Ambient Agent 101

Welcome to Ambient Agent 101!

Introduction

In this session, you will learn about the fundamentals of LangGraph through one of our notebooks. It builds up to an ["ambient"](https://blog.langchain.dev/introducing-ambient-agents/) agent that can manage your email with connection to the Gmail API. It's grouped into 4 sections in the notebook in `notebooks` , with accompanying code in the `src/email_assistant` directory. These section build from the basics of agents, to human-in-the-loop, and finally to memory. These all come together in an agent that we will deploy and evaluate, and the principles can be applied to other agents across a wide range of tasks.

This is a condensed version of LangChain Academy, and is intended to be run in a session with a LangChain engineer. If you're interested in going into more depth, or working through a tutorial on your own, check out LangChain Academy here! LangChain Academy has helpful pre-recorded videos from one of our LangChain engineers.


Environment Setup

Clone the Ambient Agent 101 repo

git clone https://github.com/langchain-ai/langgraph-101.git

Python Version

• Ensure you're using Python 3.11 or later.
• This version is required for optimal compatibility with LangGraph.

python3 --version

API Keys

• If you don't have an OpenAI API key, you can sign up here.
• Sign up for LangSmith here.
• Generate a LangSmith API key.

Set Environment Variables

• Create a .env file in the root directory:

# Copy the .env.example file to .env
cp .env.example .env

Alternative Models Instructions

If you are using alternative models (e.g., Anthropic, Bedrock, AzureOpenAI) instead of OpenAI, there are a few things you need to do.

• Set necessary environment variables in the `.env` file.

• Navigate to [utils.py](/src/email_assistant/utils.py), and uncomment t