Metadata-Version: 2.4
Name: modelcli
Version: 0.0.6a0
Summary: Universal CLI for sending prompts to any LLM model and provider.
Home-page: https://github.com/Tomigambii/modelcli
Author: Tomás Gambirassi
Author-email: tomasgambirassi@gmail.com
Project-URL: Bug Tracker, https://github.com/Tomigambii/modelcli/issues
Project-URL: Source Code, https://github.com/Tomigambii/modelcli
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: requests
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: project-url
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary


# modelcli

`modelcli` is a universal command-line interface to interact with any LLM provider or local model.

## Installation

```bash
pip install .
```

## Commands

### Add a model
```bash
modelcli configure-model --name mymodel --url http://localhost:11434/v1/chat/completions --key none --model llama3
```

### Use predefined commands
```bash
modelcli summarize "This is a long article..." --model mymodel
modelcli translate "Hola mundo" --language english --model mymodel
modelcli email "Meeting canceled" --tone formal --model mymodel
```

### Run a custom prompt
```bash
modelcli custom "List 3 interesting facts about Saturn" --model mymodel
```
