Skip to main content

A powerful desktop client for Mistral LLMs

Project description

desktop4mistral

A powerful desktop client for interacting with Mistral Large Language Models (LLMs)

License: GPL v3 PyPI - Version Total Downloads PyPI - Python Version PyPI - Status

Overview

desktop4mistral is a Python-based desktop application that provides a user-friendly interface for chatting with Mistral AI models. Built with PySide6, it offers a modern GUI with features like model selection, chat history, and command support.

Features

  • Interactive chat interface with Mistral LLMs
  • Support for multiple Mistral models with easy switching
  • Full Markdown support.
  • Command system (e.g., /read to fetch any local file or webpage, wiki_search to search Wikipedia, etc).
  • Some commands also support a more natural language syntax. You can, for instance, say "read the contents of /tmp/myfile.txt".
  • Use /save_markdown to save your entire chat as a markdown file, which you could use in other tools, like Obsidian.
  • Supports Python code execution. Ideally, you should first ask it to write some Python code. In the next prompt you can just say something like "run it". This way you can be sure what the model's doing.

Commands

Desktop4Mistral supports several commands.

  • /read to read a local or remote file. Can also be used to reload a previous chat session.
  • /git to read a github repository
  • /wiki_search to search Wikipedia
  • /wiki_id to look up the contents of a Wikipedia page
  • /save to save the entire chat session as a JSON file
  • /save_markdown to save the entire chat session as a markdown file
  • /talk to turn talking on or off. Uses Kokoro as the TTS model. You can expect reasonable performance on most hardware.

Screenshots

Installation

Prerequisites

  • Python 3.11 or 3.12
  • Mistral API key (get it from Mistral AI)

Quickstart

Install using pip.

pip install desktop4mistral

And run...

export MISTRAL_API_KEY='your-api-key-here'
desktop4mistral

or

python3 -m desktop4mistral.main

Setup for development

  1. Clone the repository:
git clone https://github.com/hathibelagal-dev/desktop4mistral.git
cd desktop4mistral
  1. Install the app and its dependencies:
pip3 install .

Usage

  • Launch the application
  • Select a Mistral model from the "Models" menu
  • Type your message in the input field
  • Press Ctrl+Enter or click "Send" to submit
  • View responses in the chat window

Support

For issues and feature requests, please use the GitHub Issues page.

License

This project is licensed under the GNU General Public License v3 (GPLv3) - see the LICENSE file for details.

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

desktop4mistral-0.1.2.tar.gz (164.0 kB view details)

Uploaded Source

Built Distribution

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

desktop4mistral-0.1.2-py3-none-any.whl (163.4 kB view details)

Uploaded Python 3

File details

Details for the file desktop4mistral-0.1.2.tar.gz.

File metadata

  • Download URL: desktop4mistral-0.1.2.tar.gz
  • Upload date:
  • Size: 164.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for desktop4mistral-0.1.2.tar.gz
Algorithm Hash digest
SHA256 a3907ac4b30cbb631ec0a2ec5ee904119b82708e5f96d81f51aaaebd841e3799
MD5 8c2a68c72cb302e6aaa6061f1fdbe263
BLAKE2b-256 80c728977b4040d8fdba07bf1d042bdbc9638edbf8e010f81415bf64b1de103b

See more details on using hashes here.

File details

Details for the file desktop4mistral-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for desktop4mistral-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 50edae8d64588c8adc7a34d13c5b341c1ff2629aef02250f5d30683be0e31b28
MD5 58ec7ac4f112a816fefbaa1fbaac387d
BLAKE2b-256 eaf227c35decd3a56e432389964303f1fcf3d76813bf92c55d8eb20e018560d1

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