skills.rest
gerald-ica
gerald-icaCOMMUNITY
Explore all skills by this author →
GitHub

rag-engineer

Optimize RAG systems with embedding models, vector databases, and chunking strategies.

Updated Apr 6, 2026
Search Tags:#semantic search#RAG#vector search#document retrieval#embedding models
One-click install
npx skills add https://github.com/gerald-ica/dev-tool-configs --skill rag-engineer-gerald-ica
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/gerald-ica/dev-tool-configs/tree/main/gemini/skills/rag-engineer
Command: npx skills add https://github.com/gerald-ica/dev-tool-configs --skill rag-engineer-gerald-ica

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of building high-quality Retrieval-Augmented Generation (RAG) systems, focusing on embedding models, vector databases, chunking strategies, and retrieval optimization.

Core Features & Use Cases

  • Vector Embeddings & Similarity Search: Master the creation and use of vector embeddings for efficient document retrieval.
  • Document Chunking & Preprocessing: Implement effective chunking and preprocessing techniques to enhance retrieval quality.
  • Retrieval Pipeline Design: Design robust retrieval pipelines that balance precision and recall.
  • Semantic Search Implementation: Integrate semantic search capabilities for more nuanced document understanding.
  • Context Window Optimization: Optimize context windows to improve the relevance of retrieved documents.
  • Hybrid Search: Combine keyword and semantic search for comprehensive search capabilities.
  • Use Case: When developing a RAG system for a legal document search application, this Skill can help in optimizing the retrieval of relevant documents based on semantic similarity.

Quick Start

Use the rag-engineer skill to optimize the retrieval of legal documents for a RAG system.

Frequently Asked Questions about rag-engineer

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

FAQPage Schema
How do I optimize document retrieval for a Retrieval-Augmented Generation system?▼

Optimizing document retrieval for a Retrieval-Augmented Generation system involves applying effective chunking strategies, tuning embedding models, and implementing robust vector search pipelines to balance precision and recall.

What is the best way to chunk documents for semantic search in LLM applications?▼

The best way to chunk documents for semantic search is to apply targeted preprocessing techniques that segment text into meaningful units, directly enhancing embedding quality and retrieval relevance.

How does hybrid search improve vector search results over standard semantic search?▼

Hybrid search improves vector search results by combining traditional keyword search with semantic search, providing comprehensive search capabilities that capture both exact matches and nuanced semantic meaning.

Do I need to know NLP concepts to build a RAG pipeline with vector databases?▼

Yes, building a RAG pipeline with vector databases requires prerequisite knowledge of NLP concepts, embedding models, and retrieval techniques to effectively manage context window optimization and similarity search.

Why is context window optimization important for retrieval pipeline design?▼

Context window optimization is important for retrieval pipeline design because it directly improves the relevance of retrieved documents fed into LLM applications, ensuring the generated output is accurate and contextually grounded.

Related Skills

Explore More Software Engineering Skills→
kivo360kivo360
1

moai-essentials-refactor

Transform domain knowledge into vector embeddings for semantic retrieval.

Community
Intermediate
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced
gil00pitagil00pita

pinecone

Store and query high-dimensional embeddings with Pinecone for semantic similarity.

Community
Advanced
ataschzataschz
18

google-gemini-embeddings

Embed text into Gemini vector representations for retrieval and semantic search.

Community
Advanced