Skip to main content

LocalAssistant (locas) is an AI designed to be used in CLI. (Currently in development)

Project description

LocalAssistant

Locas - your local assistant

icon

Your CLI friend.


>> locas -h

usage: locas [-h] [-v] [-V] COMMAND ...

LocalAssistant (locas) is an AI designed to be used in CLI.

options:
  -h, --help          show this help message and exit
  -v, --verbose       show debug messages (Can be used multiple times for higher level: CRITICAL[v] -> DEBUG[vvvv])
  -V, --version       show program's version number and exit

commands:
  built-in commands (type 'locas COMMAND -h' for better description)

  COMMAND
    download          Download models from Hugging Face
    config            Configurate LocalAssistant.
    user              Config user.
    chat              Chat with models for limited lines. (no history saved)
    start             Chat with models using history.
    self-destruction  LocalAssistant's self-destruction.

Installing

Download locas_installer.py, and let magic happens.

python3 locas_installer.py

Let's try if it works:

locas.cmd -h

Preparing

To chat, we will need model! You can download other models you want. Below is my recommend for first use (Like a starter pack.)

For text generation: (Choose other models from here.)

locas.cmd download -n qwen Qwen/Qwen2.5-1.5B-Instruct 1

For sentence transformer: (Choose other models from here.)

locas.cmd download -n minilm sentence-transformers/all-MiniLM-L6-v2 2

For cross encoder: (Choose other models from here.)

locas.cmd download -n msmarco cross-encoder/ms-marco-MiniLM-L-6-v2 3

Running

By default, locas works at most of the time:

(Unix user may try locas.cmd ... first. Window user can use both locas and locas.cmd)

locas ...

Learn more about useful functions:

locas -h

To deactivate: (It uses python's virtual environment)

deactivate

Removing

locas self-destruction

License

GNU GPLv3


Disclaimer

This AI was designed to communicating with Hugging Face models in CLI. Please do not use this AI for any unethical reasons. Any damages from abusing this application will not be the responsibility of the author.

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

localassistant-1.1.0.tar.gz (31.4 kB view details)

Uploaded Source

Built Distribution

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

LocalAssistant-1.1.0-py3-none-any.whl (36.2 kB view details)

Uploaded Python 3

File details

Details for the file localassistant-1.1.0.tar.gz.

File metadata

  • Download URL: localassistant-1.1.0.tar.gz
  • Upload date:
  • Size: 31.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for localassistant-1.1.0.tar.gz
Algorithm Hash digest
SHA256 81d5fd8c27fa7c01d8fc82b5a1258136a17af7cb6c87d5d79d16ce0e439e254e
MD5 bb8c21c2881349d743ba506832e39302
BLAKE2b-256 928bacd0c41847660f3f772347e1e870f47980d47a31243ef7137bf38fcbfdb7

See more details on using hashes here.

Provenance

The following attestation bundles were made for localassistant-1.1.0.tar.gz:

Publisher: python-publish.yml on Linos1391/LocalAssistant

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file LocalAssistant-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: LocalAssistant-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 36.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for LocalAssistant-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 092def8a8b0509129048447a47f3602c2198e58338129da7330d725bbba86a8b
MD5 fd62334b1ee3c920f792159155557efb
BLAKE2b-256 1dade5ddf8007fa9c09c8c75f621a38e22effdf78b020a2829d7d87bca28c1ef

See more details on using hashes here.

Provenance

The following attestation bundles were made for LocalAssistant-1.1.0-py3-none-any.whl:

Publisher: python-publish.yml on Linos1391/LocalAssistant

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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