Secure, Deliver and Optimize GenAI Apps with F5

Welcome to the Secure, Deliver and Optimize GenAI Apps with F5

The content contained here leverages a full DevOps CI/CD pipeline and is sourced from the GitHub repository at https://github.com/f5devcentral/secure-deliver-optimize-genai. Bugs and Requests for enhancements can be made by opening an Issue within the repository.

Contents:

• Introduction - GenAI Practitioner
  • Learning Path
• Prerequisite
  • Readiness
  • Lab Setup Environment
• Class 1: The fundamental of Generative Artificial Intelligent (AI)
  • AI Primer
    • What is AI and how different with GenAI?
    • What is LLM?
    • What is SLM?
    • What is ML?
    • What hallucination means in AI?
    • What “token” means in context in AI?
    • What is quantization?
    • What is Retrival Augmented Generation?
    • What is Agentic RAG?
    • What is vectorizing in AI?
    • What is embedding in AI?
    • What is “context windows” in AI?
    • What is “temperature” in AI?
• Class 2: Deploy and Secure a modern application
  • 1 - Deploy Nginx Ingress Controller with App Protect to protect Web Apps Server
  • 2 - Deploy Arcadia Financial Modern Apps
  • 3 - Secure Modern Apps with NGINX App Protect WAF
  • 4 - Recap
• Class 3: Architect, build and deploy AI Services
  • 1 - Conceptual Architecture of AI Services
  • 2 - Deploy Nginx Ingress Controller for AIGW K8S
  • 3 - Deploy Open-WebUI with Ollama Service
  • 4 - Download Language Model
  • 5 - Deploy LLM model service (Ollama)
  • 6 - Deploy LLM orchestrator service (Flowise AI)
  • 7 - Deploy Vector Database (Qdrant)
  • 8 - Build RAG pipeline with FlowsieAI/Langchain
    • Vectorize Proprietary Data
    • Validate your first GenAI RAG Chatbot
• Class 4: Enhance Modern Application with GenAI ChatBot
  • 1 - Integrate AI Service (RAG ChatBot) into Arcadia Trading
• Class 5: Secure, Deliver and Optimize GenAI ChatBot
  • 1 - Fundamental about F5 AI Gateway
    • AI Core
    • AI Processor
    • Understanding AIGW Configuration
  • 2 - Deploy F5 AI Gateway
    • Install AIGW Core helm charts
  • 3 - Deploy AI GW User Interface.
  • 4 - Deploy F5 AI Processor
    • Install AIGW processor helm chart
  • 5 - Update AIGW policy
  • 6 - Update LLM Orchestrator to point to AI Gateway
  • 7 - Deploy Simply-Chat Apps
  • 8 - Use Cases
    • LLM Traffic Management
    • PII Redactor - Sensitive Information Disclosure
    • RAG ChatBot - Sensitive Information Disclosure
• Class 6: LLM Red Teaming
  • What is AI Governance?
  • AI Risk/Safety vs AI Security
  • What is LLM Red Teaming?
  • F5 LLM Red Teaming Solution