Orq.ai Embeddings API

openapi: 3.2.0
info:
  title: orq.ai Embeddings API
  version: '2.0'
  description: orq.ai API documentation
servers:
- url: https://my.orq.ai
security:
- ApiKey: []
tags:
- name: Embeddings
paths:
  /v2/router/embeddings:
    post:
      description: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
      operationId: createEmbedding
      requestBody:
        content:
          application/json:
            examples:
              array_of_strings:
                summary: Array of strings input
                value:
                  input:
                  - The food was delicious
                  - And the waiter was friendly
                  model: openai/text-embedding-3-small
              single_string:
                summary: Single string input
                value:
                  input: The food was delicious and the waiter...
                  model: openai/text-embedding-3-small
            schema:
              additionalProperties: false
              properties:
                cache:
                  $ref: '#/components/schemas/EmbeddingCacheConfig'
                  description: Cache configuration for the request.
                dimensions:
                  description: The number of dimensions the resulting output embeddings should have.
                  format: int64
                  type: integer
                encoding_format:
                  description: The format to return the embeddings in. Can be either float or base64.
                  enum:
                  - float
                  - base64
                  type: string
                fallbacks:
                  description: Array of fallback models to use if primary model fails.
                  items:
                    $ref: '#/components/schemas/FallbackConfig'
                  type:
                  - array
                  - 'null'
                input:
                  anyOf:
                  - description: A single text string to embed. Must be non-empty.
                    minLength: 1
                    title: String
                    type: string
                  - description: An array of strings or token arrays to embed. Must be non-empty.
                    items:
                      anyOf:
                      - minLength: 1
                        type: string
                      - items:
                          type: integer
                        minItems: 1
                        type: array
                    minItems: 1
                    title: Array
                    type: array
                  description: Input text to embed, encoded as a string or array of tokens.
                load_balancer:
                  $ref: '#/components/schemas/EmbeddingLoadBalancerConfig'
                  description: Load balancer configuration for the request.
                model:
                  description: ID of the model to use.
                  type: string
                name:
                  description: The name to display on the trace. If not specified, the default system name will be used.
                  type: string
                orq:
                  $ref: '#/components/schemas/EmbeddingOrqParams'
                  description: Orq platform extension parameters. Top-level equivalents take priority when both are set.
                retry:
                  $ref: '#/components/schemas/EmbeddingRetryConfig'
                  description: Retry configuration for the request.
                timeout:
                  $ref: '#/components/schemas/EmbeddingTimeoutConfig'
                  description: Timeout configuration to apply to the request.
                user:
                  description: A unique identifier representing your end-user.
                  type: string
                fallback_on_codes:
                  description: HTTP status codes that trigger fallback. Defaults to [408,429,500,502,503,504,529]. Each code must be unique and between 400 and 599.
                  items:
                    format: int64
                    type: integer
                  maxItems: 20
                  type:
                  - array
                  - 'null'
              required:
              - model
              - input
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                additionalProperties: false
                properties:
                  data:
                    description: List of embedding objects.
                    items:
                      $ref: '#/components/schemas/PublicEmbeddingData'
                    minItems: 0
                    type:
                    - array
                    - 'null'
                  model:
                    description: ID of the model used.
                    type: string
                  object:
                    description: Always "list".
                    enum:
                    - list
                    type: string
                  usage:
                    $ref: '#/components/schemas/PublicEmbeddingUsage'
                    description: The usage information for the request.
                required:
                - object
                - data
                - model
                - usage
                type: object
          description: Returns the embedding vector.
        '401':
          description: Authentication required. See https://docs.orq.ai/reference/errors for the error codes.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/APIErrorResponse'
      summary: Create embeddings
      tags:
      - Embeddings
      x-cli-group: embeddings
      x-cli-name: create
      x-orq-gateway-group: true
      x-speakeasy-group: router.embeddings
      x-speakeasy-name-override: create
components:
  schemas:
    PublicEmbeddingUsage:
      additionalProperties: false
      properties:
        prompt_tokens:
          description: The number of tokens used by the prompt.
          format: int64
          type: integer
        total_tokens:
          description: The total number of tokens used by the request.
          format: int64
          type: integer
      required:
      - prompt_tokens
      - total_tokens
      type: object
    EmbeddingTimeoutConfig:
      additionalProperties: false
      properties:
        call_timeout:
          description: Timeout value in milliseconds.
          format: int64
          type: integer
      required:
      - call_timeout
      type: object
    APIErrorResponse:
      type: object
      additionalProperties: false
      properties:
        error:
          $ref: '#/components/schemas/APIError'
      required:
      - error
    FallbackConfig:
      additionalProperties: false
      properties:
        model:
          type: string
      required:
      - model
      type: object
    ResponseIdentity:
      additionalProperties: false
      properties:
        display_name:
          type: string
        email:
          type: string
        id:
          type: string
        metadata:
          items:
            additionalProperties: {}
            type: object
          type:
          - array
          - 'null'
        tags:
          items:
            type: string
          type:
          - array
          - 'null'
      required:
      - id
      type: object
    EmbeddingLoadBalancerModelConfig:
      additionalProperties: false
      properties:
        model:
          description: Model identifier for load balancing.
          type: string
        weight:
          description: Weight assigned to this model for load balancing.
          format: double
          type: number
      required:
      - model
      - weight
      type: object
    EmbeddingLoadBalancerConfig:
      additionalProperties: false
      properties:
        models:
          description: Array of models with weights for load balancing requests.
          items:
            $ref: '#/components/schemas/EmbeddingLoadBalancerModelConfig'
          type:
          - array
          - 'null'
        type:
          description: Load balancer type.
          enum:
          - weight_based
          type: string
      required:
      - type
      - models
      type: object
    EmbeddingOrqParams:
      additionalProperties: false
      properties:
        cache:
          $ref: '#/components/schemas/EmbeddingCacheConfig'
          description: 'Deprecated: use top-level cache instead.'
        contact:
          $ref: '#/components/schemas/EmbeddingContactParams'
          description: 'Deprecated: use identity instead. Information about the contact making the request.'
        fallbacks:
          description: 'Deprecated: use top-level fallbacks instead.'
          items:
            $ref: '#/components/schemas/FallbackConfig'
          type:
          - array
          - 'null'
        identity:
          $ref: '#/components/schemas/ResponseIdentity'
          description: Information about the identity making the request.
        load_balancer:
          $ref: '#/components/schemas/EmbeddingLoadBalancerConfig'
          description: 'Deprecated: use top-level load_balancer instead.'
        name:
          description: 'Deprecated: use top-level name instead.'
          type: string
        retry:
          $ref: '#/components/schemas/EmbeddingRetryConfig'
          description: 'Deprecated: use top-level retry instead.'
        timeout:
          $ref: '#/components/schemas/EmbeddingTimeoutConfig'
          description: 'Deprecated: use top-level timeout instead.'
      type: object
    EmbeddingContactParams:
      additionalProperties: false
      properties:
        display_name:
          type: string
        email:
          type: string
        id:
          type: string
        metadata:
          items:
            additionalProperties: {}
            type: object
          type:
          - array
          - 'null'
        tags:
          items:
            type: string
          type:
          - array
          - 'null'
      required:
      - id
      type: object
    APIError:
      additionalProperties: false
      properties:
        code:
          type:
          - string
          - 'null'
        failures: {}
        message:
          type: string
        param:
          type:
          - string
          - 'null'
        type:
          type: string
      required:
      - message
      - type
      - param
      - code
      type: object
    EmbeddingCacheConfig:
      additionalProperties: false
      properties:
        ttl:
          description: Time to live for cached responses in seconds. Maximum 259200 seconds (3 days).
          format: int64
          type: integer
        type:
          description: Cache type.
          enum:
          - exact_match
          type: string
      required:
      - type
      type: object
    EmbeddingRetryConfig:
      additionalProperties: false
      properties:
        count:
          description: Number of retry attempts (1-5).
          format: int64
          type: integer
        on_codes:
          description: HTTP status codes that trigger retry logic.
          items:
            format: int64
            type: integer
          type:
          - array
          - 'null'
      required:
      - count
      - on_codes
      type: object
    PublicEmbeddingData:
      additionalProperties: false
      properties:
        embedding:
          description: The embedding vector, which is a list of floats. The length of vector depends on the model. Can also be a base64-encoded string when encoding_format is base64.
        index:
          description: The index of the embedding in the list of embeddings.
          format: int64
          type: integer
        object:
          description: The object type, which is always "embedding".
          enum:
          - embedding
          type: string
      required:
      - object
      - index
      - embedding
      type: object
  securitySchemes:
    ApiKey:
      type: http
      scheme: bearer
      bearerFormat: JWT
externalDocs:
  url: https://docs.orq.ai
  description: orq.ai Documentation
x-speakeasy-timeout: 600000