Intro to LangSmith

Welcome to Intro to LangSmith!

Introduction

In this course, we will walk through the fundamentals of LangSmith - exploring observability, prompt engineering, evaluations, feedback mechanisms, and production monitoring. Take a look at the setup instructions below so you can follow along with any of our notebook examples.

---

Setup

Follow these instructions to make sure you have all the resources necessary for this course!

Python version

To get the most out of this course, please ensure you're using Python 3.11 or later. This version is required for optimal compatibility with LangGraph. If you're on an older version, upgrading will ensure everything runs smoothly.

python3 --version

Sign up for LangSmith

• Sign up here
• Navigate to the Settings page, and generate an API key in LangSmith.
• Create a .env file that mimics the provided .env.example. Set LANGSMITH_API_KEY in the .env file.

Set OpenAI API key

• If you don't have an OpenAI API key, you can sign up here.
• Set OPENAI_API_KEY in the .env file.

Create an environment and install dependencies

$ cd intro-to-langsmith
$ python3 -m venv intro-to-ls
$ source intro-to-ls/bin/activate
$ pip install -r requirements.txt

Self-Hosted LangSmith

Note: If you are using a self-hosted version of LangSmith, you'll need to set this environment variable in addition to the others - see this guide for more info

LANGSMITH_ENDPOINT = "<your-self-hosted-url>/api/v1"

EU Instance

Note: If your LangSmith instance is set to the EU, you'll need to set this environment variable in addition to the others.

LANGSMITH_ENDPOINT=https://eu.api.smith.langchain.com