Cloud Vision Plugins
Introduction
Cloud Vision plugins will allow users to use pre-trained Vision API models to detect emotion, understand text, and more. They will be useful in enriching data with additional attributes such as labels, faces, etc.
NOTE: These plugins will incur additional cost of the Cloud Vision APIs.
Use case(s)
As a user, I want to various features in my images and documents using the Cloud Vision API, so that I can add ML-driven enrichments to my Data Fusion pipelines that process unstructured data
As a user, I want easy, UI-driven ways of manipulating and understanding the output of the Cloud Vision API, so that I do not need to write any code for parsing it.
User Storie(s)
Plugin Type
Configurables
File Path Batch Source
This source will read a directory, and instead of emitting records from files in the directory, it will emit all the file names as records. It should work for object stores as well.
Section | User Facing Name | Type | Description | Optional | Default |
|---|---|---|---|---|---|
Basic | Service Account File path | text | Path to service account file on | Yes | None |
Project ID | text | GCP Project ID | Yes | auto-detect | |
Path | textbox | The path to the directory where the files whose paths are to be emitted are located | No |
| |
Recursive | toggle | Whether the plugin should recursively traverse the directory for subdirectories | Yes | False | |
Last Modified After | date-time picker | A way to filter files to be returned based on their last modified timestamp | Yes | 1/1/1970 (epoch) | |
Advanced | Split by | radio button | Determines splitting mechanisms. Choose amongst default (uses the default splitting mechanism of file input format), batch size (by number of files in a batch), directory (by each sub directory) | Yes | default |
Batch size | number | Specifies the number of files to process in a single batch. Only required when Split By is set to batch size. |
|
|
Image Extractor transform
The image extractor transform can be used in conjunction with the file path batch source to extract enrichments from each image based on selected features.
It should send all errors to the error port.
Section | User Facing Name | Type | Description | Optional | Default |
|---|---|---|---|---|---|
Basic | Access Token | Password | Authentication token for Cloud Vision API. | No |
|
Path Field | Input Field Selector | Field in the input schema containing the path to the image. Defaults to 'path' | Yes | path | |
Features | function-dropdown-with-alias | The features to extract from documents, specified as a combination of feature type, max results, and model. Select from Face, Text, Handwriting, Crop Hints, Faces, Image properties, Labels, Landmarks, Logos, Multiple Objects, Explicit Content, Web Detection, Product Search, Object Localization | No |
| |
Advanced | Language Hints | multi-select | Optional hints to provide to Cloud Vision API in case it has trouble detecting the language of the text in the images. Only shown when the Text feature is selected. Select from supported languages | Yes | None/Empty |
Aspect Ratios | multi-select | Aspect ratios as a decimal number, representing the ratio of the width to the height of the image. For example, if the desired aspect ratio is 4/3, the corresponding float value should be 1.33333. Only shown when Crop Hints is selected as a feature. If not specified, the best possible crop is returned. The number of provided aspect ratios is limited to a maximum of 16; any aspect ratios provided after the 16th are ignored. | Yes | None | |
Include Geo Results | toggle | Whether to include results derived from the geo information in the image. Only shown when Web Detection is selected as a feature | Yes | false | |
Bounding Polynomial | JSON | The bounding polynomial for the image detection. Only shown when Product Search is selected as a feature. Should be a JSON in this format | Yes | None | |
Product Set | text | The resource name of a ProductSet to be searched for similar images. Only shown when Product Search is selected as a feature. Format is: | Yes | None | |
Product Categories | select | The list of product categories to search in. Select one of either "homegoods", "apparel", or "toys". Only shown when Product Search is selected as a feature. | Yes | None | |
Filter | text | The filtering expression. This can be used to restrict search results based on Product labels. We currently support an AND of OR of key-value expressions, where each expression within an OR must have the same key. An '=' should be used to connect the key and value. Only shown when Product Search is selected as a feature. For example, "(color = red OR color = blue) AND brand = Google" is acceptable, but "(color = red OR brand = Google)" is not acceptable. "color: red" is not acceptable because it uses a ':' instead of an '='. | Yes | None |
Online Document Text Extractor transform
This transform plugin can detect and transcribe text from small (upto 5 pages) PDF and TIFF files stored in Cloud Storage in an online manner.
Section | User Facing Name | Type | Description | Optional | Default |
|---|---|---|---|---|---|
Basic | Access Token | Password | Authentication token for Cloud Vision API. | No |
|
Path Field | Input field selector | Field in the input schema containing the path to the image. Defaults to 'path' | Yes | path | |
Content Field | Input field selector | Field in the input schema containing the file content, represented as a stream of bytes. Defaults to 'content'. | Yes | content | |
Mime Type | select | Choose one of "application/pdf", "image/tiff" and "image/gif" | Yes | application/pdf | |
Features | function-dropdown-with-alias | The features to extract from documents, specified as a combination of feature type, max results, and model. Select from Face, Text, Handwriting, Crop Hints, Faces, Image properties, Labels, Landmarks, Logos, Multiple Objects, Explicit Content, Web Detection, Product Search, Object Localization | No |
| |
Pages | multi-select | The pages in the file to perform image annotation. Select from 1-5. | Yes | 1,2,3,4,5 | |
Advanced | Language Hints | multi-select | Optional hints to provide to Cloud Vision API in case it has trouble detecting the language of the text in the images. Only shown when the Text feature is selected. Select from supported languages | Yes | None/Empty |
Aspect Ratios | multi-select | Aspect ratios as a decimal number, representing the ratio of the width to the height of the image. For example, if the desired aspect ratio is 4/3, the corresponding float value should be 1.33333. Only shown when Crop Hints is selected as a feature. If not specified, the best possible crop is returned. The number of provided aspect ratios is limited to a maximum of 16; any aspect ratios provided after the 16th are ignored. | Yes | None | |
Include Geo Results | toggle | Whether to include results derived from the geo information in the image. Only shown when Web Detection is selected as a feature | Yes | false | |
Bounding Polynomial | JSON | The bounding polynomial for the image detection. Only shown when Product Search is selected as a feature. Should be a JSON in this format | Yes | None | |
Product Set | text | The resource name of a ProductSet to be searched for similar images. Only shown when Product Search is selected as a feature. Format is: | Yes | None | |
Product Categories | select | The list of product categories to search in. Select one of either "homegoods", "apparel", or "toys". Only shown when Product Search is selected as a feature. | Yes | None | |
Filter | text | The filtering expression. This can be used to restrict search results based on Product labels. We currently support an AND of OR of key-value expressions, where each expression within an OR must have the same key. An '=' should be used to connect the key and value. Only shown when Product Search is selected as a feature. For example, "(color = red OR color = blue) AND brand = Google" is acceptable, but "(color = red OR brand = Google)" is not acceptable. "color: red" is not acceptable because it uses a ':' instead of an '='. | Yes | None |
Offline Document Text Extractor action
This action plugin can detect and transcribe text from large (upto 2000 pages) PDF and TIFF files stored in Cloud Storage in an async manner.
Section | User Facing Name | Type | Description | Optional | Default |
|---|---|---|---|---|---|
Basic | Access Token | Password | Authentication token for Cloud Vision API. | No |
|
Source Path | Text | Path to the location of the directory on GCS where the input files are stored | Yes | path | |
Destination Path | Text | Path to the location of the directory on GCS where output files should be stored | Yes | content | |
Mime Type | select | Choose one of "application/pdf", "image/tiff" and "image/gif" | Yes | application/pdf | |
Features | function-dropdown-with-alias | The features to extract from documents, specified as a combination of feature type, max results, and model. Select from Face, Text, Handwriting, Crop Hints, Faces, Image properties, Labels, Landmarks, Logos, Multiple Objects, Explicit Content, Web Detection, Product Search, Object Localization | No |
| |
Pages | multi-select | The pages in the file to perform image annotation. Select from 1-5. | Yes | 1,2,3,4,5 | |
Batch size | number | The max number of responses to put into each output JSON file on Google Cloud Storage. The valid range is [1, 100]. If not specified, the default value is 20. | Yes | 20 | |
Advanced | Language Hints | multi-select | Optional hints to provide to Cloud Vision API in case it has trouble detecting the language of the text in the images. Only shown when the Text feature is selected. Select from supported languages | Yes | None/Empty |
Aspect Ratios | multi-select | Aspect ratios as a decimal number, representing the ratio of the width to the height of the image. For example, if the desired aspect ratio is 4/3, the corresponding float value should be 1.33333. Only shown when Crop Hints is selected as a feature. If not specified, the best possible crop is returned. The number of provided aspect ratios is limited to a maximum of 16; any aspect ratios provided after the 16th are ignored. | Yes | None | |
Include Geo Results | toggle | Whether to include results derived from the geo information in the image. Only shown when Web Detection is selected as a feature | Yes | false | |
Bounding Polynomial | JSON | The bounding polynomial for the image detection. Only shown when Product Search is selected as a feature. Should be a JSON in this format | Yes | None | |
Product Set | text | The resource name of a ProductSet to be searched for similar images. Only shown when Product Search is selected as a feature. Format is: | Yes | None | |
Product Categories | select | The list of product categories to search in. Select one of either "homegoods", "apparel", or "toys". Only shown when Product Search is selected as a feature. | Yes | None | |
Filter | text | The filtering expression. This can be used to restrict search results based on Product labels. We currently support an AND of OR of key-value expressions, where each expression within an OR must have the same key. An '=' should be used to connect the key and value. Only shown when Product Search is selected as a feature. For example, "(color = red OR color = blue) AND brand = Google" is acceptable, but "(color = red OR brand = Google)" is not acceptable. "color: red" is not acceptable because it uses a ':' instead of an '='. |
Offline Image Extractor action
This action plugin can asynchronously extract features from images stored on GCS, and store the extracted output on GCS.
Section | User Facing Name | Type | Description | Optional | Default |
|---|---|---|---|---|---|
Basic | Access Token | Password | Authentication token for Cloud Vision API. | No |
|
Source Path | Text | Path to the location of the directory on GCS where the input files are stored | Yes | path | |
Destination Path | Text | Path to the location of the directory on GCS where output files should be stored | Yes | content | |