Access large language models from the command-line
Find a file
Chris Mungall 482292b7d7 Add a defaults parameter to templates. (#57)
This allows default values to be filled for templates.

For example:
```yaml
prompt: Summarize this text in the voice of $voice
defaults:
  voice: GlaDOS
```
2023-06-17 23:49:27 +01:00
.github/workflows Improvements to help, closes #40 2023-06-17 09:19:52 +01:00
docs Add a defaults parameter to templates. (#57) 2023-06-17 23:49:27 +01:00
llm Add a defaults parameter to templates. (#57) 2023-06-17 23:49:27 +01:00
tests Add a defaults parameter to templates. (#57) 2023-06-17 23:49:27 +01:00
.gitignore Initial prototype, refs #1 2023-04-01 14:28:24 -07:00
LICENSE Initial prototype, refs #1 2023-04-01 14:28:24 -07:00
README.md Badges on the documentation index page 2023-06-17 18:03:05 +01:00
setup.py Release 0.4.1 2023-06-17 22:41:09 +01:00

LLM

PyPI Documentation Changelog Tests License

Access large language models from the command-line

Full documentation: llm.datasette.io

See llm, ttok and strip-tags—CLI tools for working with ChatGPT and other LLMs for more on this project.

Installation

Install this tool using pip:

pip install llm

Or using Homebrew:

brew install simonw/llm/llm

Detailed installation instructions.

Getting started

First, create an OpenAI API key and save it to the tool like this:

llm keys set openai

This will prompt you for your key like so:

$ llm keys set openai
Enter key:

Now that you've saved a key you can run a prompt like this:

llm "Five cute names for a pet penguin"
1. Waddles
2. Pebbles
3. Bubbles
4. Flappy
5. Chilly

Read the usage instructions for more.

Help

For help, run:

llm --help

You can also use:

python -m llm --help