https://github.com/patw/multimuse

Use an LLM to answer a question from multiple perspectives
https://github.com/patw/multimuse

chatbot mistralai

Last synced: 29 days ago
JSON representation

Use an LLM to answer a question from multiple perspectives

• Host: GitHub
• URL: https://github.com/patw/multimuse
• Owner: patw
• License: mit
• Created: 2024-03-21T01:13:32.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-04-03T14:28:04.000Z (9 months ago)
• Last Synced: 2024-05-07T18:23:06.756Z (8 months ago)
• Topics: chatbot, mistralai
• Language: Python
• Homepage:
• Size: 129 KB
• Stars: 0
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MultiMuse

One of the significant benefits of Large Language Models (LLMs) is their ability to serve as a sounding board for ideas and assist in problem-solving. MultiMuse is a unique tool that allows you to configure multiple distinct personalities, each providing a fresh viewpoint on a given question. 

While its primary purpose may lean more towards entertainment than practicality, it offers an engaging experience. 

This tool is powered by Mistral.ai.

![UI Screenshot](images/ui.png)

## Basic Installation

```

pip install -r requirements.txt

```

## Configuration

* Get an API key from [Mistral.ai](https://console.mistral.ai/)

* Copy the sample.env file to .env and edit this file. 

* Use your mistral API key in the API_KEY field.

* Edit the advisors.json if you want different advisors

* APP_NAME will change the name of the app

* MODEL_NAME can be mistral-tiny (cheap to run), mistral-small, mistral-medium or mistral-large

## Running

### MacOS / Linux

```

python3 -m flask run

```

### Windows

```

flask run

```