Mistral AI Provider Integration

This skill enables you to integrate Mistral AI models into your application using the AI SDK Mistral provider. It provides access to Mistral's chat API with support for text generation, streaming, and structured outputs.

What This Skill Does

Configures and integrates the `@ai-sdk/mistral` provider package to enable:

Step-by-Step Instructions

1. Install the Mistral Provider Package

First, install the `@ai-sdk/mistral` package:

```bash

npm i @ai-sdk/mistral

```

If the AI SDK core is not already installed, also install:

```bash

npm i ai

```

2. Set Up Environment Variables

Create or update your `.env.local` file with your Mistral API key:

```

MISTRAL_API_KEY=your_mistral_api_key_here

```

The API key can be obtained from the [Mistral AI Console](https://console.mistral.ai/).

3. Import and Configure the Provider

In your code, import the Mistral provider:

```typescript

import { mistral } from '@ai-sdk/mistral';

import { generateText } from 'ai';

```

4. Use Mistral Models

Available models include:

Example implementation for text generation:

```typescript

import { mistral } from '@ai-sdk/mistral';

import { generateText } from 'ai';

const { text } = await generateText({

model: mistral('mistral-large-latest'),

prompt: 'Write a vegetarian lasagna recipe for 4 people.',

});

console.log(text);

```

5. Streaming Responses

For streaming text generation:

```typescript

import { mistral } from '@ai-sdk/mistral';

import { streamText } from 'ai';

const result = await streamText({

model: mistral('mistral-large-latest'),

prompt: 'Explain quantum computing in simple terms.',

});

for await (const textPart of result.textStream) {

process.stdout.write(textPart);

}

```

6. Structured Output Generation

Generate structured data with type safety:

```typescript

import { mistral } from '@ai-sdk/mistral';

import { generateObject } from 'ai';

import { z } from 'zod';

const { object } = await generateObject({

model: mistral('mistral-large-latest'),

schema: z.object({

recipe: z.object({

name: z.string(),

ingredients: z.array(z.string()),

steps: z.array(z.string()),

}),

}),

prompt: 'Generate a simple pasta recipe.',

});

console.log(object.recipe);

```

7. Multi-Turn Conversations

Build conversational interfaces:

```typescript

import { mistral } from '@ai-sdk/mistral';

import { generateText } from 'ai';

const { text } = await generateText({

model: mistral('mistral-large-latest'),

messages: [

{ role: 'user', content: 'What is the capital of France?' },

{ role: 'assistant', content: 'The capital of France is Paris.' },

{ role: 'user', content: 'What is its population?' },

],

});

console.log(text);

```

Configuration Options

The Mistral provider supports standard AI SDK options:

Example with options:

```typescript

const { text } = await generateText({

model: mistral('mistral-large-latest'),

prompt: 'Write a haiku about coding',

temperature: 0.7,

maxTokens: 100,

});

```

Examples

Basic Text Generation

```typescript

import { mistral } from '@ai-sdk/mistral';

import { generateText } from 'ai';

const { text } = await generateText({

model: mistral('mistral-large-latest'),

prompt: 'Explain recursion in programming',

});

```

Streaming Chat Response

```typescript

import { mistral } from '@ai-sdk/mistral';

import { streamText } from 'ai';

const result = await streamText({

model: mistral('mistral-small-latest'),

messages: [

{ role: 'user', content: 'Tell me a joke' },

],

});

for await (const chunk of result.textStream) {

process.stdout.write(chunk);

}

```

Important Notes

Related Documentation