Metadata-Version: 2.4
Name: llm-empiriolabs
Version: 0.1.0
Summary: Access EmpirioLabs models via the llm CLI
Author-email: EmpirioLabs <support@empiriolabs.ai>
License: Apache-2.0
Project-URL: Homepage, https://empiriolabs.ai
Project-URL: Documentation, https://docs.empiriolabs.ai
Project-URL: Repository, https://github.com/EmpirioLabs-ai/llm-empiriolabs
Project-URL: Issues, https://github.com/EmpirioLabs-ai/llm-empiriolabs/issues
Project-URL: Changelog, https://github.com/EmpirioLabs-ai/llm-empiriolabs/releases
Classifier: License :: OSI Approved :: Apache Software License
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: llm>=0.19
Provides-Extra: test
Requires-Dist: pytest; extra == "test"
Requires-Dist: pytest-httpx; extra == "test"
Dynamic: license-file

# llm-empiriolabs

[![PyPI](https://img.shields.io/pypi/v/llm-empiriolabs.svg)](https://pypi.org/project/llm-empiriolabs/)

[LLM](https://llm.datasette.io/) plugin for accessing [EmpirioLabs](https://empiriolabs.ai) models.

EmpirioLabs serves frontier open models (Qwen3, DeepSeek V4, GLM-5.1, Kimi K2.7 Code, MiniMax M3, and more) through one OpenAI-compatible API. Browse the full catalog at [docs.empiriolabs.ai](https://docs.empiriolabs.ai).

## Installation

Install this plugin in the same environment as [LLM](https://llm.datasette.io/).

```bash
llm install llm-empiriolabs
```

## Configuration

Set an [API key](https://platform.empiriolabs.ai) for EmpirioLabs:

```bash
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 models:

```bash
llm models list | grep -i empiriolabs
```

Run a prompt:

```bash
llm -m empiriolabs/qwen3-7-plus "Five surprising facts about octopuses"
```

Start an interactive chat:

```bash
llm chat -m empiriolabs/deepseek-v4-pro
```

Pipe content in:

```bash
cat article.txt | llm -m empiriolabs/glm-5-1 "Summarize this in three bullet points"
```

The plugin fetches the live model list from `https://api.empiriolabs.ai/v1/models` on first use (cached for an hour). If that call is unavailable it falls back to a built-in list of popular slugs:

- `empiriolabs/qwen3-7-plus`
- `empiriolabs/qwen3-7-max`
- `empiriolabs/deepseek-v4-pro`
- `empiriolabs/deepseek-v4-flash`
- `empiriolabs/glm-5-1`
- `empiriolabs/kimi-k2-7-code`
- `empiriolabs/minimax-m3`

## Development

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

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

Now install the dependencies and test dependencies:

```bash
pip install -e '.[test]'
```

To run the tests:

```bash
pytest
```

## License

Apache-2.0
