CodeProject.AI Server API

openapi: 3.1.0
info:
  title: CodeProject.AI Server API
  description: >-
    CodeProject.AI Server is a self-contained, self-hosted, free and open-source
    AI service that exposes computer-vision, audio, NLP, and model-training
    capabilities through a local HTTP REST API. It runs on Windows, macOS,
    Linux, Raspberry Pi, NVIDIA Jetson, OrangePi, and as a Docker container,
    and is most often integrated with home-automation and surveillance
    platforms (Blue Iris, Home Assistant, Agent DVR) for object detection,
    face recognition, ALPR (license-plate), and scene classification. All
    endpoints are POST and accept multipart/form-data uploads.
  version: '2.9'
  contact:
    name: CodeProject.AI Server
    url: https://www.codeproject.com/AI/
  license:
    name: GPL-3.0
    url: https://github.com/codeproject/CodeProject.AI-Server/blob/main/LICENSE
externalDocs:
  description: CodeProject.AI Server documentation
  url: https://codeproject.github.io/codeproject.ai/
servers:
  - url: http://localhost:32168
    description: Default local CodeProject.AI Server endpoint
tags:
  - name: Status
    description: Server status, version, logs, and update checks.
  - name: Vision-Detection
    description: Object detection across general and custom YOLO models.
  - name: Vision-Scene
    description: Scene classification.
  - name: Vision-Face
    description: Face detection, comparison, registration, and recognition.
  - name: Vision-ALPR
    description: Automatic license-plate recognition.
  - name: Image-Processing
    description: Background removal, cartoonise, portrait filter, super-resolution.
  - name: Audio
    description: Sound classification.
  - name: Text
    description: Sentiment analysis and summarization.
  - name: Training
    description: Custom YOLO dataset and model training lifecycle.
paths:
  /v1/status/ping:
    post:
      operationId: pingServer
      summary: Server health check
      tags: [Status]
      responses:
        '200':
          description: Server reachable
  /v1/status/version:
    post:
      operationId: getServerVersion
      summary: Get server version
      tags: [Status]
      responses:
        '200':
          description: Version information
  /v1/status/logs:
    post:
      operationId: getServerLogs
      summary: Retrieve server logs
      tags: [Status]
      responses:
        '200':
          description: Log entries
  /v1/status/updateavailable:
    post:
      operationId: checkForUpdates
      summary: Check whether a new server version is available
      tags: [Status]
      responses:
        '200':
          description: Update availability status
  /v1/vision/detection:
    post:
      operationId: detectObjects
      summary: Detect objects in an image
      description: YOLO-based object detection across 80 default classes.
      tags: [Vision-Detection]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
                min_confidence:
                  type: number
                  format: float
                  default: 0.4
      responses:
        '200':
          description: Detection results
  /v1/vision/custom/{modelName}:
    post:
      operationId: detectCustom
      summary: Run a custom-model detection
      tags: [Vision-Detection]
      parameters:
        - name: modelName
          in: path
          required: true
          schema:
            type: string
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
                min_confidence:
                  type: number
                  format: float
      responses:
        '200':
          description: Detection results
  /v1/vision/custom/list:
    post:
      operationId: listCustomModels
      summary: List installed custom detection models
      tags: [Vision-Detection]
      responses:
        '200':
          description: Custom model list
  /v1/vision/scene:
    post:
      operationId: classifyScene
      summary: Classify the scene depicted in an image
      tags: [Vision-Scene]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
      responses:
        '200':
          description: Scene classification result
  /v1/vision/face:
    post:
      operationId: detectFaces
      summary: Detect faces in an image
      tags: [Vision-Face]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
                min_confidence:
                  type: number
                  format: float
      responses:
        '200':
          description: Face detection result
  /v1/vision/face/match:
    post:
      operationId: matchFaces
      summary: Compare two face images for similarity
      tags: [Vision-Face]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image1, image2]
              properties:
                image1:
                  type: string
                  format: binary
                image2:
                  type: string
                  format: binary
      responses:
        '200':
          description: Match result
  /v1/vision/face/list:
    post:
      operationId: listRegisteredFaces
      summary: List registered users for face recognition
      tags: [Vision-Face]
      responses:
        '200':
          description: Registered users
  /v1/vision/face/register:
    post:
      operationId: registerFace
      summary: Register face images for a user
      tags: [Vision-Face]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [userid, image]
              properties:
                userid:
                  type: string
                image:
                  type: string
                  format: binary
      responses:
        '200':
          description: Registration result
  /v1/vision/face/delete:
    post:
      operationId: deleteFace
      summary: Remove a registered user
      tags: [Vision-Face]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [userid]
              properties:
                userid:
                  type: string
      responses:
        '200':
          description: Deletion result
  /v1/vision/face/recognize:
    post:
      operationId: recognizeFaces
      summary: Identify faces in an image against the registered set
      tags: [Vision-Face]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
                min_confidence:
                  type: number
                  format: float
      responses:
        '200':
          description: Recognition result
  /v1/vision/alpr:
    post:
      operationId: readLicensePlate
      summary: Detect and read license plates
      tags: [Vision-ALPR]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [upload]
              properties:
                upload:
                  type: string
                  format: binary
      responses:
        '200':
          description: ALPR result
  /v1/image/alpr:
    post:
      operationId: readLicensePlateLegacy
      summary: Legacy ALPR route (deprecated alias of /v1/vision/alpr)
      deprecated: true
      tags: [Vision-ALPR]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [upload]
              properties:
                upload:
                  type: string
                  format: binary
      responses:
        '200':
          description: ALPR result
  /v1/image/removebackground:
    post:
      operationId: removeBackground
      summary: Remove the background from an image
      tags: [Image-Processing]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
                use_alphamatting:
                  type: boolean
      responses:
        '200':
          description: Image with background removed
  /v1/image/cartoonise:
    post:
      operationId: cartoonise
      summary: Convert an image to anime/cartoon style
      tags: [Image-Processing]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
      responses:
        '200':
          description: Cartoonised image
  /v1/image/portraitfilter:
    post:
      operationId: portraitFilter
      summary: Apply a portrait/background-blur effect
      tags: [Image-Processing]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
                strength:
                  type: number
                  format: float
      responses:
        '200':
          description: Filtered image
  /v1/image/superresolution:
    post:
      operationId: superResolution
      summary: Upscale an image
      tags: [Image-Processing]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [image]
              properties:
                image:
                  type: string
                  format: binary
      responses:
        '200':
          description: Upscaled image
  /v1/sound/classify:
    post:
      operationId: classifySound
      summary: Classify a sound file
      tags: [Audio]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [sound]
              properties:
                sound:
                  type: string
                  format: binary
                min_confidence:
                  type: number
                  format: float
      responses:
        '200':
          description: Sound classification result
  /v1/text/sentiment:
    post:
      operationId: analyzeSentiment
      summary: Sentiment analysis
      tags: [Text]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [text]
              properties:
                text:
                  type: string
      responses:
        '200':
          description: Sentiment result
  /v1/text/summarize:
    post:
      operationId: summarizeText
      summary: Summarize text
      tags: [Text]
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [text]
              properties:
                text:
                  type: string
                num_sentences:
                  type: integer
      responses:
        '200':
          description: Summary
  /v1/train/create_dataset:
    post:
      operationId: createTrainingDataset
      summary: Create a custom training dataset
      tags: [Training]
      responses:
        '200':
          description: Dataset metadata
  /v1/train/train_model:
    post:
      operationId: trainModel
      summary: Start YOLOv5 model training
      tags: [Training]
      responses:
        '200':
          description: Training job started
  /v1/train/status:
    post:
      operationId: getTrainingStatus
      summary: Check training progress
      tags: [Training]
      responses:
        '200':
          description: Training status
  /v1/train/cancel:
    post:
      operationId: cancelTraining
      summary: Stop a running training job
      tags: [Training]
      responses:
        '200':
          description: Cancellation result
  /v1/train/get_model:
    post:
      operationId: getTrainedModel
      summary: Retrieve a trained model
      tags: [Training]
      responses:
        '200':
          description: Model artifact
  /v1/train/get_dataset:
    post:
      operationId: getTrainingDataset
      summary: Retrieve a training dataset
      tags: [Training]
      responses:
        '200':
          description: Dataset
components:
  securitySchemes:
    none:
      type: apiKey
      in: header
      name: X-Disabled
      description: >-
        CodeProject.AI Server runs locally and does not require authentication
        by default. Operators are expected to keep the service on a private
        network or behind their own reverse proxy.