OSS-first docs

These docs teach the open system first: contracts, generated surfaces, runtimes, governance, and incremental adoption. Studio shows up as the operating layer on top, not as the source of truth.

ai-llm.mistral

Mistral integration providing chat completions and embedding generation.

  • Type: integration (integration)
  • Version: 1.0.0
  • Owners: platform.ai
  • Tags: ai, llm, embeddings
  • File: packages/libs/contracts-integrations/src/integrations/providers/mistral.ts
  • field.key.label
    ai-llm.mistral
    field.version.label
    1.0.0
    field.type.label
    integration (integration)
    field.title.label
    ai-llm.mistral
    field.description.label

    Mistral integration providing chat completions and embedding generation.

  • Type: integration (integration)
  • Version: 1.0.0
  • Owners: platform.ai
  • Tags: ai, llm, embeddings
  • File: packages/libs/contracts-integrations/src/integrations/providers/mistral.ts
  • field.tags.label
    ai,llm,embeddings
    field.owners.label
    platform.ai
    field.stability.label

    Mistral integration providing chat completions and embedding generation.

    Source Definition

    export const mistralIntegrationSpec = defineIntegration({
    	meta: {
    		key: 'ai-llm.mistral',
    		version: '1.0.0',
    		category: 'ai-llm',
    		title: 'Mistral Large Language Model',
    		description:
    			'Mistral integration providing chat completions and embedding generation.',
    		domain: 'ai',
    		owners: ['platform.ai'],
    		tags: ['ai', 'llm', 'embeddings'],
    		stability: StabilityEnum.Experimental,
    	},
    	supportedModes: ['managed', 'byok'],
    	transports: [
    		{ type: 'rest', baseUrl: 'https://api.mistral.ai' },
    		{ type: 'sdk', packageName: '@mistralai/mistralai' },
    	] satisfies IntegrationTransportConfig[],
    	preferredTransport: 'rest',
    	supportedAuthMethods: [
    		{ type: 'api-key', headerName: 'Authorization', prefix: 'Bearer ' },
    	] satisfies IntegrationAuthConfig[],
    	capabilities: {
    		provides: [
    			{ key: 'ai.chat', version: '1.0.0' },
    			{ key: 'ai.embeddings', version: '1.0.0' },
    		],
    	},
    	configSchema: {
    		schema: {
    			type: 'object',
    			properties: {
    				model: {
    					type: 'string',
    					description:
    						'Default chat completion model (e.g., mistral-large-latest).',
    				},
    				embeddingModel: {
    					type: 'string',
    					description: 'Embedding model identifier.',
    				},
    			},
    		},
    		example: {
    			model: 'mistral-large-latest',
    			embeddingModel: 'mistral-embed',
    		},
    	},
    	secretSchema: {
    		schema: {
    			type: 'object',
    			required: ['apiKey'],
    			properties: {
    				apiKey: {
    					type: 'string',
    					description:
    						'Mistral API key with access to chat and embeddings endpoints.',
    				},
    			},
    		},
    		example: {
    			apiKey: 'mistral-***',
    		},
    	},
    	healthCheck: {
    		method: 'custom',
    		timeoutMs: 5000,
    	},
    	docsUrl: 'https://docs.mistral.ai/platform/endpoints',
    	constraints: {
    		rateLimit: {
    			rpm: 600,
    		},
    	},
    	byokSetup: {
    		setupInstructions:
    			'Generate an API key within the Mistral console and ensure the selected models are enabled for the account.',
    		keyRotationSupported: true,
    		quotaTrackingSupported: true,
    	},
    });