skills.rest
sergiomvj
sergiomvjCOMMUNITY
Explore all skills by this author →
GitHub

rag-engineer

Design retrieval pipelines with embeddings, chunking, and hybrid search.

Updated Aug 27, 2026
Search Tags:#embeddings#rag#chunking#semantic-search#vector-databases#llm-integration#retrieval-pipeline
One-click install
npx skills add https://github.com/sergiomvj/facebrasil --skill rag-engineer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/sergiomvj/facebrasil/tree/main/.agent/skills/rag-engineer
Command: npx skills add https://github.com/sergiomvj/facebrasil --skill rag-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams build Retrieval-Augmented Generation (RAG) systems by enabling reliable access to external knowledge during LLM inference, reducing hallucinations and data gaps.

Core Features & Use Cases

  • Vector embeddings and similarity search
  • Document chunking and preprocessing
  • Retrieval pipeline design
  • Semantic search implementation
  • Context window optimization
  • Hybrid search (keyword + semantic)
  • Use Case: Build a RAG assistant that answers questions by retrieving relevant documents from a knowledge base.

Quick Start

Load your documents, select an embedding model, initialize a vector store, and run an LLM with a retrieval step.

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 retrieval pipeline for retrieval-augmented generation?▼

To build a retrieval pipeline for retrieval-augmented generation, you load documents, select an embedding model, initialize a vector store, and run an LLM with a retrieval step to fetch relevant context.

What is the best way to implement document chunking for semantic search?▼

Document chunking for semantic search involves preprocessing unstructured data into smaller segments, enabling embeddings-based similarity search to accurately match user queries with relevant context windows.

Does RAG reduce hallucinations when connecting LLMs with external knowledge?▼

RAG reduces LLM hallucinations by connecting models with external knowledge sources during inference, providing reliable access to structured or unstructured data to fill knowledge gaps.

Can I use hybrid search combining keyword and semantic similarity for complex question answering?▼

Yes, you can use hybrid search combining keyword and semantic similarity for complex question answering, allowing the retrieval pipeline to effectively match queries across structured or unstructured knowledge bases.

How do I optimize context windows when integrating vector database results with an LLM?▼

Context window optimization involves designing the retrieval pipeline to limit vector database results to the most relevant chunks, ensuring the LLM integration receives precise context without exceeding processing limits.

Why do I need vector embeddings for a document search assistant?▼

Vector embeddings are needed for a document search assistant because they convert unstructured text into numerical representations, enabling similarity search to accurately locate and retrieve relevant external knowledge.

Related Skills

Explore More Software Engineering Skills→
zeronx798zeronx798

chroma

Manage vector collections and perform similarity searches with metadata filtering.

Community
Intermediate
xuanhh567xuanhh567

local_rag

Retrieve relevant documentation chunks from local Python package knowledge bases.

Community
Basic
discountedcookiediscountedcookie

postgres-vectors

Store 384-dimensional embeddings in Postgres and query cosine similarity with pgvector.

Community
Advanced
winsorllcwinsorllc

Embedding Search

Provides semantic search across documents with Tunrsity and Tunrsity-like features.

Community
Intermediate