Training programme overview
Design robust data pipelines for RAG: ingestion, parsing, chunking, embeddings, vector and hybrid search, access control, citation handling, and data refresh strategies.
This intermediate course addresses preparing sources for RAG, from ingestion to indexed storage.
It details chunking strategies and embedding selection to improve relevance in vector search.
The curriculum covers vector and hybrid search implementations, combining semantic and boolean signals.
It also treats citation handling, access control policies and refresh strategies to keep RAG data current.
Training · Intermediate
Courses included in this training programme
RAG Data Foundations
Foundational RAG concepts for AI data engineers: architecture, limits and source governance. Covers source inventory, data ownership, freshness, ACLs, parsing common formats (PDF, HTML, Markdown, CSV) and metadata design for citations and filtering.
4 lessons · 20 activities · 0 exercises · 3 videos
Chunking and Embeddings
Chunking and embedding techniques: chunking strategies (fixed, semantic, recursive, document-aware), embedding model selection including multilingual options, deduplication and normalization, and incremental indexing with re-index triggers.
4 lessons · 20 activities · 0 exercises · 3 videos
Vector and Hybrid Search
Vector and hybrid search: fundamentals (cosine, dot product, HNSW, IVF), using pgvector for small-to-medium RAG, Qdrant for dedicated vector search with payload filtering, and hybrid BM25+vector+reranking strategies.
4 lessons · 20 activities · 0 exercises · 3 videos
Grounded Answers and Citations
Grounded answers and citations: prompt template patterns for grounded responses, source attribution UX, document-level access control, and production operations (refresh, jobs, monitoring, rollback).
4 lessons · 20 activities · 0 exercises · 3 videos
Access the platform
Open the catalogue to review course details, access conditions, and your personal progress. Sign in.