skills.rest
AmidVoshakul
AmidVoshakulCOMMUNITY
Explore all skills by this author →
GitHub

rag-engineer

Design and optimize RAG pipelines with vector databases and hybrid search.

Updated Dec 29, 2025
Search Tags:#semantic search#embeddings#llm#rag#vector database#retrieval
One-click install
npx skills add https://github.com/AmidVoshakul/chatorai --skill rag-engineer-amidvoshakul
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-engineer
Source: https://github.com/AmidVoshakul/chatorai/tree/main/assets/skills/rag-engineer
Command: npx skills add https://github.com/AmidVoshakul/chatorai --skill rag-engineer-amidvoshakul

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the common failure points in Retrieval-Augmented Generation, such as poor retrieval quality, hallucination due to irrelevant context, and inefficient chunking strategies.

Core Features & Use Cases

  • Retrieval Optimization: Implements hybrid search, re-ranking, and metadata filtering to ensure the most relevant context is retrieved.
  • Advanced Chunking: Provides strategies for semantic chunking that respect document structure rather than arbitrary token limits.
  • Use Case: Use this skill to design a robust knowledge base architecture for a technical documentation portal, ensuring that users receive accurate, context-aware answers from complex, multi-format datasets.

Quick Start

Use the rag-engineer skill to analyze my current document chunking strategy and suggest improvements for better semantic retrieval.

Frequently Asked Questions about rag-engineer

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

FAQPage Schema
How do I improve retrieval quality in my RAG pipeline?▼

Improve retrieval quality in your RAG pipeline by implementing hybrid search, re-ranking, and metadata filtering to retrieve the most relevant context. Semantic chunking that respects document structure also prevents retrieving irrelevant context and reduces hallucination.

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

The best way to chunk documents for semantic search is using semantic chunking strategies that respect document structure rather than relying on arbitrary token limits. This ensures that retrieved context remains coherent and highly relevant to the query.

Why does my LLM hallucinate when retrieving context from a vector database?▼

Your LLM hallucinates during retrieval because of irrelevant context entering the prompt. Applying metadata filtering, re-ranking, and optimized embedding models ensures the vector database supplies only high-precision information to the context window.

Can I use hybrid search for a multi-format technical documentation knowledge base?▼

Yes, you can use hybrid search for a multi-format technical documentation knowledge base. It combines vector and keyword retrieval to handle complex datasets, ensuring users receive accurate, context-aware answers from diverse documents.

How do I manage the context window when building LLM-powered knowledge bases?▼

Manage the context window in LLM-powered knowledge bases by applying advanced chunking strategies and metadata filtering. This limits the injected context to only the most relevant information, optimizing context window usage and retrieval evaluation metrics.

Related Skills

Explore More Software Engineering Skills→
dotlab-hqdotlab-hq

langchain-rag

Build RAG pipelines that ingest, chunk, embed, and retrieve documents for LLMs.

Official
Intermediate
felipeganamefelipeganame
2

AgentDB Vector Search

Implement semantic vector search with AgentDB for document retrieval and similarity matching.

Community
Advanced
ArdurAIArdurAI
1

god-mlops-llm

Guide LLM engineering with fine-tuning, RAG design, evaluation, and security.

Official
Advanced
NicolasHoyosDevssNicolasHoyosDevss

rag-implementation

Build RAG systems integrating vector databases, embedding models, and retrieval strategies.

Community
Advanced