From 159df8e2ef2a6d65a6a5f3f7e8bcfd0276c2ce48 Mon Sep 17 00:00:00 2001 From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com> Date: Wed, 17 Jun 2026 09:32:17 +0200 Subject: [PATCH] feat(swagger): update swagger (#10365) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --- swagger/docs.go | 146 +++++++++++++++++++++++++++++++++++++++++++ swagger/swagger.json | 146 +++++++++++++++++++++++++++++++++++++++++++ swagger/swagger.yaml | 102 ++++++++++++++++++++++++++++++ 3 files changed, 394 insertions(+) diff --git a/swagger/docs.go b/swagger/docs.go index dded35c43..f75803edc 100644 --- a/swagger/docs.go +++ b/swagger/docs.go @@ -2142,6 +2142,33 @@ const docTemplate = `{ } } }, + "/v1/depth": { + "post": { + "tags": [ + "depth" + ], + "summary": "Estimates per-pixel depth (and optionally pose/points) from an image.", + "parameters": [ + { + "description": "query params", + "name": "request", + "in": "body", + "required": true, + "schema": { + "$ref": "#/definitions/schema.DepthRequest" + } + } + ], + "responses": { + "200": { + "description": "Response", + "schema": { + "$ref": "#/definitions/schema.DepthResponse" + } + } + } + } + }, "/v1/detection": { "post": { "tags": [ @@ -3905,6 +3932,125 @@ const docTemplate = `{ } } }, + "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 \u003e= 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" + } + } + }, "schema.Detection": { "type": "object", "properties": { diff --git a/swagger/swagger.json b/swagger/swagger.json index 2079c378d..6da5855ba 100644 --- a/swagger/swagger.json +++ b/swagger/swagger.json @@ -2139,6 +2139,33 @@ } } }, + "/v1/depth": { + "post": { + "tags": [ + "depth" + ], + "summary": "Estimates per-pixel depth (and optionally pose/points) from an image.", + "parameters": [ + { + "description": "query params", + "name": "request", + "in": "body", + "required": true, + "schema": { + "$ref": "#/definitions/schema.DepthRequest" + } + } + ], + "responses": { + "200": { + "description": "Response", + "schema": { + "$ref": "#/definitions/schema.DepthResponse" + } + } + } + } + }, "/v1/detection": { "post": { "tags": [ @@ -3902,6 +3929,125 @@ } } }, + "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 \u003e= 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" + } + } + }, "schema.Detection": { "type": "object", "properties": { diff --git a/swagger/swagger.yaml b/swagger/swagger.yaml index 4a0de31de..c49ba6c79 100644 --- a/swagger/swagger.yaml +++ b/swagger/swagger.yaml @@ -594,6 +594,91 @@ definitions: text: type: string type: object + schema.DepthRequest: + properties: + dst: + description: optional output directory for exports (glb/colmap) + type: string + exports: + description: 'requested exports: "glb", "colmap"' + items: + type: string + type: array + 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 + type: object + schema.DepthResponse: + properties: + confidence: + description: width*height row-major confidence (DualDPT) + items: + type: number + type: array + depth: + description: width*height row-major metric depth + items: + type: number + type: array + export_paths: + description: paths written for the requested exports + items: + type: string + type: array + extrinsics: + description: 12 floats, 3x4 row-major (world-to-camera) + items: + type: number + type: array + height: + type: integer + intrinsics: + description: 9 floats, 3x3 row-major + items: + type: number + type: array + 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 + items: + type: number + type: array + sky: + description: width*height row-major sky map (mono) + items: + type: number + type: array + width: + type: integer + type: object schema.Detection: properties: class_name: @@ -3769,6 +3854,23 @@ paths: summary: Generate completions for a given prompt and model. tags: - inference + /v1/depth: + post: + parameters: + - description: query params + in: body + name: request + required: true + schema: + $ref: '#/definitions/schema.DepthRequest' + responses: + "200": + description: Response + schema: + $ref: '#/definitions/schema.DepthResponse' + summary: Estimates per-pixel depth (and optionally pose/points) from an image. + tags: + - depth /v1/detection: post: parameters: