AI & Generative AIAdvanced
RAG in Production — Build AI on Your Own Data
Retrieval-Augmented Generation is how enterprises are deploying AI that actually knows their business. This full day covers the complete RAG stack: embeddings, vector search, chunking strategies, hybrid retrieval, and evaluation. You will build a working RAG system from scratch during the session.
Tools & Technologies
PythonOpenAI APIpgvectorPineconeLangChainLlamaIndex
Course Curriculum
1
RAG Architecture
- Why RAG exists and when to use it vs fine-tuning
- The retrieval-generation pipeline end to end
- Common failure modes and how to avoid them
2
Embeddings & Vector Search
- Embedding models — choosing and comparing
- Vector databases: pgvector, Pinecone, Weaviate
- Similarity search and approximate nearest neighbours
3
Chunking & Retrieval Strategy
- Document parsing and preprocessing
- Chunking strategies and their trade-offs
- Hybrid search (dense + sparse), re-ranking
4
Evaluation & Deployment
- RAG evaluation metrics (faithfulness, relevance, context recall)
- Hallucination testing and guardrails
- Deployment patterns and production considerations
What's Included
Live instructor-led session
Small cohort
Course materials pack (slides, code, datasets)
Certificate of completion
14-day email support
£1,485Early bird
£995Save £490
per person
7 hours (1 day)
Next: Tue, 19 May 2026
7 seats remaining
Advanced level
3/10 seats filled
Completion certificate included