Skip to content

dair-ai/maven-pe-for-llms-10

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Prompt Engineering for LLMs - Notebooks and Exercises

Welcome to the notebooks and exercises for the Prompt Engineering for LLMs course.

1. Sign up for an OpenAI Key

To run the notebooks in this repo, you are required to sign up for an OpenAI paid account.

Sign up for a paid account here: https://platform.openai.com/. Once done, you can generate an API key.

2. Check out the repo

git clone https://github.com/dair-ai/maven-pe-for-llms-10.git
cd maven-pe-for-llms-10

If you already have the repo, go into it and make sure you have the latest.

cd maven-pe-for-llms-10
git pull origin master

If you have downloaded the zipped file instead, unzip it and go into the directory.

cd maven-pe-for-llms-10

3. Setup the environment

Conda

If you don't have conda, you can install it here.

Once installed, run the following command to create a new environment called pe-for-llms.

conda create -n pe-for-llms python=3.9

Next, activate the conda environment.

conda activate pe-for-llms

Python environment

If you don't want to use conda, you can create a virtual environment using Python's venv module.

python3 -m venv .venv

Next, activate your environment (the command below is for Linux)

source .venv/bin/activate

4. Install the packages

Next, install the dependencies inside the requirements.txt file.

pip install -r requirements.txt

5. Run the Preparation Exercise

Run the prepare exercise notebook (found inside the exercises folder). Before attempting the preparation exercise, add a .env file to your root folder and add your OPENAI_API_KEY.

That's it! You're all set to start working on the notebooks and exercises.

About

Materials for Cohort 10

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published