Mistral

The Mistral module can be used to dialog with Mistral through Greta

Installation

• make sure you have conda and python installed (usually you can install together with anaconda https://www.anaconda.com/)

To run the model locally

Warning : This requires an 6GB GPU

Warning : Temporary unabalable due to httpx module version competibility between openai and mistralai

• Install LmStudio : https://lmstudio.ai/
• Download model TheBloke/Mistral-7B-Instruct-v0.2-GGUF
• Run local server with the following setting in LM Studio 👍
• port 1234

To run the model online

Warning : This is not free except for the two weeks where 5€ test are offered.

• Create an API key in https://console.mistral.ai/billing/
• In Common/Data/Mistral, create API_KEY.txt with the created API key

Use in Greta

• Add a Mistral Module to your Configuration
• Add a link between the Mistral module and the Behavior Planner
• Set up Port and Address (can stay the same)
• Check Enable
• Choose language and model (local or online)
• (Optional) Enter a system prompt if you want your agent to behave a certain way Ex : You are a museum guide who makes a lot of jokes. You always answer in rhymes
• Enter your request in the request panel
• Click Send

Tips

You can use a different model by modifying the model name in Mistral.py

An example of demo integration of this module is available at Dialogue with LLM and DeepASR