skills.rest
devCharuzu
devCharuzuCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design and deploy production-grade RAG pipelines with chunking, embeddings, vector stores, and evaluation.

Updated Apr 16, 2026
Search Tags:#rag#evaluation#knowledge-management#chunking#vector-search#retrieval-augmented-generation#embedding-models
One-click install
npx skills add https://github.com/devCharuzu/philfida-taskmanage --skill rag-architect-devcharuzu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/devCharuzu/philfida-taskmanage/tree/main/.windsurf/skills/rag-architect
Command: npx skills add https://github.com/devCharuzu/philfida-taskmanage --skill rag-architect-devcharuzu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

RAG architectures are complex and require careful design across chunking, embeddings, vector storage, and evaluation; this skill provides comprehensive guidance to design, implement, and optimize production-grade RAG pipelines.

Core Features & Use Cases

  • Document Processing & Chunking Strategies
  • Embedding Model Selection
  • Vector Database & Retrieval Strategies
  • Query Transformation & Context Window Optimization
  • Evaluation Frameworks & Production Patterns
  • Guardrails & Safety
  • Cost & Maintenance Guidance

Quick Start

Design and deploy a production-grade RAG pipeline for a documents corpus with the right chunking, embedding model, vector store, and evaluation framework.

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 pipeline for a documents corpus?▼

To design a production-grade RAG pipeline, select the right chunking strategies, embedding models, and vector databases, then implement a measurable evaluation framework for end-to-end retrieval and generation across structured and unstructured content.

What is the best way to choose chunking strategies and embedding models for retrieval-augmented generation?▼

The best way to choose chunking strategies and embedding models is by matching them to your content structure and evaluating retrieval accuracy through a measurable evaluation framework to optimize context window usage.

How does query transformation and context window optimization work in RAG architectures?▼

Query transformation and context window optimization refine user queries and manage retrieved context length to maximize relevance, ensuring the vector store returns only the necessary data for generation.

Can I use this RAG architecture approach for both structured and unstructured content?▼

Yes, this RAG architecture approach applies to a wide range of production workloads, processing both structured and unstructured content through modular components and configurable vector databases.

What evaluation frameworks and guardrails are needed for a production RAG system?▼

Production RAG systems require evaluation frameworks to measure retrieval accuracy and generation quality, alongside guardrails and safety mechanisms to control outputs and manage ongoing maintenance costs.

Related Skills

Explore More Software Engineering Skills→
2nth-ai2nth-ai
1

data/engineering/liteparse

Parse unstructured documents into clean text and structured JSON.

Official
Basic
Miosa-osaMiosa-osa
226

eval-rag

Evaluate RAG pipelines with retrieval and generation metrics plus bottleneck analysis.

Official
Advanced
constructive-ioconstructive-io

pgvector-rag

Create and manage pgvector databases in PostgreSQL with Ollama for RAG pipelines.

Official
Advanced
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced