AI Practitioners, Solution Architects, Technical Product Managers, Data Teams, Developers, and automation specialists building or deploying RAG-powered applications.

Participants should have a foundational understanding of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) concepts

Course Outline:

1. The RAG Reality Check: Architecture & Failures
   1. The “Naïve RAG” vs. “Advanced RAG” gap: Why simple setups fail in production
   2. The Triad of Failure: Low Faithfulness (hallucinations), Low Relevance (noise), and Low Recall (missing info)
   3. Quick Audit: Identifying where your current pipeline is leaking value

2. Data Prep: Precision Chunking & Metadata
   1. Beyond Fixed-Size: Moving to semantic boundaries and recursive character splitting
   2. The Context Window vs. Retrieval Granularity: Finding the “Goldilocks” chunk size
   3. Metadata Injection: Using “Self-Querying” and filters to bypass vector noise
   4. Rapid Lab: Visualizing how different chunk sizes impact a single document’s retrieval

3. Retrieval Mastery: Hybrid Search & Reranking
   1. Why Vector Search isn’t enough: The case for Hybrid Search (Keyword + Semantic)
   2. The Power of Reranking: Why “Top K” is often wrong and how a second pass reranked fixes it
   3. Similarity Thresholds: Keeping the “garbage” out of your LLM context

4. Grounding & Prompt Guardrails
   1. The “Reference” Mandate: Structuring prompts to force citations
   2. Handling “I don’t know”: Preventing hallucinations on out-of-scope queries
   3. Context Injection: Efficiently formatting retrieved data for the LLM

5. Evaluation & The Production Checklist
   1. The RAG Triad Metrics: Faithfulness, Answer Relevance, and Context Precision
   2. LLM-as-a-Judge: Using automated tools to grade your RAG performance

Training material provided: Yes (Digital format)

Hands-on Lab: Students will be provided with docker compose file and n8n workflow JSON.