Free cookie consent management tool by TermsFeed Using Google AI Services [AI Capabilities]
Using Google AI Services

Appian has a robust set of built-in artificial intelligence (AI) capabilities to automate many of your most common tasks, such as:

  • Document classification
  • Document extraction
  • Email classification

Appian's built-in AI capabilities are only available for Cloud customers at this time. Self-managed and Appian Gov Cloud customers don't have access to these features. Other built-in capabilities are available for both Cloud and self-managed customers.

To complement our built-in AI capabilities and address any limitations for the customers listed above, we also offer low-code ways to use Google's AI functionality within your Appian applications. This page describes what features are available, how to get started, and how your data remains secure.

Note:  Customers who wish to use Google services in Appian will need to bring their own Google Cloud credentials to do so.

Features

Feature Description
Google Cloud Natural Language Perform entity and sentiment analysis to collect information from HTML or plain text. Using these capabilities on elements of text allows you to identify key subjects such as people, places, and events, determine a user's opinion or conveyed emotion, and even classify the contents of the text into predefined categories.
Google Cloud Translate Quickly and easily detect the language of a piece of text, and then translate it into the desired language.
Google Cloud Vision connected system Collect key information and structured data from images. Using this feature, you can extract the colors, logos, and labels of an image and then organize that information into categories. This functionality also allows you to extract text from a PDF or image. Unlike document extraction, Google Cloud Vision can analyze pieces of unstructured data, like paragraphs or sentences. When working with contracts, you may find Google Cloud Vision useful to extract signatures or written names.
Google Cloud AutoML connected system plug-in Create and modify custom machine learning models that fit your specific business needs. AutoML provides a series of products that harness the power of existing Google Cloud AI features, like Natural Language, Translation, and Vision, and provides you with the flexibility to customize the feature to your exact use case. Before you get started using the connected system, review the specific bucket requirements required to create and modify models.
Google Cloud Document AI In addition to Appian's built-in document extraction capabilities, you also have the option to leverage document extraction capabilities using Google.
Google Cloud Storage connected system plug-in To support the available Google Cloud AI services and store related documents or files, you can use Google Cloud Storage to store the items in a bucket. Cloud Storage allows you to store and retrieve an unlimited amount of data from a secure location. This is often used alongside Google Cloud AutoML and Document Extraction to store the items being evaluated. Once you’ve configured the connected system, create an integration to retrieve the data about a file, delete a file, create a new bucket, and more.

Setup

Review the sections below to ensure you are ready to begin building AI into your application using Google services.

If you already have a Google Cloud account set up for your business, you can use that account to create service accounts and service account keys. As long as you have a valid Google Service Account and key, you can configure and use the AI smart services, plug-ins, and connected systems. Depending on the AI functionality, you may need to configure additional items in your Google Account.

To use certain AI functionality, you will need to download and deploy additional plug-ins before you can use the Appian design objects in your application.

System requirements

  • To use the Google Cloud AI connected systems and connected system plug-ins, Appian must be running version 19.2 or higher.
  • A supported web browser.
  • If your Appian installation is on a dedicated VPN, the VPN must allow Google's APIs to be accessible from the application server.

Google Cloud setup

You must have a Google Cloud account, service account, and service account key to connect to Google Cloud AI services from Appian.

If you've purchased Google Cloud separately and already have an existing account, you don't need to create a new one. You will, however, need to take a few additional configuration steps.

To use your Google Cloud Platform project with Appian, you must do the following:

  1. As the Project Owner, log into the Google Cloud console and select an existing project or create a new project.
  2. Ensure that billing is enabled for your project.
  3. Enable the following APIs:
    • Google Cloud Storage JSON API
    • Cloud Document AI API
  4. Create Cloud Storage buckets that follow the bucket requirements to store the AutoML Natural Language files:
    • For us-central1:
    • Location type: Region
    • Location: us-central1
    • Storage class: Standard (sometimes displayed in the Cloud Storage browser as Regional) - For eu:
    • Location type: Multi-region
    • Location: eu
    • Storage class: Standard (sometimes displayed in the Cloud Storage browser as Multi-Regional)
  5. You may choose to have two buckets: one for the training documents and one for the prediction documents. Or, you can use the same storage bucket for both. If you use two buckets, then they must be in the same regional location.
  6. Create a Google Service Account in the Google Cloud console with AutoML Admin and Storage Admin permissions.
  7. Create the service account key and save the file as a JSON document.
Using Google's Document AI API v1

In the v1 release of Google's Document AI API, the service is better equipped to handle more complex text content in documents, such as handwriting. Customers can take advantage of this updated endpoint by setting up a Form Parser processor in their Google Cloud console.

Tip:  Setting up the Form Parser processor in the Google Document AI API v1 endpoint is optional.

This option is currently only available for customers managing their own Google Cloud Platform because you will need access to your Google Cloud Platform project to set up the processor and retrieve the processor ID.

Before you get started, create a Form Parser processor in your Google Cloud Platform:

  1. In the Google Cloud Platform, open the Form Parser processor you created.
  2. Locate and copy the processor ID. You'll use this value in Appian to connect to the processor.

Then you can connect the Google Document AI Form Parser with Appian's document extraction features:

  1. In Appian Designer, open the process model used for document extraction.
  2. Open the Start Doc Extraction Smart Service and select the Data tab.
  3. On the Inputs tab, click Processor ID and configure a value so it uses the processor ID from the Form Parser processor you set up earlier. You can paste the processor ID directly, or configure it using a process variable.
    • Note: Processor ID is not supported when Appian is selected for Preferred Vendor.
  4. Click OK.
  5. Save and publish your process model.

When a document is extracted in this process, it will be sent to the new Form Parser processor you set up, which uses Google's Document AI API v1.

Deploy plug-ins

To use Google's machine learning models or access a Google Cloud Storage bucket in your application, you'll need to deploy the Google Cloud Storage connected system plug-in.

To deploy the plug-in for Appian Cloud installations:

  1. In your Appian environment, log in as a system administrator.
  2. Go to > Admin Console.
  3. On the left side of the console, click Plug-ins.
  4. Click DEPLOY NEW PLUG-INS.
  5. Search for and click the desired plug-in. Note that only cloud-approved plug-ins that are supported for your site's version of Appian will appear.
  6. Click DEPLOY.

To deploy plug-ins for self-managed installations, see Appian Suite Plug-Ins.

How is my data protected?

Appian ensures your data moves securely, no matter the AI services you choose to use in your applications.

When you use Appian's built-in AI capabilities, all of your data stays within the confines of your environment.

As for customers who use Google's AI services, each Google Cloud Platform project is configured for each customer to segregate data flows, security, and storage. Each project is also created with privileges that only provide access to the needed APIs.

The project uses automatic provisioning of unique service accounts to access Google Cloud Platform resources. Automatic provisioning means that service account credentials are generated automatically and no other users see or have access to the credentials during the process, making it more secure and straightforward. Additionally, the Google Cloud Platform project is set up in a region most applicable or as you select (either us-central1 or eu).

Data is concealed through key parts of setup:

  • Provisioning: The entire Google Cloud Platform project setup process is automated with no human intervention.
  • Access: A limited number of support and engineering team members have access to metadata (customer name, support contact, and preferred region) to confirm the setup was complete and successful, with no access to underlying project resources or service account credentials.
  • Monitoring: We have monitoring dashboards to ensure we meet our service level agreements (SLAs) and monitor for problems with proactive alerts on performance, budget, and other diagnostic information.

How is the data stored after it's extracted and processed from my documents? For how long?

Data storage location and duration changes based on how it's being used:

  • Classification model training: The document is stored in a Google Cloud storage bucket when uploaded, in the supported region where storage was originally provisioned. Then the documents are converted and digitized to form a dataset to train the classification model. The model and the dataset are stored and processed in the supported location corresponding with the region of the storage bucket. The documents and their digitized datasets are deleted once the model is trained and deployed, which can take up to 24 hours.
  • Document type classification: Classification sends the document to Google Cloud for AutoML Natural Language Processing. The document is stored in a Google Cloud storage bucket, in the supported region where storage was originally provisioned. Google's AutoML Natural Language digitizes and classifies the document content into user-defined categories based on a machine learning model that has been trained on a representative data set. The results are then returned back to Appian. The document is deleted after the model returns a prediction, which can take up to three minutes.
  • Data extraction: The document is sent to Google Cloud Storage within your configured Google Cloud Platform project so that Document AI can be performed on it. The document is then analyzed using the Google Cloud Document AI API. This analysis data is stored in a JSON document in a Google Cloud storage bucket and sent back to Appian. For customers who are using an Appian-managed Google Cloud account, the uploaded document and JSON analysis document are deleted after 24 hours. Customers managing their own Google Cloud accounts will need to arrange for the deletion of the document. The auto-mapping learning of labels and values is stored in the Appian environment. The learning happens independently in each environment.

How does Google use my data?

Visit Google's site for the most up to date information regarding their security commitments. We've summarized some key points in this section.

Throughout this section, we reference the following resources to help summarize what the policies mean for your data:

Google's data security and privacy practices

Note:  Refer to Google's resources for up-to-date information and more details about Google Cloud Platform. Google Cloud Platform's Terms and Conditions, Data Privacy and Access is summarized below for convenience.

At a high-level, Google states that they do not access customer data in transit or at rest for any purpose other than to provide the respective services requests. By default, data is also encrypted during transit and at rest for security. In practice, this means that Google does not use customer data to improve the service: in this case, the machine learning models. Additionally for customers using an Appian-managed Google Cloud account, Appian has implemented a strict data retention policy that automatically deletes processed documents and results within 24 hours. This results in further security of customer data by making the encrypted data available only for a short period sufficient for Google's service to process the request and write the results to be consumed by Appian. Processing and communication all occur within the confines of the customer's own Appian cloud instance and the customer's own Google Cloud Platform project.

Refer to section 5.2.1.: Customer's Instructions in Google's processing terms for more details.

Google provides access transparency logs, which expose any action including reading of data by anyone (Google, Appian, or otherwise) of both data and services.

How does Google treat your content?

Visit Google's site for the most up to date information regarding their security commitments. We've summarized some key points from Google Vision data-processing FAQ and AutoML FAQ to provide you with helpful answers to key questions.

  • Google won't use your content for any purpose except to provide the Cloud Vision API or AutoML service.
  • Google won't make content sent through these services available to the public or share them otherwise. If necessary, data may be shared with third-party vendors to provide aspects of the Cloud Vision API or AutoML services, such as data storage or transmission. In these cases, the data is shared only under contractually defined security and confidentiality conditions.
  • Google stores the content for a short period of time for analysis and to return results. The length of time depends on whether these actions take place asynchronously or immediately, but won't exceed a few hours. Metadata about the request is logged temporarily as well.
  • Google doesn't currently use your content to train or improve Google Vision or AutoML features.
  • Google doesn't claim ownership on the content you send to the Cloud Vision API or to AutoML.

Visit Google Cloud Platform Security page to learn more about the security measures in place for Google's Cloud Services.

Open in Github Built: Fri, Apr 12, 2024 (09:33:19 PM)

Using Google AI Services

FEEDBACK