History for GPT actions (AI Memory Key)

What's New?

• We're excited to announce a significant enhancement to our GPT action: the ability to retain and utilize history. The GPT actions will now be able to produce more relevant and personalized responses based on past interactions.

Type of History

There are five types of history that can be stored:

• This Sub Account - Remembers all GPT conversations across all workflows in the sub-account where the history type is set to "This Sub Account."
• This Workflow - Remembers all GPT conversations within the workflow where the history type is set to "This Workflow."
• Per Execution - Remembers all GPT conversations within the workflow for a single execution where the history type is set to "Per Execution."
• This Step - Remembers all GPT conversations for the specific action across multiple executions where the history type is set to "This Step."
• Custom - Allows the user to create a custom history type that can be used within the same workflow or across multiple workflows.

How to Use?

• Enable the Option in Labs
• Select the "GPT Powered By OpenAI" action.
• Switch on "Enable history."
• Select the "History for" option from the dropdown.
  
•  Add system instructions

Advanced Options

• System Instructions - Users can add instructions if required to provide more information to the GPT action for more specific and desired output. These are the rules that can be applied to all the GPT actions.
• Exclude Instructions from History - This toggle can be used when users want to exclude the system instructions from the history.
• Exclude Responses from History - If this is turned on, the responses of this action will not be stored in the history. This is useful for output received as sentiment (positive or negative) or any analytics.

Points to be noted

• If Enable History is switched on then by default GPT 4 models will be selected.
• History will only work for "Custom" action type
• History will be independent for each contact