> ## Documentation Index > Fetch the complete documentation index at: https://docs.inworld.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create embeddings > Generates embeddings for the given text input. ## OpenAPI ````yaml post /ml/v1alpha/embedding:embed openapi: 3.0.0 info: title: ai/inworld/embedding/v1alpha/embedding_service.proto version: version not set servers: - url: https://api.inworld.ai security: - inworld_basic: [] tags: - name: CreateEmbeddings paths: /ml/v1alpha/embedding:embed: post: tags: - EmbeddingService summary: Create embeddings description: Generates embeddings for the given text input. operationId: EmbeddingService_Embed requestBody: content: application/json: schema: $ref: '#/components/schemas/v1alphaEmbedRequest' examples: single_text: summary: Single text embeddings description: Simple example with a single text input value: inputs: - text: Hello Inworld! model: model: >- sentence-transformers/paraphrase-multilingual-mpnet-base-v2 serviceProvider: SERVICE_PROVIDER_INWORLD multiple_texts: summary: Multiple text embeddings description: Example with multiple text inputs for batch processing value: inputs: - text: Hello Inworld! - text: Could you please generate embeddings? - text: Thanks! model: model: >- sentence-transformers/paraphrase-multilingual-mpnet-base-v2 serviceProvider: SERVICE_PROVIDER_INWORLD semantic_search: summary: Semantic search use case description: Embeddings documents for semantic search functionality value: inputs: - text: How to implement machine learning models in production - text: Best practices for deploying AI systems at scale - text: Monitoring and observability for ML applications model: model: >- sentence-transformers/paraphrase-multilingual-mpnet-base-v2 serviceProvider: SERVICE_PROVIDER_INWORLD multilingual_content: summary: Multilingual text embedding description: Processing text in different languages value: inputs: - text: Hello, how are you today? - text: Hola, ¿cómo estás hoy? - text: Bonjour, comment allez-vous aujourd'hui? - text: こんにちは、今日はいかがですか？ model: model: >- sentence-transformers/paraphrase-multilingual-mpnet-base-v2 serviceProvider: SERVICE_PROVIDER_INWORLD long_text_content: summary: Long text embeddings description: Processing longer text content like paragraphs or articles value: inputs: - text: >- Artificial intelligence has revolutionized the way we interact with technology. From voice assistants to recommendation systems, AI is becoming increasingly integrated into our daily lives. Machine learning algorithms can now process vast amounts of data to identify patterns and make predictions with remarkable accuracy. The field continues to evolve rapidly, with new breakthroughs in deep learning, natural language processing, and computer vision emerging regularly. model: model: >- sentence-transformers/paraphrase-multilingual-mpnet-base-v2 serviceProvider: SERVICE_PROVIDER_INWORLD batch_processing_large: summary: Large batch processing description: >- Processing a larger batch of texts efficiently in a single request value: inputs: - text: Customer service inquiry about order status - text: Product return request for damaged item - text: Technical support ticket for login issues - text: Billing question about subscription charges - text: Feature request for mobile app improvement - text: Feedback on recent website update - text: Question about shipping options and delivery times - text: Request for product catalog and pricing information model: model: >- sentence-transformers/paraphrase-multilingual-mpnet-base-v2 serviceProvider: SERVICE_PROVIDER_INWORLD required: true responses: '200': description: A successful response message for Embed method content: application/json: schema: $ref: '#/components/schemas/v1alphaEmbedResponse' examples: single_embedding: summary: Single text embeddings response description: >- Real example response from DEV (api.dev.inworld.ai), values truncated. value: embeddings: - values: - -0.0034770966 - 0.014472961 - -0.0031032562 - 0.043792725 - 0.033081055 - 0.003566742 - -0.048217773 - 0.03970337 - 0.023040771 - 0.006038666 multiple_embeddings: summary: Multiple text embeddings response description: Example response for multiple text inputs embeddings value: embeddings: - values: - 0.009628296 - -0.03213501 - -0.0030879974 - 0.008979797 - 0.0146102905 - values: - 0.02420044 - -0.013900757 - 0.029541016 - -0.037628174 - 0.061950684 default: description: An unexpected error response. content: application/json: schema: $ref: '#/components/schemas/rpcStatus' x-codeSamples: - lang: bash label: cURL source: >- curl --location 'https://api.inworld.ai/ml/v1alpha/embedding:embed' \ --header "Authorization: Basic $INWORLD_API_KEY" \ --header 'Content-Type: application/json' \ --data '{ "inputs": [ { "text": "Hello Inworld!" } ], "model": { "model": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2", "serviceProvider": "SERVICE_PROVIDER_INWORLD" } }' - lang: python label: Python source: |- import requests url = "https://api.inworld.ai/ml/v1alpha/embedding:embed" headers = { "Authorization": "Basic ", "Content-Type": "application/json" } payload = { "inputs": [ {"text": "Hello Inworld!"} ], "model": { "model": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2", "serviceProvider": "SERVICE_PROVIDER_INWORLD" } } response = requests.post(url, json=payload, headers=headers) print(response.json()) - lang: javascript label: JavaScript source: |- const url = 'https://api.inworld.ai/ml/v1alpha/embedding:embed'; const response = await fetch(url, { method: 'POST', headers: { 'Authorization': 'Basic ', 'Content-Type': 'application/json', }, body: JSON.stringify({ inputs: [{ text: 'Hello Inworld!' }], model: { model: 'sentence-transformers/paraphrase-multilingual-mpnet-base-v2', serviceProvider: 'SERVICE_PROVIDER_INWORLD', }, }), }); const data = await response.json(); console.log(data); components: schemas: v1alphaEmbedRequest: type: object properties: inputs: type: array items: $ref: '#/components/schemas/v1alphaEmbedRequestInput' description: Input to embed. model: $ref: '#/components/schemas/v1alphaModelId' description: >- The ID of the model to be used to generate embeddings. If no model_id is specified, the default model will be used. See [Models](../../../models#embedding) for available models. description: >- Request message for Embed method. Contains the input texts and model configuration for the embeddings request required: - inputs - model v1alphaEmbedResponse: type: object properties: embeddings: type: array items: $ref: '#/components/schemas/v1alphaEmbedding' description: List of embeddings generated from the input messages rpcStatus: type: object properties: code: type: integer format: int32 message: type: string details: type: array items: $ref: '#/components/schemas/protobufAny' v1alphaEmbedRequestInput: type: object properties: text: type: string description: Text string input required: - text v1alphaModelId: type: object properties: model: type: string description: >- The ID of the model to be used to generate embeddings. If no model_id is specified, the default model will be used. See [Models](../../../models#embedding) for available models. serviceProvider: $ref: '#/components/schemas/v1alphaServiceProvider' description: Service provider hosting model and handling requests description: >- The ID of the model to be used to generate embeddings. If no model_id is specified, the default model will be used. See [Models](../../../models#embedding) for available models. required: - model - serviceProvider v1alphaEmbedding: type: object properties: values: type: array items: type: number format: float description: The embeddings vector, which is a list of floats required: - values protobufAny: type: object properties: '@type': type: string additionalProperties: {} v1alphaServiceProvider: type: string enum: - SERVICE_PROVIDER_UNSPECIFIED - SERVICE_PROVIDER_INWORLD - SERVICE_PROVIDER_OPENAI default: SERVICE_PROVIDER_UNSPECIFIED description: |- Service provider hosting model and handling requests. - SERVICE_PROVIDER_UNSPECIFIED: No service provider specified. Default SERVICE_PROVIDER_INWORLD will be used - SERVICE_PROVIDER_INWORLD: Inworld service provider securitySchemes: inworld_basic: type: apiKey in: header name: Authorization description: >- Should follow the format Basic {credentials}. The {credentials} consists of the Base64-encoded string of the API key and the secret in the format key:secret. You can create a key in one command with the [Inworld CLI](../../../tts/resources/inworld-cli): `inworld workspace add-key`. ````