Installation and setup

LangChain installs from PyPI with one pip command: the langchain package brings the framework, its core types, and the runtime that runs its agents.

Last updated: 27 Sep, 2026 · LangChain 1.4

The langchain package brings langchain-core, which holds the message types and the base classes every model builds on, and langgraph, which runs the agent loop.

Installing the langchain package

pip install "langchain==1.4.2"

In a notebook, prefix it with a percent sign: %pip install "langchain==1.4.2".

Check the install

Check which version Python finds:

from importlib.metadata import version

print(version("langchain"))
print(version("langchain-core"))

Reading the version numbers

• 1.4.2 is the langchain version you pinned.
• 1.6.3 is langchain-core, pulled in as a dependency; it holds the message types and the base classes every model builds on.

Lessons 26 and 29 install what they need when they need it: a text splitter, numpy and MCP support.

Keys, for when you want a hosted modelOptional

Every lesson runs on a stand-in model you write in lesson 3. To use a hosted model instead, install its provider package and set its key as an environment variable. The real-model lesson makes the switch with init_chat_model.

Install a provider package and set its key. Groq is shown here.

pip install "langchain-groq==1.1.3"

export GROQ_API_KEY=gsk_...

Related

• Previous: LangChain overview
• Next: Messages: a conversation as a list
• Reference: Install LangChain