Mistral AI

Mistral AI is a French artificial intelligence company that develops efficient and powerful language models. Their models are known for strong performance across reasoning, coding, and multilingual tasks, while maintaining competitive efficiency.

The sgcWebSockets library provides a Delphi component TsgcHTTP_API_Mistral to interact with the Mistral AI API.

Mistral API

The Mistral API provides access to Mistral models for building AI-powered applications. The API supports text generation, vision (image understanding), streaming, embeddings, JSON mode, and model listing.

Features

• Messages
  • Mistral Messages Examples

• Vision
  • Mistral Vision Examples

• Models
  • Mistral Models Examples

• Embeddings
  • Mistral Embeddings Examples

Configuration

The Mistral API uses API keys for authentication. Visit your API Keys page in the Mistral Console to retrieve the API key you'll use in your requests.

Remember that your API key is a secret! Do not share it with others or expose it in any client-side code.

This API Key must be configured in the MistralOptions.ApiKey property of the component.

Mistral := TsgcHTTP_API_Mistral.Create(nil);
Mistral.MistralOptions.ApiKey := 'YOUR_API_KEY';

Messages

Send a structured list of input messages with text content, and the model will generate the next message in the conversation.

• _CreateMessage: Creates a message with the specified model and user prompt.
  • Model: The model to use (e.g. mistral-large-latest).
  • Message: The user message content.
• _CreateMessageWithSystem: Creates a message with a system prompt.
  • System: System prompt that sets the behavior of the assistant.
• _CreateMessageStream: Creates a message with streaming (SSE) enabled. Events are delivered through the OnHTTPAPISSE event handler.
• _CreateMessageJSON: Creates a message with JSON mode enabled. The model will return a valid JSON response.
  • Model: The model to use.
  • Message: The user message content.

Vision

Mistral can understand images passed as base64-encoded content within messages.

• _CreateVisionMessage: Sends an image with a text prompt.
  • ImageBase64: The base64-encoded image data.
  • MediaType: The MIME type (image/jpeg, image/png, image/gif, image/webp).
  • Prompt: The text prompt to accompany the image.

Models

List the available Mistral models.

• _GetModels: Lists all available models.

Embeddings

Get a vector representation of a given input that can be used for semantic search, clustering, and other machine learning tasks.

• _CreateEmbeddings: Creates an embedding vector representing the input text.
  • Model: The model to use (e.g. mistral-embed).
  • Input: Input text to get embeddings for.