Clarifeye Extraction Flows API

openapi: 3.0.3
info:
  title: Clarifeye Platform Agent Settings Extraction Flows API
  description: 'REST API for the Clarifeye Platform - Document intelligence and AI-powered analysis.


    ## Authentication

    All endpoints require authentication. Include the Authorization header in every request using either format:

    - `Authorization: Token <token_key>`

    - `Authorization: Bearer <token_key>`


    ## Impersonation


    Certain endpoints support user impersonation for creating or listing data on behalf of other users.

    This is useful for integrating external systems that need to attribute actions to specific users.


    **Header:** `X-Impersonate-Email`


    **Required Permission:** `CAN_IMPERSONATE_OTHER_USERS` (contact Clarifeye to enable this permission)


    **Behavior:**

    - If the header is provided and the impersonator has the required permission, the action is performed as the target user

    - If the target user is not found, the request proceeds as the original authenticated user

    - If the target user does not have access to the project, the request proceeds as the original authenticated user

    - If the impersonator lacks the `CAN_IMPERSONATE_OTHER_USERS` permission, the header is ignored

    '
  version: 1.0.0
  contact:
    name: Clarifeye Support
servers:
- url: https://eu.app.clarifeye.ai/api/v1
  description: EU
- url: https://us.app.clarifeye.ai/api/v1
  description: US
security:
- BearerAuth: []
- TokenAuth: []
tags:
- name: Extraction Flows
  description: Manage extraction flows (auto-sync DAGs) — list, run, inspect statistics, update, and publish
paths:
  /projects/{project_id}/extraction-flows/:
    get:
      tags:
      - Extraction Flows
      summary: List extraction flows
      description: 'List all extraction flows for the project, ordered by most recently updated.

        '
      operationId: listExtractionFlows
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/ExtractionFlow'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
  /projects/{project_id}/extraction-flows/{flow_id}/:
    patch:
      tags:
      - Extraction Flows
      summary: Update an extraction flow
      description: "Partially update an extraction flow. The most common use is to switch its\n**publish mode** between `auto_publish` and `manual_publish`.\n\n**Publish modes:**\n- `auto_publish` — Each successful flow run automatically publishes the\n  extracted data. No separate publish step\n  is required.\n- `manual_publish` — Flow runs only compute and persist extracted data in\n  the warehouse. Publishing to downstream indexes must be triggered\n  explicitly via the `publish` action. Use this when you want to review\n  the results of a run before exposing them to search / agents.\n"
      operationId: updateExtractionFlow
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - $ref: '#/components/parameters/FlowId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: Human-readable name of the flow
                publish_mode:
                  type: string
                  enum:
                  - auto_publish
                  - manual_publish
                  description: 'Controls whether extracted data is pushed to downstream indexes

                    automatically after each run (`auto_publish`) or only on an

                    explicit `publish` call (`manual_publish`).

                    '
                dag:
                  type: object
                  description: DAG definition (`name` + `nodes`) for the extraction flow.
            example:
              publish_mode: manual_publish
      responses:
        '200':
          description: Flow updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionFlow'
        '400':
          description: Invalid payload (e.g. malformed DAG or unknown publish_mode)
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
  /projects/{project_id}/extraction-flows/{flow_id}/run-sync/:
    post:
      tags:
      - Extraction Flows
      summary: Run an extraction flow
      description: 'Queue a pipeline run that executes the flow''s DAG across the given

        documents (or all project documents if `document_ids` is omitted).


        Returns the `pipeline_run_id` you can poll to track progress.

        '
      operationId: runExtractionFlow
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - $ref: '#/components/parameters/FlowId'
      requestBody:
        required: false
        content:
          application/json:
            schema:
              type: object
              properties:
                document_ids:
                  type: array
                  items:
                    type: string
                    format: uuid
                  description: 'Optional list of document UUIDs to run the flow on. If omitted

                    or empty, the flow runs against all documents in the project.

                    '
            example:
              document_ids:
              - 550e8400-e29b-41d4-a716-446655440000
      responses:
        '200':
          description: Sync started
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    example: Sync started.
                  pipeline_run_id:
                    type: string
                    format: uuid
        '400':
          description: Flow DAG is empty, inconsistent, or document_ids are invalid
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
  /projects/{project_id}/extraction-flows/{flow_id}/node-stats/:
    post:
      tags:
      - Extraction Flows
      summary: Get extraction flow statistics
      description: 'Dry-run cache simulation of the flow — returns, per DAG node, how many

        inputs would be reused from cache vs. recomputed, without actually

        executing any extraction. Useful to preview the cost/impact of a run.

        '
      operationId: getExtractionFlowStatistics
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - $ref: '#/components/parameters/FlowId'
      requestBody:
        required: false
        content:
          application/json:
            schema:
              type: object
              properties:
                document_ids:
                  type: array
                  items:
                    type: string
                    format: uuid
                  description: 'Optional list of document UUIDs to scope the simulation to.

                    When omitted, statistics are computed over all documents in

                    the project.

                    '
            example:
              document_ids:
              - 550e8400-e29b-41d4-a716-446655440000
      responses:
        '200':
          description: Per-node statistics
          content:
            application/json:
              schema:
                type: object
                description: 'Map of DAG node names to their cache/recompute statistics.

                  '
                additionalProperties:
                  type: object
        '400':
          description: Flow DAG is empty, inconsistent, or document_ids are invalid
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
  /projects/{project_id}/extraction-flows/{flow_id}/publish/:
    post:
      tags:
      - Extraction Flows
      summary: Publish an extraction flow
      description: 'Queue a pipeline run that publishes previously-extracted data to the

        downstream indexes without re-running extraction.


        > **Only valid for flows whose `publish_mode` is `manual_publish`.**

        > For `auto_publish` flows, publishing happens automatically at the end

        > of each `run-sync`, so calling this endpoint is unnecessary.

        '
      operationId: publishExtractionFlow
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - $ref: '#/components/parameters/FlowId'
      requestBody:
        required: false
        content:
          application/json:
            schema:
              type: object
              properties:
                document_ids:
                  type: array
                  items:
                    type: string
                    format: uuid
                  description: 'Optional list of document UUIDs to scope publishing to. When

                    omitted, publishing covers all documents in the project.

                    '
            example:
              document_ids:
              - 550e8400-e29b-41d4-a716-446655440000
      responses:
        '200':
          description: Publish started
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    example: Publish started.
                  pipeline_run_id:
                    type: string
                    format: uuid
        '400':
          description: Flow DAG is empty or inconsistent
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
components:
  parameters:
    FlowId:
      name: flow_id
      in: path
      required: true
      description: UUID of the extraction flow
      schema:
        type: string
        format: uuid
    ProjectId:
      name: project_id
      in: path
      required: true
      description: UUID of the project
      schema:
        type: string
        format: uuid
  responses:
    Forbidden:
      description: Forbidden - insufficient permissions
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error: You do not have permission to perform this action.
    Unauthorized:
      description: Unauthorized - missing or invalid authentication
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error: Authentication credentials were not provided.
    NotFound:
      description: Not found - resource does not exist
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error: Not found.
  schemas:
    Error:
      type: object
      properties:
        error:
          type: string
          description: Error message
      example:
        error: User not found
    ExtractionFlowPublishMode:
      type: string
      enum:
      - auto_publish
      - manual_publish
      description: '- `auto_publish` — runs automatically push extracted data to downstream indexes.

        - `manual_publish` — publishing is triggered explicitly via the `publish` action.

        '
    ExtractionFlow:
      type: object
      properties:
        id:
          type: string
          format: uuid
        name:
          type: string
        publish_mode:
          $ref: '#/components/schemas/ExtractionFlowPublishMode'
        dag:
          type: object
          description: DAG definition (`name` + `nodes`) describing the extractor pipeline.
        tpuf_namespaces:
          type: object
          description: Per-namespace-type TurboPuffer namespace mapping populated on publish.
        last_pushed_to_tpuf:
          type: string
          format: date-time
          nullable: true
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: 'Use Authorization: Bearer <token>'
    TokenAuth:
      type: apiKey
      in: header
      name: Authorization
      description: 'Use Authorization: Token <token>'