Consensus AI Improving trust in AI with Kubernetes

Welcome to Part Two of our Infrastructure as Code series! 🚀
In Part One, we covered setting up the foundation: Windows 11 with WSL2, Ubuntu, Docker Desktop, Kubernetes with Minikube, and the essential components to get started.
In this video, we take it a step further! 🌟
Learn how to:
✅ Use kubectl and YAML files to set up pods for multiple Ollama instances running various Large Language Models (LLMs).
✅ Deploy a LangChain Retrieval-Augmented Generation (RAG) Streamlit app, orchestrated with NGINX for seamless user interaction.
✅ Upload .pcap files and ask questions to get AI-powered insights from multiple models simultaneously.
🎯 Key Highlights:
1️⃣ Multiple AI responses: Get answers from Mistral by Mistral, Gemma2 by Google, Llama3 by Meta, and Qwen by Alibaba.
2️⃣ Consensus-driven insights: After gathering individual responses, we prompt the AIs to reach a consensus for a "best" democratic answer.
Don’t miss this deep dive into using Kubernetes, Ollama, and LangChain to build a next-level AI application. Perfect for developers, network engineers, and AI enthusiasts looking to harness the power of multiple LLMs.
🔗 [Add links to related resources, repositories, or documentation]
🎥 Watch Part One here: [Add link to Part One]
👍 Don’t forget to like, subscribe, and hit the bell icon for updates!
#AI #Kubernetes #Ollama #LangChain #Networking #LLM #PCAPAnalysis #InfrastructureAsCode #Minikube