skills.rest
roanbrasil
roanbrasilCOMMUNITY
Explore all skills by this author →
Website𝕏@roanbrasilGitHub

rag-production

Build RAG pipelines with hybrid retrieval, reranking, and RAGAS evaluation.

5|1|Updated Jun 17, 2026
Search Tags:#rag#reranking#embedding#vector-search#retrieval-augmented-generation#ragas#document-chunking
One-click install
npx skills add https://github.com/roanbrasil/engineer-grade-agent-skills --skill rag-production
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-production
Source: https://github.com/roanbrasil/engineer-grade-agent-skills/tree/main/skills/rag-production
Command: npx skills add https://github.com/roanbrasil/engineer-grade-agent-skills --skill rag-production

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the common failures of RAG pipelines that return irrelevant results, hallucinate answers, incur unnecessary embedding costs, or cannot scale to production workloads, ensuring reliable, accurate retrieval-augmented generation for proprietary data.

Core Features & Use Cases

  • End-to-End Pipeline Coverage: Guides every stage from document loading, chunking, embedding, retrieval, reranking, augmentation to production evaluation.
  • Optimized Document Processing: Includes best practices for loading PDF, HTML, DOCX and Markdown files with full metadata preservation, plus incremental loading to avoid re-embedding unchanged documents.
  • Production-Grade Retrieval: Implements hybrid dense+sparse retrieval with Reciprocal Rank Fusion, cross-encoder reranking, and query transformation techniques like HyDE and multi-query to maximize result relevance.
  • Use Case: Build a customer support knowledge base that answers product questions with cited sources, or an internal engineering document search tool that retrieves relevant code and policy documents accurately.

Quick Start

Use the rag-production skill to build a RAG pipeline over your product documentation that answers user questions with cited sources and passes RAGAS quality evaluation thresholds.

Frequently Asked Questions about rag-production

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

FAQPage Schema
How do I build a production-ready RAG pipeline that minimizes hallucinations?▼

To build a production-ready RAG pipeline that minimizes hallucinations, implement end-to-end best practices for document loading, chunking, hybrid dense+sparse retrieval, cross-encoder reranking, and RAGAS-based quality evaluation to maximize retrieval relevance.

What is the best way to retrieve relevant documents from proprietary data using LLMs?▼

The best way to retrieve relevant documents from proprietary data is using hybrid dense and sparse retrieval with Reciprocal Rank Fusion, enhanced by query transformation techniques like HyDE and multi-query to maximize result relevance.

How do I optimize embedding costs when loading PDF, HTML, and DOCX files for retrieval-augmented generation?▼

Optimize embedding costs for retrieval-augmented generation by applying incremental loading practices to avoid re-embedding unchanged documents, while preserving full metadata during PDF, HTML, DOCX, and Markdown file processing.

Can I use cross-encoder reranking and HyDE to improve vector search relevance?▼

Yes, you can improve vector search relevance by implementing cross-encoder reranking alongside query transformation techniques like HyDE and multi-query within your retrieval-augmented generation pipeline.

Why does my RAG pipeline return irrelevant results and how can RAGAS evaluation help?▼

RAG pipelines return irrelevant results due to unoptimized retrieval and chunking; applying RAGAS-based quality evaluation identifies these failures by measuring retrieval relevance and grounding to ensure accurate, cited answers.

Does rag-production support building a customer support knowledge base with cited sources?▼

Yes, rag-production supports building a customer support knowledge base that answers product questions with cited sources by applying optimized document processing and production-grade retrieval to your proprietary data.

Related Skills

Explore More Software Engineering Skills→
zevtoszevtos
11

doc2kb

Convert mixed document corpora into an LLM-optimized knowledge base with manifest indexing.

Community
Advanced
HermeticOrmusHermeticOrmus
89

rag-implementation

Implement RAG systems integrating vector databases and semantic search for LLM applications.

Community
Advanced
JNZaderJNZader

rag-advanced

Optimize RAG pipelines with HyDE, reranking, and hybrid search.

Community
Advanced
Renzo-TognellaRenzo-Tognella

Advanced RAG Patterns

Implement advanced RAG patterns for hybrid search retrieval quality.

Community
Advanced