Mistral Typescript Client

This repository is the typescript version of mistralai/client-js

You can use the Mistral JavaScript/Typescript client to interact with the Mistral AI API.

Besides, the examples in this repository are still offical examples.

Installing

You can install the library in your project using:

npm i mistral-ts

Usage

You can watch a free course on using the Mistral JavaScript client here.

Set up

import MistralClient from 'mistralai-ts';

const apiKey = process.env.MISTRAL_API_KEY || 'your_api_key';

const client = new MistralClient(apiKey);

or in commonjs

const {MistralClient} = 'mistralai-ts';

const apiKey = process.env.MISTRAL_API_KEY || 'your_api_key';

const client = new MistralClient(apiKey);

List models

const listModelsResponse = await client.listModels();
const listModels = listModelsResponse.data;
listModels.forEach((model) => {
  console.log('Model:', model);
});

Chat with streaming

const chatStreamResponse = await client.chatStream({
  model: 'mistral-tiny',
  messages: [{role: 'user', content: 'What is the best French cheese?'}],
});

console.log('Chat Stream:');
for await (const chunk of chatStreamResponse) {
  if (chunk.choices[0].delta.content !== undefined) {
    const streamText = chunk.choices[0].delta.content;
    process.stdout.write(streamText);
  }
}

Chat without streaming

const chatResponse = await client.chat({
  model: 'mistral-tiny',
  messages: [{role: 'user', content: 'What is the best French cheese?'}],
});

console.log('Chat:', chatResponse.choices[0].message.content);

Embeddings

const input = [];
for (let i = 0; i < 1; i++) {
  input.push('What is the best French cheese?');
}

const embeddingsBatchResponse = await client.embeddings({
  model: 'mistral-embed',
  input: input,
});

console.log('Embeddings Batch:', embeddingsBatchResponse.data);

Files

// Create a new file
const file = fs.readFileSync('file.jsonl');
const createdFile = await client.files.create({ file });

// List files
const files = await client.files.list();

// Retrieve a file
const retrievedFile = await client.files.retrieve({ fileId: createdFile.id });

// Delete a file
const deletedFile = await client.files.delete({ fileId: createdFile.id });

Fine-tuning Jobs

// Create a new job
const createdJob = await client.jobs.create({
  model: 'open-mistral-7B',
  trainingFiles: [trainingFile.id],
  validationFiles: [validationFile.id],
  hyperparameters: {
    trainingSteps: 10,
    learningRate: 0.0001,
  },
});

// List jobs
const jobs = await client.jobs.list();

// Retrieve a job
const retrievedJob = await client.jobs.retrieve({ jobId: createdJob.id });

// Cancel a job
const canceledJob = await client.jobs.cancel({ jobId: createdJob.id });

Run examples

You can run the examples in the examples directory by installing them locally:

cd examples
npm install .

API key setup

Running the examples requires a Mistral AI API key.

Get your own Mistral API Key: https://docs.mistral.ai/#api-access

Run the examples

MISTRAL_API_KEY='your_api_key' node chat_with_streaming.js

Persisting the API key in environment

Set your Mistral API Key as an environment variable. You only need to do this once.

# set Mistral API Key (using zsh for example)
$ echo 'export MISTRAL_API_KEY=[your_api_key]' >> ~/.zshenv

# reload the environment (or just quit and open a new terminal)
$ source ~/.zshenv

You can then run the examples without appending the API key:

node chat_with_streaming.js

After the env variable setup the client will find the MISTRAL_API_KEY by itself

import MistralClient from 'mistralai-ts';

const client = new MistralClient();

ChangeLog

• 20240705---sync the progress from the last PR
• 20240506---init the project from offical js version