rag-patterns

Implement RAG pipelines with chunking, embedding, retrieval, reranking, and generation.

3|1|Updated Feb 2, 2026

Search Tags:#llm #rag #vector search #document qa #retrieval augmented generation #knowledge grounding

Ready to run

npx skills add https://github.com/HouseGarofalo/claude-code-base --skill rag-patterns-housegarofalo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-patterns
Source: https://github.com/HouseGarofalo/claude-code-base/tree/main/.claude/skills/rag-patterns
Command: npx skills add https://github.com/HouseGarofalo/claude-code-base --skill rag-patterns-housegarofalo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, sentence-transformers, chromadb, langchain, nltk, rank-bm25, cohere, ragas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides expert guidance and practical code examples for building robust Retrieval-Augmented Generation (RAG) systems, enabling AI to leverage external knowledge effectively.

Core Features & Use Cases

RAG Pipeline Implementation: Covers chunking, embedding, retrieval, reranking, and generation.
Advanced Strategies: Includes hybrid embeddings, multi-vector embeddings, query expansion, and HyDE.
Use Case: Develop a document QA system that accurately answers user questions by retrieving relevant information from a large corpus of documents and synthesizing an answer.

Quick Start

Use the rag-patterns skill to index documents and then perform a RAG query.

Frequently Asked Questions about rag-patterns

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

FAQPage Schema

How do I implement a retrieval augmented generation pipeline for document QA?▼

You can build a retrieval augmented generation pipeline by applying patterns for document chunking, embedding, vector retrieval, reranking, and generation to accurately answer questions from a large document corpus.

What is the best way to improve RAG retrieval accuracy with vector search?▼

Improve RAG retrieval accuracy by using advanced strategies like hybrid embeddings, multi-vector embeddings, query expansion, and HyDE to enhance vector search relevance before generation.

Can I use LangChain and ChromaDB for knowledge grounding in LLM applications?▼

Yes, you can use LangChain and ChromaDB within your RAG pipeline to index documents and perform vector search, providing essential knowledge grounding for your LLM applications.

How do I chunk documents and create embeddings for a RAG system?▼

Chunk documents into smaller segments and use embedding strategies like sentence-transformers to convert text into vectors, enabling effective retrieval in your RAG system.

Does Cohere provide reranking techniques for retrieval augmented generation?▼

Yes, Cohere is included as a dependency for applying reranking techniques, which help reorder retrieved documents to prioritize the most relevant context for the generation step.

How do I evaluate RAG pipeline performance using Ragas?▼

You can evaluate RAG pipeline performance using the Ragas framework to measure how effectively your system retrieves relevant context and generates accurate, grounded responses.