Mistral
Mistral is a platform for providing endpoints for Large Language models.
Authentication
Set your MISTRAL_API_KEY
environment variable.
Example
Use Mistral
with your Assistant
:
Params
The name identifier for the assistant.
The specific model ID used for generating responses.
The sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
The maximum number of tokens to generate in the response.
The nucleus sampling parameter. The model considers the results of the tokens with top_p probability mass.
The seed for random number generation to ensure reproducibility of results.
Enable safe mode to filter potentially harmful or inappropriate content.
Enable safe prompt mode to filter potentially harmful or inappropriate prompts.
The format of the response, either as a dictionary or as a ChatCompletionResponseFormat object.
The API key for authenticating requests to the service.
The API endpoint URL for making requests to the service.
The maximum number of retry attempts for failed requests.
The timeout duration for requests, specified in seconds.
An instance of MistralClient provided for making API requests.