LangChain Agent Executor Deep Dive

Description

In this video, we will continue from the introduction to agents and dive deeper into agents. Learning how to build our custom agent execution loop for v0.3 of LangChain. When we talk about agents, a significant part of an "agent" is simple code logic, iteratively rerunning LLM calls and processing their output. The exact logic varies significantly, but one well-known example is the ReAct agent. Reason + Action (ReAct) agents use iterative reasoning and action steps to incorporate chain-of-thought and tool-use into their execution. During the reasoning step, the LLM generates the steps to take to answer the query. Next, the LLM generates the action input, which our code logic parses into a tool call. Following our action step, we get an observation from the tool call. Then, we feed the observation back into the agent executor logic for a final answer or further reasoning and action steps. The agent and agent executor we will be building will follow this pattern. 🔗 Full Course: https://www.aurelio.ai/course/langchain 📌 Article and code: https://www.jamesbriggs.io/langchain-agent-executor 👾 Discord: https://discord.gg/c5QtDB9RAP Twitter: https://twitter.com/jamescalam LinkedIn: https://www.linkedin.com/in/jamescalam/ #ai #coding #aiagents #langchain 00:00 LangChain v0.3 Agent Executor 09:26 Creating an Agent with LCEL 13:53 Executing Tool Calls 16:58 Agentic Final Answers 25:58 Building a Custom Agent Executor 32:47 Executing Multiple Tool Calls