O’Reilly Live Trainining - Building Text Based Applications with the ChatGPT API and Langchain

Setup

Conda

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

Pip

1. Create a Virtual Environment:
   Navigate to your project directory. Make sure you have python 3.11 installed!
   If using Python 3’s built-in venv:

   python -m venv oreilly-chatgpt-apps
   

   If you’re using virtualenv:

   virtualenv oreilly-chatgpt-apps
   

2. Activate the Virtual Environment:

   • On Windows:

     .\oreilly-chatgpt-apps\Scripts\activate
     

   • On macOS and Linux:

     source oreilly-chatgpt-apps/bin/activate
     

3. Install Dependencies from requirements.txt:

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

4. Setup your openai API key

Remember to deactivate the virtual environment once you’re done by simply typing:

deactivate

Setup your .env file

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

To use this Environment with Jupyter Notebooks:

• pip install jupyter
• python3 -m ipykernel install --user --name=oreilly-chatgpt-apps

Notebooks

Here are the notebooks available in the notebooks/ folder:

1. Intro to ChatGPT API & Prompt Basics

   

2. Applying Prompt Engineering Strategies

   

3. Prompt Engineering Guide

   

4. Fine-tuning ChatGPT API

   

5. Intro to LangChain

   

6. Q&A with LangChain

   

7. Quiz Generator App

   

8. Notes Summarizer App

   

9. General Intro to LLMs

   

10. Prompt Engineering Techniques: Knowledge Generation

    

11. Prompt Engineering Techniques