openapi: 3.2.0
info:
  description: The LocalAI Rest API.
  title: LocalAI Depth API
  contact:
    name: LocalAI
    url: https://localai.io
  license:
    name: MIT
    url: https://raw.githubusercontent.com/mudler/LocalAI/master/LICENSE
  version: 2.0.0
servers:
- url: /
tags:
- name: depth
paths:
  /v1/depth:
    post:
      tags:
      - depth
      summary: Estimates per-pixel depth (and optionally pose/points) from an image.
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.DepthResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.DepthRequest'
        description: query params
        required: true
components:
  schemas:
    schema.DepthRequest:
      type: object
      properties:
        dst:
          description: optional output directory for exports (glb/colmap)
          type: string
        exports:
          description: 'requested exports: "glb", "colmap"'
          type: array
          items:
            type: string
        image:
          description: URL or base64-encoded image to analyze
          type: string
        include_confidence:
          description: return the per-pixel confidence map (DualDPT)
          type: boolean
        include_depth:
          description: return the per-pixel depth map
          type: boolean
        include_points:
          description: back-project to a 3D point cloud (DualDPT)
          type: boolean
        include_pose:
          description: return camera extrinsics/intrinsics (DualDPT)
          type: boolean
        include_sky:
          description: return the per-pixel sky map (mono models)
          type: boolean
        model:
          type: string
        points_conf_thresh:
          description: keep points with confidence >= this threshold
          type: number
    schema.DepthResponse:
      type: object
      properties:
        confidence:
          description: width*height row-major confidence (DualDPT)
          type: array
          items:
            type: number
        depth:
          description: width*height row-major metric depth
          type: array
          items:
            type: number
        export_paths:
          description: paths written for the requested exports
          type: array
          items:
            type: string
        extrinsics:
          description: 12 floats, 3x4 row-major (world-to-camera)
          type: array
          items:
            type: number
        height:
          type: integer
        intrinsics:
          description: 9 floats, 3x3 row-major
          type: array
          items:
            type: number
        is_metric:
          description: depth is in metric units
          type: boolean
        num_points:
          description: number of 3D points
          type: integer
        point_colors:
          description: base64-encoded num_points*3 uint8 rgb
          type: string
        points:
          description: num_points*3 xyz, world space
          type: array
          items:
            type: number
        sky:
          description: width*height row-major sky map (mono)
          type: array
          items:
            type: number
        width:
          type: integer
  securitySchemes:
    BearerAuth:
      type: apiKey
      name: Authorization
      in: header