Preparation

If you would like to follow along the code demonstrations, you will either need to (1) create an account with a provider (e.g. OpenAI, Anthropic, Google) or (2) install a local model via Ollama. The latter requires you to have a sufficiently powerful computer, but the benefit is that you can use it offline. The former requires you to have an account with a provider and generally require some small payment.

(1) Create an account with a provider

You only need to create one of the account below. Currently Google Gemini models offer a free tier.

(2) Install a local model via Ollama

I will predominantly demonstrate applications using local LLMs via Ollama. This approach requires no payment as well as no internet access after you download/pull the LLM. You do require sufficient RAM to use these models locally (at least 16GB for 13b models), so it is preferable to use a more powerful computer.

Download Ollama at https://ollama.com/download.

In addition, download at least one local LLM. Please note that these local LLMs are large (several GB) and may take some time (>10 minutes) to download. I will mainly use llama3.1:8b which can be downloaded/pulled by using the command below in the terminal (not the R console):

ollama pull llama3.1:8b

If you do not have a large RAM (<8GB), you may try a smaller model such as llama3.2:1b (but its output may not be as accurate):

ollama pull llama3.2:1b

To check that ollama is installed properly, open a terminal and start ollama.

ollama serve

Check the

ollama --version

Software installation

To follow the code demonstrations on your own computer, please make sure to install the following software before the start of the workshop.

  • Latest R (or at least version 4) https://cran.r-project.org/
  • An Integrated Development Environment (IDE) for R such as RStudio
  • The following R packages by running the commands below in the R console:
install.packages(c('usethis', 'tidyverse', 'ellmer'))