storage-extract-image-text/extension.yaml

name: storage-extract-image-text
version: 0.1.6
specVersion: v1beta

displayName: Extract Image Text with Cloud Vision AI
description:
  Extracts text from images and saves to Firestore using Cloud Vision API.

license: Apache-2.0 # The license you want for the extension

icon: icon.png

tags:
  [
    ai,
    image,
    text-extraction,
    cloud-vision,
    image-recognition,
    image-classification,
    text-recognition,
    character-recognition,
    ocr,
    google-ai,
    cloud-vision-api,
  ]

author:
  authorName: Google Cloud
  url: https://cloud.google.com

contributors:
  - authorName: Invertase
    email: oss@invertase.io
    url: https://github.com/invertase

sourceUrl: https://github.com/GoogleCloudPlatform/firebase-extensions/tree/main/storage-extract-image-text
releaseNotesUrl: https://github.com/GoogleCloudPlatform/firebase-extensions/tree/main/storage-extract-image-text/CHANGELOG.md

billingRequired: true

apis:
  - apiName: vision.googleapis.com
    reason: Powers all Vision tasks performed by the extension.

resources:
  - name: extractText
    type: firebaseextensions.v1beta.function
    description:
      Listens to incoming Storage documents, executes OCR on them and writes
      extracted text to Firestore into a preconfigured collection.
    properties:
      location: ${param:LOCATION}
      availableMemoryMb: 1024
      eventTrigger:
        eventType: google.storage.object.finalize
        resource: projects/_/buckets/${param:IMG_BUCKET}
      runtime: nodejs20

params:
  - param: LOCATION
    label: Cloud Functions location
    description: >-
      Where do you want to deploy the functions created for this extension? You
      usually want a location close to your database. Realtime Database
      instances are located in `us-central1`. For help selecting a location,
      refer to the [location selection
      guide](https://firebase.google.com/docs/functions/locations).
    type: select
    options:
      - label: Iowa (us-central1)
        value: us-central1
      - label: South Carolina (us-east1)
        value: us-east1
      - label: Northern Virginia (us-east4)
        value: us-east4
      - label: Belgium (europe-west1)
        value: europe-west1
      - label: London (europe-west2)
        value: europe-west2
      - label: Frankfurt (europe-west3)
        value: europe-west3
      - label: Hong Kong (asia-east2)
        value: asia-east2
      - label: Tokyo (asia-northeast1)
        value: asia-northeast1
    default: us-central1
    required: true
    immutable: true
  - param: IMG_BUCKET
    label: Cloud Storage bucket for images
    description: >
      To which Cloud Storage bucket will you upload images from which you want
      to extract text?
    type: string
    example: my-project-12345.appspot.com
    validationRegex: ^([0-9a-z_.-]*)$
    validationErrorMessage: Invalid storage bucket
    default: ${STORAGE_BUCKET}
    required: true
  - param: COLLECTION_PATH
    label: Collection path
    description: >
      What is the path to the collection where extracted text will be written
      to.
    example: extractedText
    validationRegex: '^[^/]+(/[^/]+/[^/]+)*$'
    validationErrorMessage: Must be a valid Cloud Firestore Collection
    default: extractedText
    required: true
  - param: INCLUDE_PATH_LIST
    label: Paths that contain images you want to extract text from
    description: >
      Restrict storage-image-text-extraction to only extract text from images in
      specific locations in your Storage bucket by  supplying a comma-separated
      list of absolute paths. For example, specifying the paths
      `/users/pictures,/restaurants/menuItems` will process any images found in
      any subdirectories of `/users/pictures` and `/restaurants/menuItems`.

      If you prefer not to explicitly exclude any directories of your Storage
      bucket, leave this field empty.
    type: string
    example: '/users/avatars,/design/pictures'
    validationRegex: ^(\/[^\s\/\,]+)+(\,(\/[^\s\/\,]+)+)*$
    validationErrorMessage:
      Invalid paths, must be a comma-separated list of absolute path values.
    required: false

  - param: EXCLUDE_PATH_LIST
    label: List of absolute paths not included for image text extraction
    description: >
      Ensure storage-image-text-extraction does *not* process images in
      _specific locations_ in your Storage bucket by  supplying a
      comma-separated list of absolute paths. For example, to *exclude* the
      images  stored in the `/foo/alpha` and its subdirectories and `/bar/beta`
      and its subdirectories, specify the paths `/foo/alpha,/bar/beta`.

      If you prefer to process every image uploaded to your Storage bucket,
      leave this field empty.
    type: string
    example: '/users/avatars/thumbs,/design/pictures/thumbs'
    validationRegex: ^(\/[^\s\/\,]+)+(\,(\/[^\s\/\,]+)+)*$
    validationErrorMessage:
      Invalid paths, must be a comma-separated list of absolute path values.
    required: false

  - param: DETAIL
    label: Amount of text extraction information to write to firestore.
    description: >
      How much information should be written to firestore? Do you want just the
      extracted text written to firestore,  or the full data of the annotation?
      Select \"basic\" for the former, \"full\" for the later.
    type: select
    options:
      - label: Basic
        value: basic
      - label: Full
        value: full
    default: basic
    required: true
roles:
  - role: storage.objectAdmin
    reason: Allows the extension to write to your Cloud Storage.
  - role: datastore.user
    reason: Allows the extension to write to your Firestore Database instance.