O'Reilly Live Trainining - Getting Started with LLM Agents using LangChain

Setup

Conda

• Install anaconda
• This repo was tested on a Mac with python=3.11.
• Create an environment: conda create -n oreilly-agents python=3.11
• Activate your environment with: conda activate oreilly-agents
• Install requirements with: pip install -r requirements/requirements.txt
• Setup your openai API key

Pip

1. Create a Virtual Environment: Navigate to your project directory. Make sure you have python3.10 installed! If using Python 3's built-in venv: python -m venv oreilly-agents If you're using virtualenv: virtualenv oreilly-agents

2. Activate the Virtual Environment:

   • On Windows:: .\oreilly-agents\Scripts\activate
   • On macOS and Linux:: source oreilly-agents/bin/activate

3. Install Dependencies from requirements.txt:

   pip install python-dotenv
   pip install -r ./requirements/requirements.txt

4. Setup your openai API key

Remember to deactivate the virtual environment afterwards: deactivate

Setup your .env file

• Change the .env.example file to .env and add your OpenAI API key.

OPENAI_API_KEY=<your openai api key>

To use this Environment with Jupyter Notebooks:

• conda install jupyter -y
• python -m ipykernel install --user --name=oreilly-agents

Notebooks

Here are the notebooks available in the notebooks/ folder:

1. Intro LLM Agents from Scratch

2. Intro LLM Patterns and LangChain Components

3. Agents with LangChain & LangGraph

4. Intro to LangGraph

5. Local Research Agent with LangGraph

6. Local RAG Agent with LangGraph

Additional resources can be found in:

• notebooks/agent-deploy/ - Agent deployment examples
• notebooks/assets-resources/ - Supporting assets and resources
• notebooks/extra-notebooks/ - Additional example notebooks
• notebooks/extra-scripts/ - Utility scripts and helpers