FriendliAI Dedicated.Embeddings API

openapi: 3.1.0
info:
  title: Friendli Suite API Reference Container.Audio Dedicated.Embeddings API
  description: This is an OpenAPI reference of Friendli Suite API.
  termsOfService: https://friendli.ai/terms-of-service
  contact:
    name: FriendliAI Support Team
    email: support@friendli.ai
  version: 0.1.0
servers:
- url: https://api.friendli.ai
tags:
- name: Dedicated.Embeddings
paths:
  /dedicated/v1/embeddings:
    post:
      tags:
      - Dedicated.Embeddings
      summary: Embeddings
      description: Generate an embedding vector from input text or token sequence.
      operationId: dedicatedEmbeddings
      security:
      - token: []
      parameters:
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DedicatedEmbeddingsBody'
      responses:
        '200':
          description: Successfully generated embeddings.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEmbeddingsSuccess'
              examples:
                Example:
                  value:
                    id: embd-26a1e10db1311bc2adb488d2d205288b
                    model: (endpoint-id)
                    object: list
                    data:
                    - index: 0
                      object: embedding
                      embedding:
                      - 0.0023064255
                      - -0.009327292
                      - -0.0028842222
                    usage:
                      prompt_tokens: 26
                      completion_tokens: 0
                      total_tokens: 26
                    created: 1735722153
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: embeddings
      x-mint:
        metadata:
          title: Dedicated Embeddings
          sidebarTitle: Embeddings
          og:title: Dedicated Embeddings
          description: Generate an embedding vector from input text or token sequence.
          og:description: Generate an embedding vector from input text or token sequence.
        href: /openapi/dedicated/inference/embeddings
        content: 'Generate an embedding vector from input text or token sequence.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.'
components:
  schemas:
    TextUsage:
      properties:
        prompt_tokens:
          type: integer
          title: Prompt Tokens
          description: Number of tokens in the prompt.
          examples:
          - 5
        completion_tokens:
          type: integer
          title: Completion Tokens
          description: Number of tokens in the generated completions.
          examples:
          - 7
        total_tokens:
          type: integer
          title: Total Tokens
          description: Total number of tokens used in the request (`prompt_tokens` + `completion_tokens`).
          examples:
          - 12
        prompt_tokens_details:
          anyOf:
          - $ref: '#/components/schemas/PromptTokensDetails'
          - type: 'null'
          description: Breakdown of tokens used in the prompt.
      type: object
      required:
      - prompt_tokens
      - completion_tokens
      - total_tokens
      title: TextUsage
    DedicatedEmbeddingsBody:
      properties:
        model:
          type: string
          title: Model
          description: ID of target endpoint. If you want to send request to specific adapter, use the format "YOUR_ENDPOINT_ID:YOUR_ADAPTER_ROUTE". Otherwise, you can just use "YOUR_ENDPOINT_ID" alone.
          examples:
          - (endpoint-id)
        input:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
          - type: 'null'
          title: Input
          description: 'Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays.


            Either `input` or `tokens` field is required.'
          examples:
          - The food was delicious and the waiter...
        tokens:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Tokens
          description: 'The tokenized prompt (i.e., input tokens).


            Either `input` or `tokens` field is required.'
        encoding_format:
          anyOf:
          - type: string
            enum:
            - float
            - base64
          - type: 'null'
          title: Encoding Format
          description: The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/).
          default: float
      type: object
      required:
      - model
      title: DedicatedEmbeddingsBody
      example:
        encoding_format: float
        input: The food was delicious and the waiter...
        model: (endpoint-id)
    EmbeddingObject:
      properties:
        index:
          type: integer
          title: Index
          description: The index of the embedding in the list of embeddings.
        object:
          type: string
          const: embedding
          title: Object
          description: The object type, which is always set to `embedding`.
        embedding:
          anyOf:
          - items:
              type: number
            type: array
          - type: string
            format: binary
          title: Embedding
          description: The embedding vector, which is a list of floats or a base64-encoded string. The length of vector depends on the model.
      type: object
      required:
      - index
      - object
      - embedding
      title: EmbeddingObject
    DedicatedEmbeddingsSuccess:
      properties:
        id:
          type: string
          title: Id
          description: A unique ID of the embeddings.
        model:
          anyOf:
          - type: string
          - type: 'null'
          title: Model
          description: The model to generate the embeddings. For dedicated endpoints, it returns the endpoint ID.
        object:
          type: string
          const: list
          title: Object
          description: The object type, which is always set to `list`.
        data:
          items:
            $ref: '#/components/schemas/EmbeddingObject'
          type: array
          title: Data
          description: A list of embedding objects.
        usage:
          $ref: '#/components/schemas/TextUsage'
        created:
          type: integer
          title: Created
          description: The Unix timestamp (in seconds) for when the embeddings were created.
      type: object
      required:
      - id
      - object
      - data
      - usage
      - created
      title: DedicatedEmbeddingsSuccess
    PromptTokensDetails:
      properties:
        cached_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cached Tokens
          description: Cached tokens present in the prompt.
      type: object
      title: PromptTokensDetails
  securitySchemes:
    token:
      type: http
      description: 'When using Friendli Suite API for inference requests, you need to provide a **Friendli Token** for authentication and authorization purposes.


        For more detailed information, please refer [here](https://friendli.ai/docs/openapi/introduction#authentication).'
      scheme: bearer
x-speakeasy-retries:
  strategy: backoff
  backoff:
    initialInterval: 500
    maxInterval: 60000
    maxElapsedTime: 3600000
    exponent: 1.5
  statusCodes:
  - 429
  - 500
  - 502
  - 503
  - 504
  retryConnectionErrors: true