Enrich AI Agents’ Toolbox with Anypoint APIsAI agents are equipped with Large Language Models (LLMs) as their “brains” and various tools as their “arms” and “legs.” The efficacy of…Sep 13, 2024Sep 13, 2024
How to Deploy LangGraph Agents to KubernetesLangGraph is a popular tool for developing AI agents, while Kubernetes (K8s) is the leading platform for running production applications…Sep 12, 20242Sep 12, 20242
Create an AI Agent with Llama Guard in Anypoint PlatformIn our previous story, we explored Build Production-Ready AI Agents with Anypoint Platform. AI agents are basically a bunch of APIs, and…Sep 9, 2024Sep 9, 2024
Build Production-Ready AI Agents with Anypoint PlatformAI agents are a collection of APIs (See the other story Demystify Agent Tool-Calling with the Llama 3 Model). These APIs connect to LLMs…Sep 6, 2024Sep 6, 2024
Power Your AI Agent with Anypoint Platform Secured Llama 3.1 APISelf-hosted Large Language Models (LLMs) like Llama 3.1 are getting more attention for two main reasons. Firstly, security is a concern for…Sep 2, 2024Sep 2, 2024
Secure Llama API with Anypoint Flex GatewayIn previous discussions, we explored Host Your Own Ollama Service in a Cloud Kubernetes (K8s) Cluster and Run Your Own OLLAMA in Kubernetes…Aug 30, 2024Aug 30, 2024
Understand How Llama3.1 Works — A Deep Dive Into the Model FlowLarge Language Models like Llama 3.1 are powerful, yet understanding their inner workings can be complex, especially when theory becomes…Aug 29, 20241Aug 29, 20241
Fine-Tuning Llama3.1 and Deploy to OllamaIn the last story, we explored Fine-Tuning Ollama Models with Unsloth. I’ll guide you through fine-tuning Llama 3.1 from its original FP16…Aug 28, 20245Aug 28, 20245
Demystify Agent Tool-Calling with the Llama 3 ModelAI agents are rapidly evolving, increasingly mimicking human problem-solving rather than merely functioning as intelligent chatbots. At the…Aug 24, 2024Aug 24, 2024
Prepare Your Dataset for Fine-Tuning Llama 3.1In my previous story, I walked through the process of Fine-Tuning Ollama Models with Unsloth. With the Supervised Fine-Tuning Trainer…Aug 22, 2024Aug 22, 2024
