skills.rest
4lerman
4lermanCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design and optimize RAG pipelines for knowledge retrieval.

Updated Apr 2, 2026
Search Tags:#knowledge retrieval#rag#vector database#reranking#evaluation framework#retrieval augmented generation#embedding model#retrieval strategy#document chunking
One-click install
npx skills add https://github.com/4lerman/text_evaluator --skill rag-architect-4lerman
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/4lerman/text_evaluator/tree/main/.agents/skills/engineering-advanced-skills/rag-architect
Command: npx skills add https://github.com/4lerman/text_evaluator --skill rag-architect-4lerman

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill unit provides the knowledge and tools to design, implement, and optimize production-grade RAG (Retrieval-Augmented Generation) pipelines, addressing the challenges of building scalable, efficient, and accurate retrieval systems.

Core Features & Use Cases

  • Document Chunking: Offers various chunking strategies (fixed-size, sentence-based, paragraph-based, semantic) to split documents into manageable units for processing.
  • Embedding Model Selection: Recommends suitable embedding models based on the document type and quality/cost trade-offs.
  • Vector Database Selection: Provides recommendations for vector databases like Pinecone, Weaviate, Qdrant, and Chroma based on system scale and requirements.
  • Retrieval Strategies: Includes dense, sparse, and hybrid retrieval strategies for different scenarios.
  • Reranking: Implements reranking using cross-encoders to improve precision.
  • Evaluation Frameworks: Utilizes comprehensive evaluation metrics like precision, recall, MRR, and NDCG.
  • Production Patterns: Offers caching strategies, streaming retrieval, fallback mechanisms, and cost optimization techniques.
  • Security and Safety: Implements content filtering, query safety, and response safety to ensure safe and reliable operations.

Quick Start

Run the rag-architect skill to generate a recommendation for a RAG pipeline design based on your specific requirements.

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 efficient knowledge retrieval?▼

To design a RAG pipeline, implement document chunking, select embedding models, choose a vector database, and define retrieval strategies. This provides specific recommendations for building accurate and scalable retrieval systems.

What are the best chunking strategies for processing PDF documents?▼

The best chunking strategies for PDF documents include fixed-size, sentence-based, paragraph-based, and semantic chunking. These strategies split documents into manageable units for processing using Python libraries like pypdf and pdfplumber.

How do I choose between Pinecone, Weaviate, Qdrant, and Chroma for vector databases?▼

Choosing between Pinecone, Weaviate, Qdrant, and Chroma depends on your system scale and requirements. This provides tailored vector database recommendations to balance performance, system scale, and operational needs for retrieval systems.

When should I use hybrid retrieval and cross-encoders for reranking?▼

You should use hybrid retrieval combining dense and sparse strategies for different scenarios, followed by cross-encoders for reranking. This approach significantly improves retrieval precision and ensures accurate knowledge retrieval.

What evaluation metrics do I need to measure RAG pipeline accuracy?▼

You need evaluation metrics like precision, recall, MRR, and NDCG to measure RAG pipeline accuracy. This framework provides comprehensive evaluation metrics to assess and optimize the performance of your retrieval systems.

Can I use Python to implement production patterns and cost optimization for RAG systems?▼

Yes, you can use Python to implement production patterns and cost optimization for RAG systems. This includes caching strategies, streaming retrieval, fallback mechanisms, and content filtering to ensure safe and reliable operations.

Related Skills

Explore More Software Engineering Skills→
zjy-devzjy-dev
2

pdf

Extract text, fill forms, and manipulate PDFs using Python libraries.

Community
Advanced
whiteboardevwhiteboardev

memory-retrieve

Classify user queries to retrieve memories via recent, keyword, or semantic search.

Community
Advanced
agentsopeagentsope
287

agentsop-reranker-stage

Rerank bi-encoder candidate sets with cross-encoders to improve RAG precision.

Community
Advanced
leonardoteodorooleonardoteodoroo

similarity-search-patterns

Implement similarity search patterns for vector embeddings with distance metrics and index templates.

Community
Advanced