Enterprise AI Search with RAG: Building Document Intelligence Systems (SF)
About This Course
This intensive Five-day workshop guides learners through the design, implementation, and assessment of a complete File-based Retrieval-Augmented Generation (RAG) pipeline. Starting with the fundamentals of RAG and prompt-chaining architectures, participants will progress to building embedding pipelines and Q&A chatbots, before culminating in hands-on NLP-to-SQL integrations and end-to-end workflow demonstrations.
Learners will engage in a blend of interactive presentations, written assessments, and practical lab exercises—ensuring they not only understand core concepts but can apply them immediately in real-world scenarios.
What You'll Learn
LO2: Apply context augmentation using Retrieval-Augmented Generation (RAG) and effective prompt engineering/model configurations to integrate foundational models into applications by leveraging developer tools frameworks, and low-code/no-code platforms to accelerate generative AI application development.
LO3: Troubleshoot on escalated issues on performance problem that encountered with AI tools by applying standard procedures, interpreting documentation, and leveraging concepts of context augmentation for prompts (e.g., RAG).
Entry Requirements
• The candidate should hold a diploma and have at least 2 years of experience working as a developer/programmer.
• Candidates who do not meet the above requirements will be assessed on case to case basis.