining semantic search accuracy and embedding costs, requiring careful evaluation to balance retrieval relevance with vector database storage efficiency.

Can I evaluate retrieval-augmented generation performance for faithfulness and relevance?▼

You can evaluate retrieval-augmented generation performance using dedicated evaluation frameworks that measure faithfulness, relevance, and completeness metrics to ensure your knowledge retrieval outputs meet system requirements.

Does this RAG pipeline design approach work for BIM model search optimization?▼

This RAG pipeline design approach works for BIM model search optimization by applying semantic and hybrid retrieval strategies to complex knowledge systems, enabling efficient vector search across architectural metadata.

Why does query transformation matter in machine learning retrieval systems?▼

Query transformation matters in machine learning retrieval systems because it optimizes the input queries before embedding, significantly improving the relevance of knowledge retrieved from the vector database.

Related Skills

Explore More Software Engineering Skills→
icyzhicyzh
1

chroma

Manage vector embeddings for retrieval-augmented generation and semantic search.

Community
Intermediate
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate
tranhieutttranhieutt
70

rag-engineer

Designs hybrid semantic and keyword retrieval pipelines for AI knowledge bases.

Community
Advanced
as4584as4584
2

hybrid-search-implementation

Combine vector and keyword search results using RRF, linear combination, or cross-encoder reranking.

Community
Advanced