https://docs.mistral.ai/api#operation/createChatCompletion

MistralSharp is facing the same issue, as depicted here: https://discord.com/channels/1144547040454508606/1184444810279522374/1195108690353717369

Pull-request #7 fixes it.

I've been working rather quickly to implement the API, and a refactor is needed to cleanup the MistralClient class. I plan to split the GetAvailableModelsAsync() and ChatAsync() methods into smaller private methods to handle the conversion to DTO classes as they're currently quite long.

Need to implement null checks in MistralClient class.

https://docs.mistral.ai/api#operation/createEmbedding

Implement the list available models endpoint as outlined here:

https://docs.mistral.ai/api#operation/listModels

Need to add support for streaming. You can specify streamlining as a parameter in the ChatRequest class, and it is defined as:

//  Default: false
// Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events
// as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will
// hold the request open until the timeout or until completion, with the response containing the full
// result as JSON.
Stream = false,

The best way to implement it would be to add a check to the ChatAsync() method, and if the ChatRequest Stream is set to false, default to the standard HTTPClient PostAsync call. If true, then setup a stream.