Welcome to LangChain Academy's Introduction to LangChain course!

This repository is the companion to the course located HERE.

• The Chrome browser is recommended
• git is recommended
• A package/project manager: uv (recommended) or pip
• note: uv is also required in Module 2, Lesson 1 to run the MCP server with uvx
• The course requires Python >=3.12, <3.14 If you use uv, it will take care of this for you. More info

Download the course repository

# Clone the repo
git clone --depth 1 https://github.com/langchain-ai/lca-lc-foundations.git
cd lca-lc-foundations

Make a copy of example.env

# Create .env file
cp example.env .env

Edit the .env file to include the keys below for Models and optionally LangSmith

• Get an OpenAI API Key here.
• Optional for Module1/Lesson1, get an Anthropic API Key here and a Google API Key here.
• Optional, Create a LangSmith account and API Key.

# Manual installs for checking: uv

# Required
OPENAI_API_KEY='your_openai_api_key_here'
TAVILY_API_KEY='your_tavily_api_key_here'

# optional, only used in Module1, Lesson 1 once
ANTHROPIC_API_KEY='your_anthropic_api_key_here'
GOOGLE_API_KEY='your_google_api_key_here'

# Optional for evaluation and tracing
LANGSMITH_API_KEY='your_langsmith_api_key_here'
# uncomment to set tracing to true when you set up your LangSmith account
#LANGSMITH_TRACING=true
LANGSMITH_PROJECT=lca-lc-foundation
# Uncomment the following if you are on the EU instance:
#LANGSMITH_ENDPOINT=https://eu.api.smith.langchain.com

Make a virtual environment and install dependencies. More info

uv sync

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt

After completing the Setup section, we recommend you run the following command to verify your environment.

uv run python env_utils.py

source .venv/bin/activate  # On Windows: .venv\Scripts\activate
python env_utils.py

If the script flags issues, see this section below.

uv run jupyter lab

source .venv/bin/activate  # On Windows: .venv\Scripts\activate
jupyter lab

Ensure you are in the notebooks/module-1 or notebooks/module-3 directory

uv run langgraph dev

source .venv/bin/activate  # On Windows: .venv\Scripts\activate
langgraph dev

This repository contains three Modules that serve as introductions to many of LangChain's most-used features.

• Foundational models
• Tools
• Short-Term Memory
• Multimodal Messages
• Project: Personal Chef

• Model Context Protocol (MCP)
• Context and State
• Multi-Agent Systems
• Project: Wedding Planner

• What is Middleware?
• Managing Long Conversations
• Human In The Loop (HITL)
• Dynamic Agents
• Project: Email Assistant
• Bonus: Agent Chat UI

What the verification procedure checks:

• ✅ Python executable location and version (must be >=3.12, <3.14)
• ✅ Virtual environment is properly activated
• ✅ Required packages are installed with correct versions
• ✅ Packages are in the correct Python version's site-packages
• ✅ Environment variables (API keys) are properly configured

Configuration Issues and Solutions:

Managing your Python version is often best done with virtual environments. This allows you to select a Python version for the course independent of the system Python version.

pyenv install 3.12
pyenv local 3.12
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

If you don't have an OpenAI API key, you can sign up here. The course primarily uses gpt-5-nano which is very inexpensive. If desired, you may also obtain additional API keys for Anthropic or Google.

This course has been created using particular models and model providers. You can use other providers, but you will need to update the API keys in the .env file and make some necessary code changes. LangChain supports many chat model providers. More Info.

Tavily is a search provider that returns search results in an LLM-friendly way. They have a generous free tier. Tavily

• Create a LangSmith account
• Create a LangSmith API key

• Update the .env file you created with your new LangSmith API Key.
• Check that LANGSMITH_TRACING is uncommented and set to true.

For more information on LangSmith, see our docs here.

Note: If you enable LangSmith tracing by setting LANGSMITH_TRACING=true in your .env file, make sure you have a valid LANGSMITH_API_KEY set. The environment verification script (env_utils.py) will warn you if tracing is enabled without a valid key.

This course uses the dotenv module to read key-value pairs from the .env file and set them in the environment in the Jupyter notebooks. They do not need to be set globally in your system environment.

Note: If you have API keys already set in your system environment, they may conflict with the ones in your .env file. The env_utils.py verification script will detect and warn you about such conflicts. By default, load_dotenv() does not override existing environment variables.

The course uses Jupyter notebooks. The Jupyter package is installed in the virtual environment and can be run as described above. Jupyter notebooks can also be edited and run in VSCode or other VSCode variants such as Windsurf or Cursor.