skills.rest
moshesham
mosheshamCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design and optimize production-grade RAG pipelines for document-heavy domains.

Updated Nov 28, 2025
Search Tags:#embeddings#rag#evaluation#pipelines#guardrails#vector-databases#retrieval-augmented-generation
One-click install
npx skills add https://github.com/moshesham/Economic-Dashboard-API --skill rag-architect-moshesham
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/moshesham/Economic-Dashboard-API/tree/main/.github/skills/rag-architect
Command: npx skills add https://github.com/moshesham/Economic-Dashboard-API --skill rag-architect-moshesham

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Designs, builds, and optimizes production-grade Retrieval-Augmented Generation (RAG) pipelines to deliver accurate, source-backed answers at scale.

Core Features & Use Cases

  • Document processing and chunking strategies that preserve context and reduce token waste.
  • Embedding model guidance, vector database selection, retrieval, and reranking to improve answer quality and traceability.
  • Evaluation frameworks, guardrails, and cost-aware deployment patterns for reliable production systems.
  • Use Case: Build a knowledge-base assistant that answers internal policy and technical questions from large document corpora with auditable sources.

Quick Start

Configure and deploy a RAG pipeline for a corporate document corpus and run a quick evaluation.

Frequently Asked Questions about rag-architect

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

FAQPage Schema
How do I build a RAG pipeline for internal knowledge bases?▼

To build a RAG pipeline, you configure document chunking strategies, select embedding models, integrate vector databases, and establish retrieval and reranking pipelines to generate source-backed answers from internal corpora.

What's the best way to choose chunking strategies for large document corpora?▼

Choosing chunking strategies involves selecting methods that preserve document context and reduce token waste, ensuring accurate retrieval across large manuals or research corpora without losing critical structural information.

Does this approach support evaluation metrics and safety guardrails for production RAG?▼

Yes, production RAG systems require evaluation frameworks to measure answer quality and safety guardrails to ensure reliable, traceable outputs across internal knowledge bases at scale.

How do I improve retrieval and reranking pipelines for accurate answer generation?▼

Improve retrieval and reranking pipelines by optimizing embedding model selection and vector database integration, which increases answer quality and traceability for document-heavy domains requiring accurate summarization.

Can I use RAG pipelines for summarization across research corpora?▼

Yes, RAG pipelines support accurate retrieval and summarization across research corpora, targeting document-heavy domains that require scalable answer generation from large internal manuals and technical documents.

What are the limitations of retrieval-augmented generation without proper context management?▼

Without proper context management, retrieval-augmented generation suffers from degraded answer accuracy and increased token waste, making it difficult to trace sources or maintain reliable outputs across large document corpora.

Related Skills

Explore More Software Engineering Skills→
iterationlayeriterationlayer
2

convert-document-for-rag-ingestion

Convert PDFs and web pages into clean Markdown for RAG ingestion.

Official
Intermediate
Veloxia-agencyVeloxia-agency

rag-architect

Design production RAG pipelines with chunking, embeddings, and vector databases.

Community
Advanced
peterlianpipeterlianpi
1

Zolai RAG Builder

Create document embeddings and index them in a vector store for retrieval-augmented generation.

Community
Advanced
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

rag-implementation

Build retrieval-augmented generation pipelines with vector databases and embedding models.

Community
Advanced