Skip to main content

An AI-powered chatbot for the terminal and editor

Project description

Lovelaice: An AI-powered assistant for your terminal and editor

Lovelaice is an LLM-powered bot that sits in your terminal. It has access to your files and it can run bash commands for you. It can also access the Internet and search for answers to general questions, as well as technical ones.

Installation

Install with pip:

pip install lovelaice

Ussage

Before using Lovelaice, you will need an API key for Mistral.

export MISTRAL_API_KEY="..."

You can use lovelaice from the command line to ask something causal like:

$ lovelaice what is the meaning of life

The meaning of life is a philosophical and metaphysical question related to the significance of living or existence in general. Many different people, cultures, and religions have different beliefs about the purpose and meaning of life.

[...]

You can also ask lovelaice to do something in your terminal:

$ lovelaice how much free space do i have
:: Using Bash

Running the following code:
$ df -h | grep '/$' | awk '{ print $4 }'
[y]es / [N]o y

5,5G

You have approximately 5.5 Gigabytes of free space left on your filesystem.

NOTE: Lovelaice will always require you to explicitly agree to run any code. Make sure that you understand what the code will do, otherwise there is no guarantee your computer won't suddenly grow a hand and slap you in the face, like, literally.

Features

So far Lovelaice has both general-purpose chat capabilites, and access to bash. Here is a list of things you can try:

  • Chat with Lovelaice about casual stuff
  • Ask Lovelaice questions about your system, distribution, free space, etc.
  • Order Lovelaice to create folders, install packages, update apps, etc.
  • Order Lovelaice to set settings, turn off the wifi, restart the computer, etc.

Here are some features under active development:

  • Generate and run Python code.
  • Search in Google, crawl webpages, and answer questions using that content.
  • Read files and answer questions about their content.
  • Create and modify notes, emails, calendar entries, etc.

Contributing

Code is MIT. Just fork, clone, edit, and open a PR.

FAQ

What models do you use?

Currently, only Mistral models are integrated, but you are welcome to submit PRs to add other LLM providers, such as OpenAI.

Is this safe?

Lovelaice will never run code without your explicit consent. That being said, LLMs are known for making subtle mistakes, so never trust that the code does what Lovelaice says it do. Always read the code and make sure you understand what it does.

When in doubt, adopt the same stance as if you were copy/pasting code from a random blog somehwere in the web (because that is exactly what you're doing).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lovelaice-0.1.5.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lovelaice-0.1.5-py3-none-any.whl (8.8 kB view details)

Uploaded Python 3

File details

Details for the file lovelaice-0.1.5.tar.gz.

File metadata

  • Download URL: lovelaice-0.1.5.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.10.6 Linux/5.15.0-43-generic

File hashes

Hashes for lovelaice-0.1.5.tar.gz
Algorithm Hash digest
SHA256 583178d7867b50450663eccdaf187f6cecb89317717cdc1c9cc483dca761eae0
MD5 416cb8e68f9d229696abd83db8938fb2
BLAKE2b-256 e8dd478441ec335c095f7bebfdb83b539b5f1b62603971c3e7ebc8721451092e

See more details on using hashes here.

File details

Details for the file lovelaice-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: lovelaice-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 8.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.10.6 Linux/5.15.0-43-generic

File hashes

Hashes for lovelaice-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 6b5fb569388897915520af53ee9cc9231925c9a735a072945950d15f1fafc4b8
MD5 4da381d1397240010a05ad508e04423c
BLAKE2b-256 9ab8a378a4675eb80e72497aa57e03a5213b22639fd0c4bd40203f6d7a2b2708

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page