AI Guardrails: Secure Generative AI Applications

Build Responsible AI using OpenSource Models [HuggingFace], Platforms [Amazon Bedrock], Frameworks[Nemo, GuardrailsAI]

Created by: Firstlink Consulting
FirstLinkConsulting - Training & consulting services

What Will I Learn?

• Understand the fundamentals of AI Guardrails and their importance in ethical AI development.
• Retrieval Augmented Generation: Learn about RAG, Vector store
• User Input Guardrails : Learn about prompt injections, user input moderations (hate, violence etc) and ways to detect user input violations
• Hallucination: Learn about Hallucination and detecting Hallucination using Open Source model from Hugging Face
• Evaluators - Faithfulness Evaluator(LLM-As-A-Judge), SAS Evaluator, Context Relevance Evaluator and RAGAS Evalauator
• Haystack Framework: Introduction to Haystack pipeline
• Guardrails on AWS Bedrock : Learn to configure, deploy and run Guardrails on AWS Bedrock
• Explore Real World Guardrails Models using Huggingface and Colab Notebooks
• Learn architecture and gain insight on open source frameworks like GuardrailsAI and NemoGuardrails with real-world AI projects.
• Learn to implement AI Guardrails and Nemo Framework in AI projects to prevent bias, ensure privacy, and enhance security.

Requirements

• For beginners: This course is structured to welcome learners at various levels. If you're new to AI, we'll start with foundational concepts, making it an ideal opportunity to dive into ethical AI development with minimal barriers.
• Familiarity with programming, preferably in Python, as it's commonly used for AI development.
• Access to a computer with internet connection, capable of running AI development tools and frameworks.
• No prior experience with GuardrailsAI or NemoGuardrails is required; this course is designed to introduce these tools from the ground up.

Target audience

• This course is tailored for a diverse audience interested in the ethical implications and security of artificial intelligence, including: AI and Machine Learning Engineers seeking to integrate ethical guidelines and security measures into their AI models.
• Data Scientists and Analysts aiming to understand and apply data privacy and integrity measures in AI applications.
• IT Professionals and Cybersecurity Experts looking to expand their knowledge in AI vulnerabilities and protective mechanisms.
• Ethics Officers and Compliance Professionals in technology sectors who wish to grasp the technical aspects of AI ethics for better regulation and implementation.
• Technology Students and Enthusiasts curious about the intersection of AI, ethics, and security, aiming to build responsible AI solutions. Whether you're a professional aiming to ensure AI implementations in your organization are secure and ethical, or a student venturing into the realm of AI with a desire to champion ethical practices, this course offers valuable insights and skills to help you make a meaningful impact in the field of artificial intelligence.