openapi: 3.0.1 info: title: Lamini Platform Classify Embeddings API description: REST API for the Lamini enterprise LLM platform covering inference (completions), fine-tuning and Memory Tuning jobs, classification, and embeddings over open base and tuned models. All requests are authenticated with a Bearer API key and served from https://api.lamini.ai. Endpoints and request fields are derived from the official Lamini Python client (github.com/lamini-ai/lamini) and the Lamini REST API documentation. termsOfService: https://www.lamini.ai/terms contact: name: Lamini Support url: https://www.lamini.ai version: '1.0' servers: - url: https://api.lamini.ai security: - bearerAuth: [] tags: - name: Embeddings description: Text embedding generation. paths: /v1/embedding: post: operationId: createEmbedding tags: - Embeddings summary: Generate embeddings description: Encode one or more text prompts into embedding vectors for similarity search, retrieval, and indexing. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/EmbeddingRequest' responses: '200': description: Generated embedding vectors. content: application/json: schema: $ref: '#/components/schemas/EmbeddingResponse' components: schemas: EmbeddingRequest: type: object required: - prompt properties: prompt: oneOf: - type: string - type: array items: type: string description: One or more texts to embed. EmbeddingResponse: type: object properties: embedding: type: array items: type: array items: type: number description: One embedding vector per input prompt. securitySchemes: bearerAuth: type: http scheme: bearer description: 'Lamini platform API key passed as Authorization: Bearer . Requests may also include a Lamini-Version header.'