llm-empiriolabs

LLM plugin for accessing EmpirioLabs AI models.

EmpirioLabs AI is specialized AI model hosting for open, proprietary, and custom stacks. Every model it serves is listed, with its ID and price, in the live catalog at empiriolabs.ai/models.

Installation

Install this plugin in the same environment as LLM.

llm install llm-empiriolabs

Configuration

Set an API key for EmpirioLabs:

llm keys set empiriolabs
# Paste your EMPIRIOLABS_API_KEY when prompted

You can also set the EMPIRIOLABS_API_KEY environment variable instead.

Usage

List the available EmpirioLabs AI models:

llm models list | grep -i empiriolabs

Run a prompt:

llm models list | grep empiriolabs
llm -m empiriolabs/MODEL_ID "Five surprising facts about octopuses"

Start an interactive chat:

llm chat -m empiriolabs/MODEL_ID

Pipe content in:

cat article.txt | llm -m empiriolabs/MODEL_ID "Summarize this in three bullet points"

Replace MODEL_ID with any chat model ID from empiriolabs.ai/models. The plugin reads the live model list from https://api.empiriolabs.ai/v1/models (cached for an hour, and the cached copy is used when the call fails), so llm models list always shows the current chat models.

Development

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

cd llm-empiriolabs
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

pip install -e '.[test]'

To run the tests:

pytest

License

Apache-2.0