PinnedJohn AdeojoinAI MindA Quick Tutorial on Multi-Agent Workflows with AutoGenDeveloping a Multi-Agent RAG for Open-Domain QA on WikipediaNov 8, 2023Nov 8, 2023
John AdeojoinAI MindAutoGen isn’t Practical for Real-world Applications, YetWhy AutoGen is Impractical with the Current Generation of LLMsFeb 125Feb 125
John AdeojoinAI MindYour Guide to the LLM EcosystemFrom models to frontends, everything you should know about the LLM ecosystemFeb 74Feb 74
John AdeojoinAI MindDeploy Mixtral Quickly & Cheaply!Deploying Mixtral with Runpod and vLLM for LangChain, Haystack, LlamaIndex, and AutoGenJan 30Jan 30
John AdeojoinAI MindBuilding Flawless Chatbots with Open-Source LLMs5 Engineering Tips For Developing Chatbots with Open-Source Large Language ModelsJan 22Jan 22
John AdeojoinAI Mind7 Things to Know About Fine-Tuning Open-Source LLMs, and RAGEngineering Wisdom from Building a themed RAG pipelineJan 101Jan 101
John AdeojoinAI MindZapier Gmail Automation: How we Automate Mundane Tasks and Save HoursStreamlining with Zapier and OpenAI WorkflowsJan 2Jan 2
John AdeojoinAI MindExplaining How LLMs Work Through Weather Forecasting AnalogiesA Concrete and Memorable Explanation of Transformers and their Inner WorkingsDec 14, 20231Dec 14, 20231
John AdeojoinAI MindWhat do Freestlye Rap Battles Reveal About Creativity in LLMs?Pitting Open Source LLMs Against GPT-4 Turbo in Rap BattlesDec 6, 2023Dec 6, 2023
John AdeojoinAI MindHow to Deploy (Large) Open Source LLMsDeploying Llama-2 70B with Runpod and vLLM’s OpenAI Endpoint in AutoGenNov 30, 20234Nov 30, 20234
