Zep x LangSmith: Foundations of LLM app development with LangChain.js and Zep

This article provides a step-by-step guide on building three foundational Language Learning Model (LLM) applications using TypeScript, LangChain.js, and Zep. The applications include a simple conversational bot, a Retrieval Augmented Generation app, and an agent with access to two tools. The post also discusses the use of Zep's long-term memory store for adding relevant documents, chat history memory, and rich user data to prompts without managing multiple pieces of infrastructure. Additionally, it highlights LangSmith's observability feature that provides insight into what chains and agents are doing under the hood.