openapi: 3.0.1
info:
  title: Extend API
  description: >-
    The Extend API turns documents into high quality structured data. It exposes
    file management, synchronous and asynchronous document processors (parse,
    extract, classify, split), reusable processor definitions (extractors,
    classifiers, splitters), durable multi-step workflows and workflow runs,
    evaluation sets, and batch processing. All requests are authenticated with a
    Bearer API token and should pin an API version via the x-extend-api-version
    header.
  termsOfService: https://www.extend.ai
  contact:
    name: Extend Support
    url: https://docs.extend.ai
  version: '2026-02-09'
servers:
  - url: https://api.extend.ai
    description: Extend production API
security:
  - BearerAuth: []
tags:
  - name: Files
  - name: Parse
  - name: Extract
  - name: Classify
  - name: Split
  - name: Workflows
  - name: Workflow Runs
  - name: Evaluations
  - name: Batch
paths:
  /files/upload:
    post:
      operationId: uploadFile
      tags:
        - Files
      summary: Upload a file
      description: >-
        Upload a document to Extend and receive a file ID that can be referenced
        by processors and workflows. Supports optional conversion to PDF and
        passwords for protected PDFs.
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - name: convertToPdf
          in: query
          required: false
          schema:
            type: boolean
          description: Convert supported inputs (images, Word, PowerPoint, Excel, HTML) to PDF.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - file
              properties:
                file:
                  type: string
                  format: binary
                  description: Binary file contents.
                password:
                  type: string
                  description: Password to unlock a protected PDF.
      responses:
        '200':
          description: The uploaded file.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/File'
        default:
          $ref: '#/components/responses/ApiError'
  /files:
    get:
      operationId: listFiles
      tags:
        - Files
      summary: List files
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/NextPageToken'
        - $ref: '#/components/parameters/MaxPageSize'
      responses:
        '200':
          description: A page of files.
          content:
            application/json:
              schema:
                type: object
                properties:
                  files:
                    type: array
                    items:
                      $ref: '#/components/schemas/File'
                  nextPageToken:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
  /files/{id}:
    get:
      operationId: getFile
      tags:
        - Files
      summary: Get a file
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested file.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/File'
        default:
          $ref: '#/components/responses/ApiError'
    delete:
      operationId: deleteFile
      tags:
        - Files
      summary: Delete a file
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: Deletion confirmation.
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
        default:
          $ref: '#/components/responses/ApiError'
  /parse:
    post:
      operationId: parseFile
      tags:
        - Parse
      summary: Parse a file (synchronous)
      description: >-
        Synchronously parse a document into markdown and structured chunks. Has
        a five minute timeout and is intended for onboarding and testing; use
        POST /parse_runs for production.
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - name: responseType
          in: query
          required: false
          schema:
            type: string
            enum: [json, url]
            default: json
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ParseRequest'
      responses:
        '200':
          description: A processed parse run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ParseRun'
        default:
          $ref: '#/components/responses/ApiError'
  /parse_runs:
    post:
      operationId: createParseRun
      tags:
        - Parse
      summary: Create a parse run (asynchronous)
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ParseRequest'
      responses:
        '200':
          description: The created parse run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ParseRun'
        default:
          $ref: '#/components/responses/ApiError'
    get:
      operationId: listParseRuns
      tags:
        - Parse
      summary: List parse runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/NextPageToken'
        - $ref: '#/components/parameters/MaxPageSize'
      responses:
        '200':
          description: A page of parse runs.
          content:
            application/json:
              schema:
                type: object
                properties:
                  parseRuns:
                    type: array
                    items:
                      $ref: '#/components/schemas/ParseRun'
                  nextPageToken:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
  /parse_runs/{id}:
    get:
      operationId: getParseRun
      tags:
        - Parse
      summary: Get a parse run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested parse run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ParseRun'
        default:
          $ref: '#/components/responses/ApiError'
  /parse_runs/batch:
    post:
      operationId: batchCreateParseRuns
      tags:
        - Batch
      summary: Batch create parse runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/BatchRequest'
      responses:
        '200':
          description: The created batch run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchRun'
        default:
          $ref: '#/components/responses/ApiError'
  /extract:
    post:
      operationId: extractFile
      tags:
        - Extract
      summary: Extract from a file (synchronous)
      description: >-
        Synchronously extract structured fields from a document using an inline
        config or a saved extractor. Five minute timeout; use POST /extract_runs
        for production.
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractRequest'
      responses:
        '200':
          description: A processed extract run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /extract_runs:
    post:
      operationId: createExtractRun
      tags:
        - Extract
      summary: Create an extract run (asynchronous)
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractRequest'
      responses:
        '200':
          description: The created extract run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /extract_runs/{id}:
    get:
      operationId: getExtractRun
      tags:
        - Extract
      summary: Get an extract run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested extract run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /extract_runs/batch:
    post:
      operationId: batchCreateExtractRuns
      tags:
        - Batch
      summary: Batch create extract runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/BatchRequest'
      responses:
        '200':
          description: The created batch run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchRun'
        default:
          $ref: '#/components/responses/ApiError'
  /extractors:
    get:
      operationId: listExtractors
      tags:
        - Extract
      summary: List extractors
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/NextPageToken'
        - $ref: '#/components/parameters/MaxPageSize'
      responses:
        '200':
          description: A page of extractors.
          content:
            application/json:
              schema:
                type: object
                properties:
                  extractors:
                    type: array
                    items:
                      $ref: '#/components/schemas/Processor'
                  nextPageToken:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
    post:
      operationId: createExtractor
      tags:
        - Extract
      summary: Create an extractor
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ProcessorCreateRequest'
      responses:
        '200':
          description: The created extractor.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Processor'
        default:
          $ref: '#/components/responses/ApiError'
  /extractors/{id}:
    get:
      operationId: getExtractor
      tags:
        - Extract
      summary: Get an extractor
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested extractor.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Processor'
        default:
          $ref: '#/components/responses/ApiError'
    post:
      operationId: updateExtractor
      tags:
        - Extract
      summary: Update an extractor
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ProcessorCreateRequest'
      responses:
        '200':
          description: The updated extractor.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Processor'
        default:
          $ref: '#/components/responses/ApiError'
  /extractors/{id}/versions:
    post:
      operationId: createExtractorVersion
      tags:
        - Extract
      summary: Create an extractor version
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                releaseType:
                  type: string
                  enum: [MAJOR, MINOR, PATCH]
                description:
                  type: string
                config:
                  type: object
      responses:
        '200':
          description: The created extractor version.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Processor'
        default:
          $ref: '#/components/responses/ApiError'
  /classify:
    post:
      operationId: classifyFile
      tags:
        - Classify
      summary: Classify a file (synchronous)
      description: >-
        Synchronously classify a document using an inline config or a saved
        classifier. Five minute timeout; use POST /classify_runs for production.
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ClassifyRequest'
      responses:
        '200':
          description: A processed classify run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /classify_runs:
    post:
      operationId: createClassifyRun
      tags:
        - Classify
      summary: Create a classify run (asynchronous)
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ClassifyRequest'
      responses:
        '200':
          description: The created classify run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /classify_runs/{id}:
    get:
      operationId: getClassifyRun
      tags:
        - Classify
      summary: Get a classify run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested classify run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /classify_runs/batch:
    post:
      operationId: batchCreateClassifyRuns
      tags:
        - Batch
      summary: Batch create classify runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/BatchRequest'
      responses:
        '200':
          description: The created batch run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchRun'
        default:
          $ref: '#/components/responses/ApiError'
  /classifiers:
    get:
      operationId: listClassifiers
      tags:
        - Classify
      summary: List classifiers
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/NextPageToken'
        - $ref: '#/components/parameters/MaxPageSize'
      responses:
        '200':
          description: A page of classifiers.
          content:
            application/json:
              schema:
                type: object
                properties:
                  classifiers:
                    type: array
                    items:
                      $ref: '#/components/schemas/Processor'
                  nextPageToken:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
    post:
      operationId: createClassifier
      tags:
        - Classify
      summary: Create a classifier
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ProcessorCreateRequest'
      responses:
        '200':
          description: The created classifier.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Processor'
        default:
          $ref: '#/components/responses/ApiError'
  /split:
    post:
      operationId: splitFile
      tags:
        - Split
      summary: Split a file (synchronous)
      description: >-
        Synchronously split a multi-document file into subdocuments and classify
        each. Five minute timeout; use POST /split_runs for production.
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SplitRequest'
      responses:
        '200':
          description: A processed split run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /split_runs:
    post:
      operationId: createSplitRun
      tags:
        - Split
      summary: Create a split run (asynchronous)
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SplitRequest'
      responses:
        '200':
          description: The created split run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /split_runs/{id}:
    get:
      operationId: getSplitRun
      tags:
        - Split
      summary: Get a split run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested split run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProcessorRun'
        default:
          $ref: '#/components/responses/ApiError'
  /split_runs/batch:
    post:
      operationId: batchCreateSplitRuns
      tags:
        - Batch
      summary: Batch create split runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/BatchRequest'
      responses:
        '200':
          description: The created batch run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchRun'
        default:
          $ref: '#/components/responses/ApiError'
  /workflows:
    get:
      operationId: listWorkflows
      tags:
        - Workflows
      summary: List workflows
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/NextPageToken'
        - $ref: '#/components/parameters/MaxPageSize'
      responses:
        '200':
          description: A page of workflows.
          content:
            application/json:
              schema:
                type: object
                properties:
                  workflows:
                    type: array
                    items:
                      $ref: '#/components/schemas/Workflow'
                  nextPageToken:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
    post:
      operationId: createWorkflow
      tags:
        - Workflows
      summary: Create a workflow
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - name
              properties:
                name:
                  type: string
                description:
                  type: string
      responses:
        '200':
          description: The created workflow.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Workflow'
        default:
          $ref: '#/components/responses/ApiError'
  /workflows/{id}:
    get:
      operationId: getWorkflow
      tags:
        - Workflows
      summary: Get a workflow
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested workflow.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Workflow'
        default:
          $ref: '#/components/responses/ApiError'
  /workflow_runs:
    post:
      operationId: createWorkflowRun
      tags:
        - Workflow Runs
      summary: Create a workflow run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/WorkflowRunRequest'
      responses:
        '200':
          description: The created workflow run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/WorkflowRun'
        default:
          $ref: '#/components/responses/ApiError'
    get:
      operationId: listWorkflowRuns
      tags:
        - Workflow Runs
      summary: List workflow runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/NextPageToken'
        - $ref: '#/components/parameters/MaxPageSize'
      responses:
        '200':
          description: A page of workflow runs.
          content:
            application/json:
              schema:
                type: object
                properties:
                  workflowRuns:
                    type: array
                    items:
                      $ref: '#/components/schemas/WorkflowRun'
                  nextPageToken:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
  /workflow_runs/{id}:
    get:
      operationId: getWorkflowRun
      tags:
        - Workflow Runs
      summary: Get a workflow run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested workflow run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/WorkflowRun'
        default:
          $ref: '#/components/responses/ApiError'
    post:
      operationId: updateWorkflowRun
      tags:
        - Workflow Runs
      summary: Update a workflow run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                metadata:
                  type: object
                  additionalProperties: true
      responses:
        '200':
          description: The updated workflow run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/WorkflowRun'
        default:
          $ref: '#/components/responses/ApiError'
  /workflow_runs/batch:
    post:
      operationId: batchCreateWorkflowRuns
      tags:
        - Workflow Runs
      summary: Batch create workflow runs
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - workflow
                - inputs
              properties:
                workflow:
                  $ref: '#/components/schemas/WorkflowReference'
                inputs:
                  type: array
                  items:
                    type: object
                    properties:
                      file:
                        $ref: '#/components/schemas/FileInput'
      responses:
        '200':
          description: The created batch run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchRun'
        default:
          $ref: '#/components/responses/ApiError'
  /evaluation_sets:
    post:
      operationId: createEvaluationSet
      tags:
        - Evaluations
      summary: Create an evaluation set
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - name
                - entityId
              properties:
                name:
                  type: string
                entityId:
                  type: string
                  description: ID of the extractor, classifier, or splitter to evaluate.
                description:
                  type: string
      responses:
        '200':
          description: The created evaluation set.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationSet'
        default:
          $ref: '#/components/responses/ApiError'
  /evaluation_sets/{id}:
    get:
      operationId: getEvaluationSet
      tags:
        - Evaluations
      summary: Get an evaluation set
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested evaluation set.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationSet'
        default:
          $ref: '#/components/responses/ApiError'
  /evaluation_set_items:
    post:
      operationId: createEvaluationSetItem
      tags:
        - Evaluations
      summary: Create an evaluation set item
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - evaluationSetId
              properties:
                evaluationSetId:
                  type: string
                fileId:
                  type: string
                expectedOutput:
                  type: object
                  additionalProperties: true
      responses:
        '200':
          description: The created evaluation set item.
          content:
            application/json:
              schema:
                type: object
                properties:
                  object:
                    type: string
                    example: evaluation_set_item
                  id:
                    type: string
                  evaluationSetId:
                    type: string
        default:
          $ref: '#/components/responses/ApiError'
  /evaluation_set_runs:
    post:
      operationId: createEvaluationSetRun
      tags:
        - Evaluations
      summary: Create an evaluation set run
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - evaluationSetId
              properties:
                evaluationSetId:
                  type: string
                processorVersionId:
                  type: string
      responses:
        '200':
          description: The created evaluation set run.
          content:
            application/json:
              schema:
                type: object
                properties:
                  object:
                    type: string
                    example: evaluation_set_run
                  id:
                    type: string
                  status:
                    $ref: '#/components/schemas/RunStatus'
        default:
          $ref: '#/components/responses/ApiError'
  /batch_runs/{id}:
    get:
      operationId: getBatchRun
      tags:
        - Batch
      summary: Get a batch run
      description: >-
        Unified endpoint to retrieve a batch run created by any of the batch
        submission endpoints.
      parameters:
        - $ref: '#/components/parameters/ApiVersion'
        - $ref: '#/components/parameters/PathId'
      responses:
        '200':
          description: The requested batch run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchRun'
        default:
          $ref: '#/components/responses/ApiError'
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: Provide your Extend API token as a Bearer token in the Authorization header.
  parameters:
    ApiVersion:
      name: x-extend-api-version
      in: header
      required: false
      description: API version to pin the request to, for example 2026-02-09.
      schema:
        type: string
        example: '2026-02-09'
    PathId:
      name: id
      in: path
      required: true
      schema:
        type: string
    NextPageToken:
      name: nextPageToken
      in: query
      required: false
      schema:
        type: string
    MaxPageSize:
      name: maxPageSize
      in: query
      required: false
      schema:
        type: integer
  responses:
    ApiError:
      description: Error response.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
  schemas:
    ApiError:
      type: object
      properties:
        code:
          type: string
        message:
          type: string
        retryable:
          type: boolean
        requestId:
          type: string
    RunStatus:
      type: string
      enum:
        - PENDING
        - PROCESSING
        - PROCESSED
        - FAILED
        - CANCELLED
        - NEEDS_REVIEW
        - REJECTED
    FileFromUrl:
      type: object
      required:
        - url
      properties:
        url:
          type: string
        name:
          type: string
        settings:
          type: object
          properties:
            password:
              type: string
    FileFromId:
      type: object
      required:
        - id
      properties:
        id:
          type: string
    FileFromText:
      type: object
      required:
        - text
      properties:
        text:
          type: string
    FileInput:
      oneOf:
        - $ref: '#/components/schemas/FileFromUrl'
        - $ref: '#/components/schemas/FileFromId'
        - $ref: '#/components/schemas/FileFromText'
    RunMetadata:
      type: object
      additionalProperties: true
      description: Custom metadata for a run, up to 10KB.
    File:
      type: object
      properties:
        object:
          type: string
          example: file
        id:
          type: string
        name:
          type: string
        type:
          type: string
          enum: [PDF, CSV, IMG, TXT, DOCX, EXCEL, XML, HTML]
        presignedUrl:
          type: string
        parentFileId:
          type: string
          nullable: true
        metadata:
          type: object
          additionalProperties: true
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    ParseRequest:
      type: object
      required:
        - file
      properties:
        file:
          $ref: '#/components/schemas/FileInput'
        config:
          type: object
          description: Parse configuration (target, blocks, figures, tables, OCR options).
        metadata:
          $ref: '#/components/schemas/RunMetadata'
    ParseRun:
      type: object
      properties:
        object:
          type: string
          example: parse_run
        id:
          type: string
        status:
          $ref: '#/components/schemas/RunStatus'
        file:
          type: object
        output:
          type: object
          properties:
            chunks:
              type: array
              items:
                type: object
        config:
          type: object
        metrics:
          type: object
          properties:
            processingTimeMs:
              type: integer
            pageCount:
              type: integer
        usage:
          type: object
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    ExtractRequest:
      type: object
      required:
        - file
      properties:
        file:
          $ref: '#/components/schemas/FileInput'
        extractor:
          type: object
          properties:
            id:
              type: string
            version:
              type: string
            overrideConfig:
              type: object
        config:
          type: object
          description: Inline extract config with schema, baseProcessor, extractionRules.
        metadata:
          $ref: '#/components/schemas/RunMetadata'
    ClassifyRequest:
      type: object
      required:
        - file
      properties:
        file:
          $ref: '#/components/schemas/FileInput'
        classifier:
          type: object
          properties:
            id:
              type: string
            version:
              type: string
        config:
          type: object
          description: Inline classify config with classifications, baseProcessor, rules.
        metadata:
          $ref: '#/components/schemas/RunMetadata'
    SplitRequest:
      type: object
      required:
        - file
      properties:
        file:
          $ref: '#/components/schemas/FileInput'
        splitter:
          type: object
          properties:
            id:
              type: string
            version:
              type: string
            overrideConfig:
              type: object
        config:
          type: object
          description: Inline split config with splitClassifications, splitRules, baseProcessor.
        metadata:
          $ref: '#/components/schemas/RunMetadata'
    ProcessorRun:
      type: object
      properties:
        object:
          type: string
          example: processor_run
        id:
          type: string
        status:
          $ref: '#/components/schemas/RunStatus'
        type:
          type: string
          enum: [EXTRACT, CLASSIFY, SPLIT]
        file:
          type: object
        output:
          type: object
          additionalProperties: true
        config:
          type: object
        usage:
          type: object
        dashboardUrl:
          type: string
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    Processor:
      type: object
      properties:
        object:
          type: string
          example: processor
        id:
          type: string
        name:
          type: string
        type:
          type: string
          enum: [EXTRACT, CLASSIFY, SPLIT]
        version:
          type: string
        config:
          type: object
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    ProcessorCreateRequest:
      type: object
      required:
        - name
      properties:
        name:
          type: string
        config:
          type: object
    Workflow:
      type: object
      properties:
        object:
          type: string
          example: workflow
        id:
          type: string
        name:
          type: string
        description:
          type: string
        version:
          type: string
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    WorkflowReference:
      type: object
      required:
        - id
      properties:
        id:
          type: string
        version:
          type: string
    WorkflowRunRequest:
      type: object
      required:
        - workflow
        - file
      properties:
        workflow:
          $ref: '#/components/schemas/WorkflowReference'
        file:
          $ref: '#/components/schemas/FileInput'
        outputs:
          type: array
          items:
            type: object
        priority:
          type: integer
          default: 50
        metadata:
          $ref: '#/components/schemas/RunMetadata'
        secrets:
          type: object
          additionalProperties: true
    WorkflowRun:
      type: object
      properties:
        object:
          type: string
          example: workflow_run
        id:
          type: string
        status:
          $ref: '#/components/schemas/RunStatus'
        stepRuns:
          type: array
          items:
            type: object
        metadata:
          type: object
          additionalProperties: true
        usage:
          type: object
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    EvaluationSet:
      type: object
      properties:
        object:
          type: string
          example: evaluation_set
        id:
          type: string
        name:
          type: string
        description:
          type: string
        entity:
          type: object
          description: Summary of the associated extractor, classifier, or splitter.
        createdAt:
          type: string
          format: date-time
        updatedAt:
          type: string
          format: date-time
    BatchRequest:
      type: object
      required:
        - inputs
      properties:
        inputs:
          type: array
          items:
            type: object
            properties:
              file:
                $ref: '#/components/schemas/FileInput'
              metadata:
                $ref: '#/components/schemas/RunMetadata'
        processor:
          type: object
        config:
          type: object
    BatchRun:
      type: object
      properties:
        object:
          type: string
          example: batch_run
        id:
          type: string
        status:
          $ref: '#/components/schemas/RunStatus'
        runCount:
          type: integer
        createdAt:
          type: string
          format: date-time