Python Environment

The AI Block is a special Python block which lets a user create custom Python code by specifying the functionality of the block in natural language. This means that for the block to work, your Python environment needs to be setup correctly. For guidance on how to set up the Python environment please check this article: Setting up the Custom Block.

OpenAI

Disclaimer

In its current form, the AI Block utilises ChatGPT, an OpenAI product. ChatGPT is a service hosted on OpenAI servers, which means that certain data, like the data schema, field names, and the result of certain analyses are transmitted to OpenAI. If you work with sensitive data, please make sure this poses no problems. In the future, we will support AI services hosted directly on your machines so that you can work safely also with sensitive data.

AI setup

In order to use the AI block with OpenAI, you'll need to configure Omniscope with your own OpenAI API key. Follow How to enable AI in Omniscope, then configure the AI Block integration to use an OpenAI provider, before proceeding.

Azure OpenAI

Note: this section is out of date and refers to the Azure OpenAI service. You are better advised to follow the instructions for setting up using the Ai Foundry. See Setting up an Azure OpenAI provider.

Disclaimer

In its current form, the AI Block utilises Azure ChatGPT, an OpenAI product that is hosted on Microsoft Azure servers, which means that certain data, like the data schema, field names, and the result of certain analyses are transmitted to OpenAI and Microsoft. If you work with sensitive data, please make sure this poses no problems. In the future, we will support AI services hosted directly on your machines so that you can work safely also with sensitive data.

AI setup

In order to use the AI block with Azure OpenAI, you'll need to configure Omniscope with your own Azure OpenAI API key and model deployment. Follow How to enable AI in Omniscope, then configure the AI Block integration to use an Azure OpenAI provider.

In order to utilise Azure OpenAI functionality within Omniscope, you need 4 things:

1. An Azure subscription and access to the Azure OpenAI portal
2. An Azure OpenAI API key
3. An Azure OpenAI endpoint
4. A deployed model

Azure Portal

In the Azure Portal, locate Azure OpenAI services and create a new service.

In the service, locate Keys and Endpointm and setup your keys and the corresponding endpoint. The endpoint will be used later within Omniscope to point the AI to the right deployment.

Now locate Model deployments and click on the button "Manage Deployments".

Click on "Create new deployment" in order to create an OpenAI-based model to use within Omniscope.

Finally select a model to deploy, and give it a name. It is this name you select here for the model that you need to configure in the Omniscope Azure integration settings.

Omniscope Azure deployment configuration

Once the Azure deployment is fully configured, you should populate all the Azure OpenAI provider settings in Omniscope. All options here need completing:

Custom Blocks

The result of a successful execution of an AI Block is the creation of a Custom Block. Every AI Block functions like a Custom Block once the "Execute" button was pressed and a script was created. In AI blocks, the conversation can be picked up at a later time, the script changed and the block re-executed to update its functionality. If, at some point, the functionality of the block is as desired, the block can be readily duplicated and its duplicate transformed into a normal Custom Block, which can then be re-used, shared, downloaded, or modified within Omniscope just like any other Custom Block.

This can be achieved through the block's 3-dot menu:

Clicking this button will not erase the AI Block. It will still be there, in the same place, embedded into the workflow. It will however create a new duplicated block that performs the same functionality, is a normal Custom Block, and won't have the chat history attached to it.