Posted by admin

Artificial Intelligence Agents! The new trend in AI and language model innovation, giving LLMs the ability to reason through problems, call external functions/api, use tools to attack a problem, and even automatically managing other agents themselves. This video is broken into two parts, a high level overview of what it means to refer to an application as an Agent, and the second being a comprehensive deep dive into my own example, an supervisor architecture with a central manager agent that controls a social media analysis subagent, and a report writing subagent. Additional Resources - Github: https://github.com/ALucek/ai-agents-video/ @LangChain LangGraph Tutorial Series: https://www.youtube.com/playlist?list=PLfaIDFEXuae16n2TWUkKq5PgJ0w6Pkwtg OpenAI Function Calling: https://platform.openai.com/docs/guides/function-calling OpenAI Tools: https://platform.openai.com/docs/assistants/tools LangChain Agents Documentation: https://python.langchain.com/docs/modules/agents/ LangGraph Documentation: https://python.langchain.com/docs/langgraph LangSmith Trace From Example: https://smith.langchain.com/public/b6682759-8e00-494e-952a-1c29b069f6ed/r Chapters: 00:00 - Part 1: Intro to Agents 02:06 - ReAct Paper 03:30 - ChatGPT Is An Agent 04:39 - Function Calling Overview 06:36 - Function Calling & Tools 08:15 - Artistic Interpretation 10:26 - Part 2: Code Example 11:10 - Agent Supervisor Architecture 13:38 - Creating Custom Tools 16:37 - Defining Agents 19:03 - Supervisor Agent Creation 21:39 - Sub Agent Creation & Graphing 23:54 - Graph Workflow Setup 24:28 - Defining Agent Edges 26:38 - Trying it out! 27:45 - Behind the Scenes with LangSmith 32:35 - Concluding Thoughts