Mixedbread extractions API

openapi: 3.1.0
info:
  title: Mixedbread admin extractions API
  version: 0.1.0
  description: Mixedbread admin endpoints extracted from the canonical OpenAPI spec at https://api.mixedbread.com/openapi.json
servers:
- url: https://api.mixedbread.com
  description: mixedbread ai production server
- url: https://api.dev.mixedbread.com
  description: mixedbread ai development server
- url: http://127.0.0.1:8000
  description: mixedbread local server
- url: http://localhost:8000
  description: mixedbread local server
tags:
- name: extractions
paths:
  /v1/extractions/jobs:
    post:
      tags:
      - extractions
      summary: Start an extraction job
      description: "Start an extraction job for the provided file and schema.\n\nArgs:\n    params: The parameters for creating an extraction job.\n\nReturns:\n    The created extraction job."
      operationId: create_extraction_job
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractJobCreateParams'
              description: The parameters for creating an extraction job
        required: true
      responses:
        '200':
          description: The created extraction job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionJob'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - ApiKeyAuth: []
  /v1/extractions/jobs/{job_id}:
    get:
      tags:
      - extractions
      summary: Get extraction job result
      description: "Get detailed information about a specific extraction job.\n\nArgs:\n    job_id: The ID of the extraction job.\n\nReturns:\n    Detailed information about the extraction job."
      operationId: retrieve_extraction_job
      security:
      - ApiKeyAuth: []
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the extraction job to retrieve
          title: Job Id
        description: The ID of the extraction job to retrieve
      responses:
        '200':
          description: Detailed information about an extraction job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionJob'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/extractions/schema:
    post:
      tags:
      - extractions
      summary: Create a schema
      description: "Create a schema with the provided parameters.\n\nArgs:\n    params: The parameters for creating a schema.\n\nReturns:\n    The created schema."
      operationId: create_schema
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/JsonSchemaCreateParams'
              description: The parameters for creating a schema
        required: true
      responses:
        '200':
          description: The created schema
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreatedJsonSchema'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - ApiKeyAuth: []
  /v1/extractions/schema/enhance:
    post:
      tags:
      - extractions
      summary: Enhance a schema
      description: "Enhance a schema by enriching the descriptions to aid extraction.\n\nArgs:\n    params: The parameters for enhancing a schema.\n\nReturns:\n    The enhanced schema."
      operationId: enhance_schema
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/JsonSchemaEnhanceParams'
              description: The parameters for enhancing a schema
        required: true
      responses:
        '200':
          description: The enhanced schema
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EnhancedJsonSchema'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - ApiKeyAuth: []
  /v1/extractions/schema/validate:
    post:
      tags:
      - extractions
      summary: Validate a schema
      description: "Validate a schema.\n\nArgs:\n    params: The parameters for validating a schema.\n\nReturns:\n    The validation result."
      operationId: validate_schema
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/JsonSchemaValidateParams'
              description: The parameters for validating a schema
        required: true
      responses:
        '200':
          description: The validation result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidatedJsonSchema'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - ApiKeyAuth: []
  /v1/extractions/content:
    post:
      tags:
      - extractions
      summary: Extract content from a string
      description: "Extract content from a string using the provided schema.\n\nArgs:\n    params: The parameters for extracting content from a string.\n\nReturns:\n    The extracted content."
      operationId: extract_content
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractContentCreateParams'
              description: The parameters for extracting content from a string
        required: true
      responses:
        '200':
          description: The extracted content
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResult'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - ApiKeyAuth: []
components:
  schemas:
    ValidatedJsonSchema:
      properties:
        is_valid:
          type: boolean
          title: Is Valid
          description: Whether the schema is valid
        errors:
          items:
            type: string
          type: array
          title: Errors
          description: List of validation errors
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The validated JSON schema
      type: object
      required:
      - is_valid
      - errors
      - json_schema
      title: ValidatedJsonSchema
      description: Result of validating a JSON schema.
    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
    ExtractContentCreateParams:
      properties:
        content:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
          - items:
              anyOf:
              - $ref: '#/components/schemas/TextInput'
              - $ref: '#/components/schemas/ImageUrlInput'
            type: array
          minLength: 1
          title: Content
          description: The content to extract from
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The JSON schema to use for extraction
        instructions:
          anyOf:
          - type: string
          - type: 'null'
          title: Instructions
          description: Additional instructions for the extraction
      type: object
      required:
      - content
      - json_schema
      title: ExtractContentCreateParams
      description: Parameters for extracting content using a schema.
    TextInput:
      properties:
        type:
          type: string
          const: text
          title: Type
          description: Input type identifier
          default: text
        text:
          type: string
          maxLength: 65536
          minLength: 1
          title: Text
          description: Text content to process
      type: object
      required:
      - text
      title: TextInput
      description: "Model for text input validation.\n\nAttributes:\n    type: Input type identifier, always \"text\"\n    text: The actual text content, with length and whitespace constraints"
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    CreatedJsonSchema:
      properties:
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The created JSON schema
      type: object
      required:
      - json_schema
      title: CreatedJsonSchema
      description: Result of creating a JSON schema.
    ExtractionJob:
      properties:
        id:
          type: string
          format: uuid
          title: Id
          description: Unique identifier for the extraction job
        organization_id:
          type: string
          format: uuid
          title: Organization Id
          description: ID of the organization that owns this job
        file_id:
          type: string
          format: uuid
          title: File Id
          description: ID of the file being extracted
        created_at:
          type: string
          format: date-time
          title: Created At
          description: When the job was created
        updated_at:
          type: string
          format: date-time
          title: Updated At
          description: When the job was last updated
        started_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Started At
          description: When the job started processing
        finished_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Finished At
          description: When the job finished processing
        status:
          $ref: '#/components/schemas/ParsingJobStatus'
          description: Current status of the job
        result:
          anyOf:
          - $ref: '#/components/schemas/ExtractionResult'
          - type: 'null'
          description: The extraction results if completed
        error:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Error
          description: Error information if failed
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The JSON schema used for extraction
      type: object
      required:
      - id
      - organization_id
      - file_id
      - created_at
      - updated_at
      - started_at
      - finished_at
      - status
      - result
      - error
      - json_schema
      title: ExtractionJob
      description: A job for extracting structured data from documents.
    EnhancedJsonSchema:
      properties:
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The enhanced JSON schema
      type: object
      required:
      - json_schema
      title: EnhancedJsonSchema
      description: Result of enhancing a JSON schema.
    ExtractJobCreateParams:
      properties:
        file_id:
          type: string
          title: File Id
          description: The ID of the file to extract from
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The JSON schema to use for extraction
      type: object
      required:
      - file_id
      - json_schema
      title: ExtractJobCreateParams
      description: Parameters for creating an extraction job.
    ImageUrl-Input:
      properties:
        url:
          anyOf:
          - type: string
            maxLength: 2083
            minLength: 1
            format: uri
          - type: string
            pattern: data:(?P<mimetype>[\w]+\/[\w\-\+\.]+)?(?:\;name\=(?P<name>[\w\.\-%!*'~\(\)]+))?(?:\;charset\=(?P<charset>[\w\-\+\.]+))?(?P<base64>\;base64)?,(?P<data>.*)
            examples:
            - data:text/plain;charset=utf-8;base64,VGhlIHF1aWNrIGJyb3duIGZveCBqdW1wZWQgb3ZlciB0aGUgbGF6eSBkb2cu
          title: Url
          description: The image URL. Can be either a URL or a Data URI.
        format:
          type: string
          title: Format
          description: The image format/mimetype
          default: ''
      type: object
      required:
      - url
      title: ImageUrl
      description: Model for image URL validation.
    JsonSchemaCreateParams:
      properties:
        description:
          type: string
          title: Description
          description: Description of the data to extract
      type: object
      required:
      - description
      title: JsonSchemaCreateParams
      description: Parameters for creating a JSON schema.
    ParsingJobStatus:
      type: string
      enum:
      - pending
      - in_progress
      - cancelled
      - completed
      - failed
      title: ParsingJobStatus
    JsonSchemaEnhanceParams:
      properties:
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The JSON schema to enhance
      type: object
      required:
      - json_schema
      title: JsonSchemaEnhanceParams
      description: Parameters for enhancing a JSON schema.
    ExtractionResult:
      properties:
        data:
          additionalProperties: true
          type: object
          title: Data
        warnings:
          items:
            type: string
          type: array
          title: Warnings
      type: object
      required:
      - data
      - warnings
      title: ExtractionResult
      description: The result of an extraction job.
    JsonSchemaValidateParams:
      properties:
        json_schema:
          additionalProperties: true
          type: object
          title: Json Schema
          description: The JSON schema to validate
      type: object
      required:
      - json_schema
      title: JsonSchemaValidateParams
      description: Parameters for validating a JSON schema.
    ImageUrlInput:
      properties:
        type:
          type: string
          const: image_url
          title: Type
          description: Input type identifier
          default: image_url
        image_url:
          $ref: '#/components/schemas/ImageUrl-Input'
          description: The image input specification.
      type: object
      required:
      - image_url
      title: ImageUrlInput
      description: Model for image input validation.
  securitySchemes:
    ApiKeyAuth:
      type: http
      description: Api key to access Mixedbreads API
      scheme: bearer