llm/docs/setup.md

Setup

Installation

Install this tool using pip:

pip install llm

Or using pipx:

pipx install llm

Or using Homebrew (much slower):

brew install simonw/llm/llm

Upgrading to the latest version

If you installed using pip:

pip install -U llm

For pipx:

pipx upgrade llm

For Homebrew:

brew tap --repair simonw/llm
brew upgrade simonw/llm/llm

Installing plugins

{ref}plugins can be used to add support for other language models, including models that can run on your own device.

For example, the llm-gpt4all plugin adds support for 17 new models that can be installed on your own machine. You can install that like so:

llm install llm-gpt4all

Authentication

Many LLM models require an API key. These API keys can be provided to this tool using several different mechanisms.

You can obtain an API key for OpenAI's language models from the API keys page on their site.

Saving and using stored keys

The easiest way to store an API key is to use the llm keys set command:

llm keys set openai

You will be prompted to enter the key like this:

% llm keys set openai
Enter key:

Once stored, this key will be automatically used for subsequent calls to the API:

llm "Five ludicrous names for a pet lobster"

Keys that are stored in this way live in a file called keys.json. This file is located at the path shown when you run the following command:

llm keys path

On macOS this will be ~/Library/Application Support/io.datasette.llm/keys.json. On Linux it may be something like ~/.config/io.datasette.llm/keys.json.

Passing keys using the --key option

Keys can be passed directly using the --key option, like this:

llm "Five names for pet weasels" --key sk-my-key-goes-here

You can also pass the alias of a key stored in the keys.json file. For example, if you want to maintain a personal API key you could add that like this:

llm keys set personal

And then use it for prompts like so:

llm "Five friendly names for a pet skunk" --key personal

Keys in environment variables

Keys can also be set using an environment variable. These are different for different models.

For OpenAI models the key will be read from the OPENAI_API_KEY environment variable.

The environment variable will be used only if no --key option is passed to the command.

If no environment variable is found, the tool will fall back to checking keys.json.

You can force the tool to use the key from keys.json even if an environment variable has also been set using llm "prompt" --key openai.

Configuration

You can configure LLM in a number of different ways.

Setting a custom default model

The model used when calling llm without the -m/--model option defaults to gpt-3.5-turbo - the fastest and least expensive OpenAI model, and the same model family that powers ChatGPT.

You can use the llm models default command to set a different default model. For GPT-4 (slower and more expensive, but more capable) run this:

llm models default gpt-4

You can view the current model by running this:

llm models default

Any of the supported aliases for a model can be passed to this command.

Setting a custom directory location

This tool stores various files - prompt templates, stored keys, preferences, a database of logs - in a directory on your computer.

On macOS this is ~/Library/Application Support/io.datasette.llm/.

On Linux it may be something like ~/.config/io.datasette.llm/.

You can set a custom location for this directory by setting the LLM_USER_PATH environment variable:

export LLM_USER_PATH=/path/to/my/custom/directory

Turning SQLite logging on and off

By default, LLM will log every prompt and response you make to a SQLite database - see {ref}logging for more details.

You can turn this behavior off by default by running:

llm logs off

Or turn it back on again with:

llm logs on

Run llm logs status to see the current states of the setting.