Build intelligent agentic systems! Discover the key components of LangChain agents, including how prompts, LLMs, and tools work together for reasoning and action. You'll set up an agent with OpenAI's API, define custom tools, and tackle real-world tasks like math calculations. Plus, explore how LangChain organizes data using graphs, nodes, and edges.

Agents in LangChain

Creating a ReAct agent

Components of LangChain agents

Building custom tools

Create a tool for math calculations

Integrating custom tools and queries

Conversation with a ReAct agent

Conversation setup

Ask questions about conversation history

The Essentials of LangChain agents

Build dynamic, tool-augmented chatbots with LangChain and LangGraph! You’ll explore how to create a chatbot that adapts based on user input by defining states and integrating external APIs for real-time information retrieval. You'll connect these components into a responsive graph structure, enabling smooth transitions between conversation and tool-assisted responses. By the end, you’ll have a visually represented chatbot framework with enhanced reasoning and multi-step workflows.

Building graphs for chatbots

Graph and agent states

Adding nodes and edges

Generating chatbot responses

Queries and responses

Generate a graph diagram

Adding external tools to a chatbot

Build a Wikipedia tool

Add a tool to a graph

Adding memory and conversation

Visualize the graph and return tool outputs

Adding graph memory

Using graph memory for conversation

Building Chatbots with LangGraph

Expand your chatbot with dynamic tools and memory! Define and integrate multiple tools into flexible workflows, build functions for dynamic tool calling, and configure your chatbot for multiple-tool handling. Organize memory and outputs to enable interleaved, multi-turn conversations. By the end, you'll have created a sophisticated chatbot capable of complex interactions.

Defining multiple tools

Build a tool that invokes the LLM

Build a tool with Python code

Binding multiple tools

Defining nodes and edges for flexible function calling

Define a function that stops the chatbot

Create a function to return an LLM response

Create the graph workflow for multiple tools

Organize chatbot outputs with memory

Configure outputs for multiple tools

Enable multi-turn conversation with memory

Congratulations!

Build Dynamic Chat Agents

Every day, intelligent systems are transforming industries—whether it's through automated customer support, personalized recommendations, or dynamic data processing. Agentic workflows, which integrate language models and tools to perform complex tasks, are at the forefront of this transformation. This course breaks down the essential components of agentic workflows and explains how to build, customize, and optimize them. You'll learn the key principles behind LangChain agents, including configuring prompts, integrating tools, and managing complex workflows with LangGraph. By the end of this course, you'll be equipped to build intelligent systems that automate complex tasks, enhance productivity, and provide dynamic solutions tailored to specific business needs.

Agentic workflows that integrate LLMs and tools to perform nuanced tasks are at the forefront of the AI transformation. In this course, you'll learn the key principles behind LangChain agents, including configuring prompts, integrating tools, and managing complex workflows. By the end of this course, you'll be able to build intelligent systems that automate complex tasks, enhance productivity, and provide dynamic solutions tailored to specific business needs.
<h2>Master the Essentials of LangChain Agents</h2>
You'll learn how to integrate prompts, language models, and tools into workflows using the Reasoning and Action (ReAct) framework. Following that, you'll be able to set up agentic workflows, configure tools, and understand the core principles of LangChain agents while visualizing these workflows with LangGraph. You'll build custom agents, set up tools for accessing external data sources like the Wikipedia API, and manage agent states. You'll be guided through defining nodes and edges, creating conditional pathways, and assembling complex workflows that adapt to varying conditions.
<h2>Build Dynamic Chat Agents</h2>
Finally, you'll learn to monitor messages, define nodes for flexible function calling, and configure your chatbot for multiple-tool handling. By the end of this course, you'll be able to build intelligent systems that automate complex tasks, enhance productivity, and provide dynamic solutions tailored to specific business needs.

Developing LLM Applications with LangChain

Get to grips with the foundational components of LangChain agents and build custom chat agents.

Build dynamic LangChain agents

Designing Agentic Systems with LangChain

Developing Applications with LangChain

Founder & AI Engineer, Genverv, Ltd.

Building a multi-tool workflow

Define workflow functions

Create a stop condition function

Create a dynamic tool caller

Create the graph

Adding memory

Let's practice!

https://s3.amazonaws.com/assets.datacamp.com/production/course_37994/subtitles/course_37994_cfc856feff1ef03487ae520ebb7b1e4b.vtt

Build Dynamic Chat Agents - Defining nodes and edges for flexible function calling

Defining nodes and edges for flexible function calling

Create Your Free Account