[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3

RAG Fundamentals in Foundry

📚 RAG & Grounding 8 min 70 BASE XP

Retrieval-Augmented Generation

RAG grounds AI model responses in your private data, reducing hallucination and enabling domain-specific answers.

The Foundry RAG Pipeline

  1. Ingest - Upload documents (PDFs, Word, web pages)
  2. Process - Document Intelligence extracts text and structure
  3. Chunk - Split into semantically meaningful segments
  4. Embed - Convert chunks to vectors using an embedding model
  5. Index - Store in Azure AI Search
  6. Retrieve - When a user asks a question, find relevant chunks
  7. Generate - Feed retrieved chunks to the LLM as grounding context

Quick Setup via Portal

The easiest way to set up RAG is through the Chat Playground:

  1. Open the Chat Playground
  2. Click "Add your data"
  3. Select Azure AI Search as the data source
  4. Upload your documents or connect an existing index
  5. The system automatically chunks, embeds, and indexes your data
💡 Key Insight: The portal's "Add your data" wizard handles the entire pipeline automatically. For production, use the SDK to customize chunking strategy, embedding model, and index configuration.
FOUNDRY VERIFICATION
QUERY 1 // 1
What is the primary purpose of RAG in Azure AI Foundry?
To train new models
To ground AI responses in your private data, reducing hallucination
To translate documents
To generate images