Dedalus Labs Embeddings API

openapi: 3.2.0
info:
  title: Dedalus Embeddings API
  description: 'MCP gateway for AI agents. Mix-and-match any model with any tool from our marketplace.


    ## Authentication

    Use Bearer token or X-API-Key header authentication:

    ```

    Authorization: Bearer your-api-key-here

    ```

    ```

    x-api-key: your-api-key-here

    ```


    ## Available Endpoints

    - **GET /v1/models**: list available models

    - **POST /v1/chat/completions**: Chat completions with MCP tools

    - **GET /health**: Service health check'
  version: 0.0.1
servers:
- url: https://api.dedaluslabs.ai
  description: Official Dedalus API
tags:
- name: Embeddings
paths:
  /v1/embeddings:
    post:
      tags:
      - Embeddings
      summary: Create Embeddings
      description: Create embeddings using the configured provider.
      operationId: create_embeddings_v1_embeddings_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EmbeddingRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EmbeddingResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - Bearer: []
      x-codeSamples:
      - lang: typescript
        label: Typescript
        source: 'const client = new Dedalus();


          const result = await client.embeddings.create({ ...params });'
      - lang: python
        label: Python
        source: 'client = Dedalus()


          result = client.embeddings.create(**params)'
      - lang: go
        label: Go
        source: 'client := dedalus.NewClient()


          result, err := client.Embeddings.New(ctx, body githubcomdedaluslabsdedalussdkgo.EmbeddingNewParams)'
components:
  schemas:
    EmbeddingResponse:
      properties:
        data:
          items:
            $ref: '#/components/schemas/Embedding'
          type: array
          title: Data
          description: The list of embeddings generated by the model.
          x-order: 0
        model:
          type: string
          title: Model
          description: The name of the model used to generate the embedding.
          x-order: 1
        object:
          type: string
          const: list
          title: Object
          description: The object type, which is always "list".
          x-order: 2
        usage:
          $ref: '#/components/schemas/Usage'
          description: The usage information for the request.
          x-order: 3
      type: object
      required:
      - data
      - model
      - object
      - usage
      title: EmbeddingResponse
      description: 'Schema for EmbeddingResponse.


        Fields:

        - data (required): list[Embedding]

        - model (required): str

        - object (required): Literal["list"]

        - usage (required): Usage'
    Embedding:
      properties:
        index:
          type: integer
          title: Index
          description: The index of the embedding in the list of embeddings.
          x-order: 0
        embedding:
          items:
            type: number
          type: array
          title: Embedding
          description: The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](/docs/guides/embeddings).
          x-order: 1
        object:
          type: string
          const: embedding
          title: Object
          description: The object type, which is always "embedding".
          x-order: 2
      type: object
      required:
      - index
      - embedding
      - object
      title: Embedding
      description: 'Represents an embedding vector returned by embedding endpoint.


        Fields:

        - index (required): int

        - embedding (required): list[float]

        - object (required): Literal["embedding"]'
    Usage:
      properties:
        prompt_tokens:
          type: integer
          title: Prompt Tokens
          description: The number of tokens used by the prompt.
          x-order: 0
        total_tokens:
          type: integer
          title: Total Tokens
          description: The total number of tokens used by the request.
          x-order: 1
      type: object
      required:
      - prompt_tokens
      - total_tokens
      title: Usage
      description: 'The usage information for the request.


        Fields:

        - prompt_tokens (required): int

        - total_tokens (required): int'
      x-ddls-inline: true
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    EmbeddingRequest:
      properties:
        input:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
            maxItems: 2048
            minItems: 1
            title: EmbeddingRequestInputArray
          - items:
              type: integer
            type: array
            maxItems: 2048
            minItems: 1
            title: EmbeddingRequestInputArray
          - items:
              items:
                type: integer
              type: array
              minItems: 1
              title: EmbeddingRequestInputItemArray
            type: array
            maxItems: 2048
            minItems: 1
            title: EmbeddingRequestInputArray
          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. The input must not exceed the max input tokens for the model (8192 tokens for all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. In addition to the per-input token limit, all embedding  models enforce a maximum of 300,000 tokens summed across all inputs in a  single request.
          x-order: 0
        model:
          anyOf:
          - type: string
          - type: string
            enum:
            - text-embedding-ada-002
            - text-embedding-3-small
            - text-embedding-3-large
          title: Model
          description: ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them.
          x-order: 1
        encoding_format:
          type: string
          enum:
          - float
          - base64
          title: Encoding Format
          description: The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/).
          default: float
          x-order: 2
        dimensions:
          type: integer
          minimum: 1
          title: Dimensions
          description: The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models.
          x-order: 3
        user:
          type: string
          title: User
          description: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids).
          x-order: 4
      type: object
      required:
      - input
      - model
      title: EmbeddingRequest
      description: 'Schema for EmbeddingRequest.


        Fields:

        - input (required): str | Annotated[list[str], MinLen(1), MaxLen(2048), ArrayTitle("EmbeddingRequestInputArray")] | Annotated[list[int], MinLen(1), MaxLen(2048), ArrayTitle("EmbeddingRequestInputArray")] | Annotated[list[Annotated[list[int], MinLen(1), ArrayTitle("EmbeddingRequestInputItemArray")]], MinLen(1), MaxLen(2048), ArrayTitle("EmbeddingRequestInputArray")]

        - model (required): str | Literal["text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large"]

        - encoding_format (optional): Literal["float", "base64"]

        - dimensions (optional): int

        - user (optional): str'
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
  securitySchemes:
    Bearer:
      type: http
      scheme: bearer