skills.rest
TwuanMinn
TwuanMinnCOMMUNITY
Explore all skills by this author →
GitHub

rag-engineer

Design and optimize Retrieval-Augmented Generation pipelines with embeddings and vector stores.

Updated Jan 26, 2026
Search Tags:#embeddings#rag#chunking#semantic-search#vector-search#retrieval-augmented-generation#document-retrieval
One-click install
npx skills add https://github.com/TwuanMinn/fadelab --skill rag-engineer-twuanminn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/TwuanMinn/fadelab/tree/main/.agent/skills/skills/rag-engineer
Command: npx skills add https://github.com/TwuanMinn/fadelab --skill rag-engineer-twuanminn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides architecture and strategies to design, optimize, and operate Retrieval-Augmented Generation systems by expertly handling embeddings, vector databases, chunking, and retrieval pipelines to maximize answer quality.

Core Features & Use Cases

  • Retrieval pipeline design and optimization for end-to-end RAG workflows, including integration of embedding models and vector stores.
  • Embedding selection, dimensionality tuning, and chunking strategies to improve retrieval accuracy and context preservation.
  • Semantic and hybrid search implementations, metadata filtering, and reranking to boost precision in document retrieval.
  • Use Case: Build a RAG system that answers user questions by grounding responses in a corpus of manuals, articles, and internal documents.

Quick Start

Create a minimal RAG architecture plan and initialize embeddings, a vector store, and a basic chunking rule for your first dataset.

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 for document understanding?▼

To build a retrieval-augmented generation pipeline, design an architecture integrating embedding models, a vector store, and chunking rules to ground responses in your document corpus.

What chunking strategies improve semantic search accuracy in RAG systems?▼

Chunking strategies improve semantic search accuracy by preserving context boundaries during document splitting, ensuring embedding models capture cohesive information for precise vector search retrieval.

Can I use metadata filtering and reranking to boost document retrieval precision?▼

Metadata filtering and reranking boost document retrieval precision by narrowing vector search results to relevant subsets and reordering candidates to maximize semantic similarity.

What is the best way to select embedding models and tune dimensionality for vector search?▼

Select embedding models and tune dimensionality by evaluating semantic similarity metrics against your dataset, optimizing the balance between vector store indexing speed and retrieval accuracy.

Does this RAG architecture support hybrid search implementations across diverse data sources?▼

RAG architecture supports hybrid search across diverse data sources by combining semantic vector search with metadata filtering, enabling precise document retrieval from manuals, articles, and internal documents.

Related Skills

Explore More Data & Analytics Skills→
giuseppe-trisciuogliogiuseppe-trisciuoglio
322

rag-implementation

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

Community
Advanced
sixscripts-aisixscripts-ai

rag-implementation

Implement RAG systems with vector stores, embeddings, and retrieval pipelines.

Community
Advanced
acarmonagacarmonag
2

AgentDB Vector Search

Implement semantic vector search with AgentDB using HNSW indexing and hybrid search.

Community
Advanced
ccfccf

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid retrieval.

Community
Intermediate