skills.rest
BoraPerusic
BoraPerusicCOMMUNITY
Explore all skills by this author →
GitHub

rag-engineer

Design and optimize RAG pipelines with embeddings, vector databases, and chunking strategies.

Updated Apr 12, 2026
Search Tags:#embeddings#llm#rag#retrieval#chunking#vector-databases
One-click install
npx skills add https://github.com/BoraPerusic/agents --skill rag-engineer-boraperusic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/BoraPerusic/agents/tree/main/skills/to%20try/rag-engineer
Command: npx skills add https://github.com/BoraPerusic/agents --skill rag-engineer-boraperusic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

RAG engineers enable teams to turn unstructured documents into actionable knowledge by designing end-to-end retrieval-augmented generation pipelines that maximize retrieval quality and minimize hallucinations.

Core Features & Use Cases

  • Design and optimize RAG pipelines including retrieval, embedding selection, vector database architecture, and chunking strategies.
  • Implement retrieval quality improvements, context management, and hybrid search to improve answer accuracy.
  • Real-world use: accelerate knowledge-base QA by combining structured metadata with semantic search and cross-encoder reranking.

Quick Start

Configure a retrieval-augmented generation workflow for a given document collection.

Frequently Asked Questions about rag-engineer

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

FAQPage Schema
How do I build a RAG pipeline for enterprise document collections?▼

Improve RAG retrieval accuracy by combining structured metadata with semantic search, context management, and cross-encoder reranking to minimize hallucinations.

How do I optimize chunking strategies and embedding selection for vector databases?▼

Optimize chunking strategies and embedding selection by designing a modular vector database architecture that supports scalable indexing and precise semantic retrieval.

Does this approach support hybrid search and cross-encoder reranking for knowledge bases?▼

Yes, this approach supports hybrid search and cross-encoder reranking to accelerate knowledge-base QA by combining structured metadata with semantic search for improved answer accuracy.

When should I use modular architecture for retrieval-augmented generation systems?▼

Use modular architecture for retrieval-augmented generation systems when you need scalable indexing, robust evaluation, and precise retrieval across enterprise data and large document collections.

Related Skills

Explore More Software Engineering Skills→
Gull-StackGull-Stack

pdf

Extract text and tables from PDFs using Python tools.

Official
Intermediate
roanbrasilroanbrasil
5

rag-production

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

Community
Advanced
neverinfamousneverinfamous
19

rag-pipelines

Design RAG pipelines with chunking, hybrid search, and cross-encoder reranking.

Community
Advanced
SEMOSSSEMOSS
2

semoss-vector

Execute pixel commands for semantic search and document management in SEMOSS vector databases.

Official
Advanced