Intermediate1h54m

Functions, Tools and Agents with LangChain

Instructor: Harrison Chase

Earn an accomplishment with PRO · Updated Oct 7, 2025

Enroll for Free

Intermediate
1h54m
8 Video Lessons
6 Code Examples
1 Graded Assignment PRO
Earn an accomplishment with PRO
Updated Oct 7, 2025
Instructor: Harrison Chase
LangChain
Learn more aboutMembership PRO Plan

Enroll for Free

What you'll learn

Learn about the most recent advancements in LLM APIs.
Use LangChain Expression Language (LCEL), a new syntax to compose and customize chains and agents faster.
Apply these new capabilities by building up a conversational agent.

Course recap

PRO

This course covers OpenAI function calling and LangChain Expression Language (LCEL), then shows how to combine them for structured data extraction, tool usage/selection, and building conversational agents. Students learn to use the OpenAI functions parameter, create custom LangChain tools, implement routing between tools, and build a full conversational agent loop.

Concept map

Key concepts

OpenAI function callingFine-tuned models that accept function definitions and return structured function call parameters (name + arguments as JSON)
AI AgentsLLM-powered systems that use reasoning to decide which tools to call, forming an iterative loop until a task is complete
LangChain toolsWrapper around Python functions with name, description, and args_schema for LLM-based tool selection
RoutingUsing an LLM to determine which tool to call and extracting the inputs, then executing the selected tool
Agent loopIterative cycle of LLM reasoning, tool selection, tool execution, and result incorporation until reaching a final answer
LCEL (LangChain Expression Language)Composable chain syntax for building LLM pipelines

About this course

The landscape of LLMs and the libraries that support them has evolved rapidly in recent months. This course is designed to keep you ahead of these changes.

You’ll explore new advancements like ChatGPT’s function calling capability, and build a conversational agent using a new syntax called LangChain Expression Language (LCEL) for tasks like tagging, extraction, tool selection, and routing.

After taking this course, you’ll know how to:

Generate structured output, including function calls, using LLMs;
Use LCEL, which simplifies the customization of chains and agents, to build applications;
Apply function calling to tasks like tagging and data extraction;
Understand tool selection and routing using LangChain tools and LLM function calling – and much more.

Start applying these new capabilities to build and improve your applications today.

Who should join?

Anyone who’s interested in learning about the latest tools to build LLM-based applications. Basic Python knowledge and a familiarity with writing prompts for LLMs is recommended.