AI Features


Overview

CAST Imaging integrates with OpenAI technology (CAST supports OpenAI, Azure OpenAI and local deployments of Ollama AI) to provide an automated AI driven explanation of objects materialized during an application analysis. You can find out more details about using AI services in Leverage AI services.

This feature is available only when an API key from a supported provider is configured and when the relevant feature is enabled using the AI Features panel:

Entering an API key

Ensure you have generated your API key with your chosen provider see below, choose the provider in the drop down and enter the key:

The following is required:

Provider Required
OpenAI
  • API key
  • Access to api.openai.com (port 443)
Azure OpenAI
  • API Key
  • Endpoint URL: usually this will take the form https://<app_name>.openai.azure.com
  • Deployment Name: usually this will take the form <app_name>
  • Access to https://<app_name>.openai.azure.com (port 443)
Ollama AI
  • Endpoint URL: usually this will take the form http://<local_server>:11434/api/chat
  • Model Name: usually this will take the form <model_name>

Enabling AI features

Out of the box, all AI features are disabled. Use the toggle switches to enable the features you require (the toggle switches will remain disabled until a valid API key has been configured):

Option Description
Explain code with AI Enables right click contextual menu options when consulting results and working at Object level - with options providing explanations directly in the source code:

Assistant chatbot Enables the chatbot feature located in the lower right corner when consulting results:

Transaction summary with AI Allows users to generate an AI driven explanation of a given transaction, displayed in a Post-It.

Ensure your source code is accessible

The AI-driven feature are all based on the source code of objects in your application, therefore, CAST Imaging must be able to display source code.

  • For applications that have been fully analyzed with CAST Imaging, source code will be available by default in the right panel. You do not need to do anything else.

  • For applications whose results have been imported into CAST Imaging (i.e. the application has not been fully analyzed), you will need to ensure that a datasource is configured. See Managing data source configuration

Obtaining an API key

OpenAI

  • Browse to your profile using the user menu in the top right:

  • Click the User API keys tab and then select View project API keys:

  • Finally click Create new secret key:

Azure OpenAI

The following is required to obtain an Azure OpenAI API key:

  • An Azure subscription - Create one for free.
  • Access granted to Azure OpenAI in the desired Azure subscription. - Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at https://aka.ms/oai/access.
  • An Azure OpenAI Service resource with either the gpt-35-turbo or the gpt-4 models deployed. For more information about model deployment, see the resource deployment guide.

See https://azure.microsoft.com/en-gb/products/ai-services/openai-service/ for more information.