rag-patterns

Community

Build robust RAG pipelines with Azure AI Search.

Authorpascalvanderheiden
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables building Retrieval-Augmented Generation (RAG) pipelines using Azure AI Search to ground LLM responses with knowledge bases and structured data.

Core Features & Use Cases

  • Agentic Retrieval: multi-query planning and synthesis across knowledge sources for complex, multi-step questions.
  • Full-Text + Vector Hybrid: combine BM25 keyword search with semantic vector similarities for robust answer grounding.
  • Semantic Ranking: leverage integrated semantic configurations to improve result relevance and citation quality.
  • Use Case: design an enterprise chatbot that can search product docs, manuals, and policy PDFs, then provide cited answers to user queries.

Quick Start

  • Install dependencies and run the example scripts to explore RAG patterns.
  • Create and configure indexes with vector and semantic capabilities: python scripts/create_index.py
  • Run vector-based search examples: python scripts/vector_search.py
  • Explore full-text search examples: python scripts/full_text_search.py
  • Experiment with agentic retrieval: python scripts/agentic_retrieval.py

Dependency Matrix

Required Modules

azure-search-documentsazure-identityopenai

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: rag-patterns
Download link: https://github.com/pascalvanderheiden/my-agent-skills/archive/main.zip#rag-patterns

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.