skills.rest
hainamchung
hainamchungCOMMUNITY
Explore all skills by this author →
GitHub

rag-architect

Design and implement Retrieval-Augmented Generation architectures with hybrid search and vector databases.

54|18|Updated Jan 21, 2026
Search Tags:#embeddings#rag#reranking#vector-databases#hybrid-search#knowledge-grounding#retrieval-evaluation
One-click install
npx skills add https://github.com/hainamchung/agent-assistant --skill rag-architect-hainamchung
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/hainamchung/agent-assistant/tree/main/skills/rag-architect
Command: npx skills add https://github.com/hainamchung/agent-assistant --skill rag-architect-hainamchung

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Design and implement Retrieval-Augmented Generation (RAG) architectures to ground LLM outputs in factual external knowledge.

Core Features & Use Cases

  • Hybrid search design, vector databases, and chunking strategies for scalable knowledge integration.
  • Multi-tenant retrieval with metadata filters and reranking to improve relevance.
  • Evaluation and observability for RAG pipelines (faithfulness, relevance, latency, and reliability).

Quick Start

Define a RAG pipeline that ingests documents, builds a vector store, and wires retrieval, generation, and evaluation steps.

Frequently Asked Questions about rag-architect

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

FAQPage Schema
How do I design a RAG pipeline to ground LLM outputs in factual external knowledge?▼

To design a RAG pipeline, define steps to ingest documents, build a vector store, and wire retrieval with generation. This grounds LLM outputs by enforcing best practices for embedding selection, metadata enrichment, and chunking strategies.

What is the best way to improve retrieval relevance in a RAG system using hybrid search?▼

The best way to improve retrieval relevance in a RAG system is implementing hybrid search combined with reranking. Multi-tenant retrieval with metadata filters further refines results to ensure highly relevant knowledge extraction.

How do I evaluate RAG pipelines for faithfulness and relevance?▼

You evaluate RAG pipelines by measuring faithfulness, relevance, latency, and reliability. Implementing observability across the production pipeline ensures your retrieval-augmented generation architecture maintains factual accuracy over time.

How does chunking strategy affect vector database performance in RAG architectures?▼

Chunking strategy directly affects vector database performance by determining how documents are segmented and indexed. Proper chunking enables scalable knowledge integration and ensures the embedding selection captures accurate context for retrieval.

Can I use multi-tenant filtering with metadata enrichment for scalable RAG retrieval?▼

Yes, you can use multi-tenant filtering with metadata enrichment for scalable RAG retrieval. This approach enforces best practices by isolating tenant data and applying specific filters during hybrid search to improve relevance.

Related Skills

Explore More Software Engineering Skills→
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate
Miosa-osaMiosa-osa
226

eval-rag

Evaluate RAG pipelines with retrieval and generation metrics plus bottleneck analysis.

Official
Advanced
JFrangelJFrangel

chunk-scoring

Optimize RAG pipelines with semantic chunking, embedding selection, and vector database configuration.

Community
Advanced
zzafergokzzafergok
1

rag-implementation

Design and build RAG systems grounding LLM outputs in external knowledge sources.

Community
Advanced