LLM Chronicles #6.5: Build LLM Agents from Scratch: PAL, ReAct & Langchain in 1 Hour

In this video, I’ll guide you through building LLM agents from scratch, starting with paradigms like PAL (Program-Aided Language models) and ReAct (Reason + Act) to enhance reasoning and agent behavior. First, you’ll learn how to implement these manually. Then, I’ll show you how to achieve the same using the Langchain framework, including LangChain Expression Language (LCEL).

After that, I’ll walk you through how to switch between different language models like GPT-4, Llama 3.1, and Mixtral on platforms like TogetherAI and Groq, giving you flexibility in agent design. Finally, I’ll demonstrate how to use OpenAI’s function calling as an alternative to a direct ReAct prompt, adding another layer of functionality to your agents.

🕤 Timestamps:
00:00:54 - Overview
00:02:37 - Setup (Imports and API Keys)
00:04:02 - PAL from Scratch
00:10:12 - LLM Chains with LangChain Expression Language
00:16:58 - Switching to Llama 3.1 (TogetherAI) and Mixtral 8x7B (Groq)
00:22:02 - ReAct Agents
00:36:49 - Implementing ReAct Operational Loop
00:46:15 - Other ReAct Formats (JSON, XML, ...)
00:51:10 - LangChain ReAct Agent
00:57:09 - OpenAI Function/Tool Calling via API
01:03:00 - Chat ReAct Agent for Conversations

#LLM #Langchain #PAL #ReAct #GPT4 #LLaMA #AI #MachineLearning #OpenAI #AIagents