rag-architect

Name: rag-architect
Availability: InStock
Author: jeffallan

Design and implement retrieval-augmented generation pipelines with vector stores and hybrid search.

10.9k|1.0k|Updated Oct 20, 2025

Search Tags:#semantic search #embeddings #knowledge base #RAG #retrieval #vector-database

Ready to run

npx skills add https://github.com/Jeffallan/claude-skills --skill rag-architect

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/Jeffallan/claude-skills/tree/main/skills/rag-architect
Command: npx skills add https://github.com/Jeffallan/claude-skills --skill rag-architect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill designs Retrieval-Augmented Generation (RAG) architectures, vector stores, and knowledge-grounded AI pipelines to ground LLM outputs and accelerate accurate retrieval.

Core Features & Use Cases

Vector store design & selection: Choose appropriate vector DB and schema.
Chunking & metadata: Plan document chunking with boundaries and enrichment.
Retrieval pipeline: Embeddings, hybrid search, reranking.
Evaluation & monitoring: Measure precision, latency, etc.

Quick Start

Draft a RAG system blueprint for a knowledge-base chatbot with a vector store, ingest workflow, and retrieval path.

Frequently Asked Questions about rag-architect

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

FAQPage Schema

How do I build a retrieval-augmented generation system for accurate LLM responses?▼

Retrieval-augmented generation grounds LLM outputs in factual knowledge by designing vector stores, selecting embeddings, chunking documents with metadata, and implementing semantic or hybrid search pipelines. This architecture retrieves relevant context before generation, improving accuracy for chatbots, Q&A systems, and knowledge bases at scale.

What's the best way to choose and design a vector database for embeddings?▼

Vector store design requires selecting a database that supports your scale and query patterns, defining schemas for embeddings and metadata, and planning ingestion workflows. Consider latency requirements, multi-tenant isolation, and reranking capabilities to ensure retrieval performance matches your production workload.

How do I implement hybrid search combining semantic and keyword retrieval?▼

Hybrid search combines vector similarity search with traditional keyword matching to improve recall and relevance. Implement both retrieval paths in parallel, normalize scores, and optionally apply reranking to surface the most relevant results before passing context to the LLM.

Can I evaluate and monitor RAG retrieval quality in production?▼

Yes. Measure retrieval precision, latency, and ranking effectiveness using standard metrics. Monitor embedding performance, track ingestion idempotence, and version both models and embeddings to ensure consistent quality across updates and identify degradation.

What are the key considerations for document chunking and metadata enrichment?▼

Document chunking preserves semantic boundaries while fitting embedding token limits. Enrich chunks with metadata—source, timestamp, section hierarchy—to enable filtering, multi-tenant queries, and contextual reranking, improving both retrieval precision and downstream LLM grounding.

How do I handle multi-tenant RAG deployments with separate knowledge bases?▼

Multi-tenant RAG requires metadata-based isolation, tenant-scoped ingestion workflows, and query filtering to prevent cross-tenant data leakage. Design schemas and retrieval pipelines with tenant context throughout embedding, search, and reranking stages.