skills.rest
Dhumitech
DhumitechCOMMUNITY
Explore all skills by this author →
GitHub

rag-engineer

Build retrieval-augmented generation systems with semantic chunking and vector search.

1|Updated Sep 11, 2025
Search Tags:#embeddings#rag#vector-search#retrieval-augmented-generation#hybrid-search#semantic-chunking
One-click install
npx skills add https://github.com/Dhumitech/DHUMI-AI-RESOURCE --skill rag-engineer-dhumitech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/Dhumitech/DHUMI-AI-RESOURCE/tree/main/AI-Engineer-planner-Skills/01-ai-core/rag-engineer
Command: npx skills add https://github.com/Dhumitech/DHUMI-AI-RESOURCE --skill rag-engineer-dhumitech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

RAG systems often struggle with retrieving relevant context and maintaining coherence across long documents, leading to hallucinations and wasted effort.

Core Features & Use Cases

  • Vector embeddings and similarity search for precise retrieval
  • Document chunking and preprocessing to preserve structure
  • Retrieval pipeline design for end-to-end workflows
  • Semantic search implementation for content discovery
  • Context window optimization to maximize usable prompt space
  • Hybrid search combining lexical and semantic signals

Quick Start

Configure a minimal RAG pipeline by providing a document corpus and a sample query to retrieve relevant results.

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-augmented generation pipeline to stop LLM hallucinations?▼

Build a retrieval-augmented generation pipeline by applying semantic chunking to documents, generating vector embeddings, and injecting retrieved context into LLM workflows to improve factual accuracy and reduce hallucinations.

What is the best way to implement hybrid search for document retrieval?▼

Implement hybrid search by combining lexical and semantic signals within your retrieval pipeline, allowing the RAG system to match exact keywords while also understanding contextual similarity for precise document retrieval.

How does semantic chunking improve vector search results?▼

Semantic chunking improves vector search by preprocessing documents to preserve their structure, ensuring that generated embeddings capture meaningful context and yield more accurate similarity search results.

Can I use this to optimize context window usage for long documents?▼

Yes, you can optimize context windows by designing a retrieval pipeline that injects only highly relevant context into the prompt, maximizing usable space and maintaining coherence across long documents.

Why does my RAG system retrieve irrelevant context from my document corpus?▼

Irrelevant context retrieval often happens when document preprocessing lacks semantic chunking or when vector embeddings are paired with a weak similarity search that fails to capture true semantic relationships.

Do I need a specific vector database to deploy a RAG system?▼

No specific vector database is required, as the RAG system focuses on generating embeddings and designing retrieval pipelines for similarity search, allowing integration with diverse document corpora across standard environments.

Related Skills

Explore More Software Engineering Skills→
zainhaszainhas
2

together-embeddings

Generate text embeddings via the Together AI embeddings API.

Community
Intermediate
ruskibeatsruskibeats

rag-evidence-contract-testing

Validate retrieved graph edge evidence structure for LLM RAG context assembly.

Community
Intermediate
jmserverajmservera

solr-pdf-indexing

Index PDF documents into SolrCloud with full-text, metadata, and vector embeddings.

Community
Advanced
Kingly-AgencyKingly-Agency

rag-implementation

Build RAG pipelines that ground LLM responses with retrieved external knowledge.

Official
Advanced