> ## Documentation Index > Fetch the complete documentation index at: https://docs.atoma.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create embeddings > This endpoint follows the OpenAI API format for generating vector embeddings from input text. The handler receives pre-processed metadata from middleware and forwards the request to the selected node. # Returns * `Ok(Response)` - The embeddings response from the processing node * `Err(AtomaProxyError)` - An error status code if any step fails ## Errors * `INTERNAL_SERVER_ERROR` - Processing or node communication failures ## OpenAPI ````yaml cloud-api-reference/openapi.yml post /v1/embeddings openapi: 3.1.0 info: title: atoma-proxy description: '' license: name: Apache-2.0 identifier: Apache-2.0 version: 0.1.0 servers: - url: https://api.atoma.network security: [] tags: - name: Completions description: OpenAI's API completions v1 endpoint - name: Confidential Completions description: Atoma's API confidential completions v1 endpoint - name: Chat description: OpenAI's API chat completions v1 endpoint - name: Confidential Chat description: Atoma's API confidential chat completions v1 endpoint - name: Confidential Embeddings description: Atoma's API confidential embeddings v1 endpoint - name: Confidential Images description: Atoma's API confidential images v1 endpoint - name: Embeddings description: OpenAI's API embeddings v1 endpoint - name: Health description: Health check - name: Images description: OpenAI's API images v1 endpoint - name: Models description: OpenAI's API models v1 endpoint - name: Nodes description: Nodes Management - name: Node Public Key Selection description: Node public key selection paths: /v1/embeddings: post: tags: - Embeddings summary: Create embeddings description: >- This endpoint follows the OpenAI API format for generating vector embeddings from input text. The handler receives pre-processed metadata from middleware and forwards the request to the selected node. # Returns * `Ok(Response)` - The embeddings response from the processing node * `Err(AtomaProxyError)` - An error status code if any step fails ## Errors * `INTERNAL_SERVER_ERROR` - Processing or node communication failures operationId: embeddings_create requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateEmbeddingRequest' required: true responses: '200': description: Embeddings generated successfully content: application/json: schema: $ref: '#/components/schemas/CreateEmbeddingResponse' '400': description: Bad request '401': description: Unauthorized '500': description: Internal server error security: - bearerAuth: [] x-codeSamples: - lang: typescript label: embeddings_create source: |- import { AtomaSDK } from "atoma-sdk"; const atomaSDK = new AtomaSDK({ bearerAuth: process.env["ATOMASDK_BEARER_AUTH"] ?? "", }); async function run() { const result = await atomaSDK.embeddings.create({ model: "intfloat/multilingual-e5-large-instruct", input: "The quick brown fox jumped over the lazy dog", encoding_format: "float", }); // Handle the result console.log(result); } run(); - lang: python label: embeddings_create source: |- from atoma_sdk import AtomaSDK import os with AtomaSDK( bearer_auth=os.getenv("ATOMASDK_BEARER_AUTH", ""), ) as atoma_sdk: res = atoma_sdk.embeddings.create( input_="The quick brown fox jumped over the lazy dog", model="intfloat/multilingual-e5-large-instruct", encoding_format="float" ) print(res) components: schemas: CreateEmbeddingRequest: type: object description: Request object for creating embeddings required: - model - input properties: dimensions: type: - integer - 'null' format: int32 description: >- The number of dimensions the resulting output embeddings should have. minimum: 0 encoding_format: type: - string - 'null' description: |- The format to return the embeddings in. Can be "float" or "base64". Defaults to "float" example: float input: $ref: '#/components/schemas/EmbeddingInput' description: >- Input text to get embeddings for. Can be a string or array of strings. Each input must not exceed the max input tokens for the model model: type: string description: ID of the model to use. example: intfloat/multilingual-e5-large-instruct user: type: - string - 'null' description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. example: user-1234 CreateEmbeddingResponse: type: object description: Response object from creating embeddings required: - object - model - data - usage properties: data: type: array items: $ref: '#/components/schemas/EmbeddingObject' description: List of embedding objects model: type: string description: The model used for generating embeddings example: intfloat/multilingual-e5-large-instruct object: type: string description: The object type, which is always "list" example: list usage: $ref: '#/components/schemas/EmbeddingUsage' description: Usage statistics for the request EmbeddingInput: oneOf: - type: string example: The quick brown fox jumped over the lazy dog - type: array items: type: string example: '["The quick brown fox", "jumped over the lazy dog"]' EmbeddingObject: type: object description: Individual embedding object in the response required: - object - embedding - index properties: embedding: type: array items: type: number format: float description: The embedding vector example: '[0.0023064255, -0.009327292]' index: type: integer description: Index of the embedding in the list of embeddings example: 0 minimum: 0 object: type: string description: The object type, which is always "embedding" example: embedding EmbeddingUsage: type: object description: Usage information for the embeddings request required: - prompt_tokens - total_tokens properties: prompt_tokens: type: integer format: int32 description: Number of tokens in the prompt example: 8 minimum: 0 total_tokens: type: integer format: int32 description: Total tokens used in the request example: 8 minimum: 0 securitySchemes: bearerAuth: type: http scheme: bearer ````