Verified:GitHub

rag-architect

Design RAG pipelines with hybrid retrieval, vector stores, and grounded citations.

6|Updated May 20, 2026

Search Tags:#rag #citations #knowledge-base #retrieval-augmented-generation #vector-store #hybrid-search #grounded-answers

Ready to run

npx skills add https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version --skill rag-architect-vignesh2027

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version/tree/main/rag-architect
Command: npx skills add https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version --skill rag-architect-vignesh2027

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Designs production-grade Retrieval-Augmented Generation systems by providing a structured approach to integrate retrieval, vector stores, and citation-grounded answers across data sources.

Core Features & Use Cases

End-to-end RAG pipeline design with modular sub-agents (ChunkerDesigner, EmbeddingSelector, VectorStoreBuilder, HybridSearchEngine, AnswerSynthesizer, HallucinationDetector) for maintainability and scalability.
Flexible vector store configuration for Chroma, Pinecone, or pgvector with appropriate indexing and retrieval strategies.
Grounded answer synthesis with precise source citations and built-in hallucination checks.
Use cases include document Q&A systems, knowledge-base construction, semantic search-enabled assistants, and compliance-ready content retrieval.

Quick Start

Instantiate a project and configure a RAG pipeline using the RAG-Architect design patterns.

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 with grounded answers and hallucination control?▼

Design a RAG pipeline by configuring modular sub-agents for chunking, embedding selection, vector store setup, hybrid search, and answer synthesis to ensure grounded answers with built-in hallucination checks and precise source citations.

What's the best way to configure a vector store for retrieval-augmented generation?▼

Configure a vector store for retrieval-augmented generation by selecting Chroma, Pinecone, or pgvector, then applying appropriate indexing and hybrid retrieval strategies to optimize semantic search performance across your data sources.

Does this RAG architecture support hybrid search and re-ranking?▼

Yes, the RAG architecture supports hybrid search and re-ranking through its modular HybridSearchEngine component, enabling precise document Q&A retrieval before synthesizing grounded answers.

When do I need chunking strategies and embedding model selection for knowledge bases?▼

You need chunking strategies and embedding model selection when building knowledge bases requiring semantic search, ensuring data is properly partitioned and vectorized for accurate retrieval and compliance-ready content generation.

Can I build document Q&A systems with citations using pgvector?▼

Yes, you can build document Q&A systems with citations using pgvector as the vector store, leveraging the AnswerSynthesizer to generate grounded responses with precise source tracking and hallucination detection.

Why does my retrieval-augmented generation pipeline produce ungrounded answers?▼

Your retrieval-augmented generation pipeline may produce ungrounded answers if lacking proper re-ranking, hybrid search configuration, or hallucination detection during the answer synthesis phase. Implement the built-in HallucinationDetector to enforce source grounding.