PHAROS AI Factory Training Series – Course 9 “RAG End-to-End: Architecture, Retrieval, Generation and Evaluation”, on July 7th, 2026

PHAROS AI Factory announced the 9th Course of its Training Series, with the title “RAG End-to-End: Architecture, Retrieval, Generation and Evaluation“, that successfully took place on July 7th, 2026.

Presentation language: Greek

Audience: This course was intended for Machine Learning Engineers, AI Engineers, Data Scientists, Academic Researchers, Language and Culture Experts.

Learning Objectives

  • Explain the core principles and architecture of Retrieval-Augmented Generation systems.
  • Understand why RAG improves factuality, grounding, transparency and access to external knowledge.
  • Describe the main RAG pipeline stages, from ingestion and preprocessing to retrieval and response generation.
  • Identify design choices for chunking, embeddings, vector storage, retrieval, prompting and answer grounding.
  • Evaluate retrieval quality, generation quality and end-to-end RAG behaviour.

Learning Outcomes:

  • A clear understanding of the main components and design paradigms of RAG systems.
  • Practical familiarity with document preparation, chunking, embedding generation, vector indexing and similarity-based retrieval.
  • Hands-on experience in constructing a working RAG pipeline using Python and contemporary tools.
  • The ability to connect retrieved evidence with LLM-based answer generation in a grounded and transparent manner.
  • Familiarity with evaluation approaches for retrieval, generation, faithfulness, groundedness and overall RAG performance.
  • An understanding of how RAG can support Greek-language applications, including public-service information retrieval and conversational assistance.
  • The skills to analyse, evaluate and improve RAG systems for real-world deployment

The course’s presentation material can be found here.

The course’s recordings can be found here.

Share: