Advanced Certificate in Applied Artificial Intelligence (AI) Programming Module 9: Retrieval Augmented Generation (RAG) Programming (Synchronous E-Learning)
About This Course
Retrieval Augmented Generation (RAG) is one of the most popular use cases of Large Language Models (LLMs). It allows you to integrate LLMs with your organisation’s proprietary data. In this 2-day module, participants will dive deep into the principles, techniques, and applications of RAG, gaining hands-on experience in harnessing its capabilities to create intelligent and contextually rich text generation systems. Whether you are a seasoned practitioner or a newcomer to the field, this module offers an invaluable opportunity to master the cutting-edge technology driving the future of natural language understanding and generation.
What You'll Learn
• Gain a deep understanding of the principles, architecture, and techniques underlying Retrieval Augmented Generation (RAG), including the integration of retrieval-based and generative models
• Familiarise themselves with leading RAG frameworks and libraries, learning how to effectively utilise them for text generation tasks and integrate them into existing systems
• Gain hands-on experience in implementing RAG models, including fine-tuning pre-trained models and customising them for specific applications and use cases
• Learn how to leverage retrieval mechanisms to enhance the contextuality and relevance of generated text, ensuring more accurate and coherent outputs
• Explore techniques for optimising the performance and efficiency of RAG models, including batch processing, caching, and parallelisation strategies
• Develop proficiency in evaluating the performance and quality of RAG models using appropriate metrics and evaluation techniques, ensuring robust and reliable text generation systems
• Apply RAG techniques and frameworks to real-world text generation tasks and scenarios, such as question answering, summarisation, and conversational artificial intelligence, demonstrating the practical utility and effectiveness of RAG technology
• Stay informed about the latest advancements and research trends in RAG technology, enabling continued learning and adaptation to evolving best practices and methodologies
Entry Requirements
• Basic programming experience using Python
• Knowledge of NumPy and Pandas (covered in Module 2)
• Recommended to have knowledge of Machine Learning (covered in Module 3)
• Recommended to have knowledge of Deep Learning (covered in Module 4)
• Recommended to have knowledge of AI applications development (covered in Module 5)