Module 0 - Getting Set Up

Setups

• All the notebooks related to this course can be found here, or you can download them as zip file from here.
• Suggested setup:
  • Python version: 3.11
  • Clone repo:
    • git clone <https://github.com/langchain-ai/langchain-academy.git>
  • Create an environment and install dependencies:
    • python3 -m venv lc-academy-env
    • source lc-academy-env/bin/activate
    • pip install -r requirements.txt
  • Set up LangSmith
    • After signing up for LangSmith, set the following keys in your environment:
      • LANGCHAIN_API_KEY
      • LANGCHAIN_TRACING_V2=true
  • Set up OpenAI
    • Get your OpenAI API key and set it in your environment → OPENAI_API_KEY
  • Set up Tavily for Web Search
    • Tavily Search API is a search engine optimized for LLMs and RAG, aimed at efficient, quick, and persistent search results → you can sign up here.
    • Set the TAVILY_API_KEY in your environment.
  • Set up LangGraph Studio
    • LangGraph Studio only runs in Mac. Also, it doesn’t run in Google Colab.
    • Download the latest .dmg file from here → then, install Docker Desktop for Mac here.
    • Graphs for LangGraph Studio are in the module-x/studio/ folders. To use LangGraph Studio, you will need to create a .env file with the relevant API keys. Run this from the command line to create these files for Module 1 to 4. As an example:
      • for i in {1..4}; do
        • cp module-$i/studio/.env.example module-$i/studio/.env
        • echo "OPENAI_API_KEY=\\"$OPENAI_API_KEY\\"" > module-$i/studio/.env
        • done
        • echo "TAVILY_API_KEY=\\"$TAVILY_API_KEY\\"" >> module-4/studio/.env

Module 1: Introduction

Motivation

A solitary language model is fairly limited…

… e.g., access to tools, external context, multi-step workflows.

So, many LLM applications use a control flow …

… with steps pre / post-LLM call (tool calls, retrieval, etc).