llm-lambda-labs

Run prompts against LLMs hosted by https://lambdalabs.com/

Installation

Install this plugin in the same environment as LLM.

llm install llm-lambda-labs

Usage

First, obtain an API key for Lambda Labs and set it like this:

llm keys set lambdalabs
# Paste key here

To see a list of available models, run this:

llm models

Run prompts like this:

llm -m lambdalabs/hermes3-405b 'short poem about a pelican with a twist'

The list of available models is fetched the first time the plugin is run. You can refresh that cached list by running:

llm lambdalabs refresh

To see a list of model information that has been stored in the cache, run this:

llm lambdalabs models

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-lambda-labs
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

llm install -e '.[test]'

To run the tests:

python -m pytest

Run this to capture new recordings of HTTP interactions for the tests:

PYTEST_LAMBDALABS_KEY="$(llm keys get lambdalabs)" pytest --record-mode once