Flagship hands-on RAG course
Building Production RAG Systems using Azure AI Search
A practical workshop for teams that need retrieval quality, grounded answers, citation discipline, security controls and operational reliability from their enterprise RAG systems.
RAG Implementation Outcomes
Participants learn how to design a RAG pipeline, tune retrieval, assemble prompts safely, measure answer quality and prepare the system for production use.
Build retrieval pipelines
Plan ingestion, parsing, chunking, metadata, refresh strategy and enterprise source integration.
Tune search quality
Use indexes, analyzers, vector search, hybrid search, scoring, filters and reranking decisions.
Evaluate and operate
Create golden datasets, relevance tests, monitoring, cost controls and security review criteria.
Course Modules
RAG fundamentals
Retrieval vs fine-tuning, grounding, citations and use-case fit.
Data ingestion
Source systems, parsing, chunking, metadata and refresh strategy.
Azure AI Search
Indexes, analyzers, vector search, hybrid search, scoring and filters.
Embeddings and retrieval quality
Embedding choice, chunk size, overlap, metadata filters and reranking.
Application layer
Prompt assembly, citations, fallback, authorization and user experience boundaries.
Evaluation and operations
Golden datasets, relevance tests, monitoring, cost and data freshness.
Capstone
Build a RAG prototype design for enterprise documents and create a production hardening plan for quality, security and operations.
Included templates
- RAG architecture diagram
- Chunking and metadata strategy
- Retrieval tuning checklist
- RAG evaluation plan
Train Your Team To Build RAG Properly
Share your document types, search stack and target users. We can tailor labs around Azure AI Search, Azure OpenAI, internal knowledge bases and quality evaluation.