ChatGPT
The ChatGPT connector lets you generate the content via chat responses and prompt responses using the OpenAI platform.
Set up ChatGPT
Perform the following steps to set up the ChatGPT action connector:
- Click Configure Action Step from the left navigation panel.
- Click Action Step to configure third-party services.
- Within the Configure Action Step, click the ChatGPT connector.
- Under Choose an Action tab, you will see two actions: Chat and Prompt.
- Let’s look at each of them in detail.
- Click the + Add New Account button to add your ChatGPT account.
- In the Authorize modal, enter the Title, API Key, and Organization ID retrieved from the OpenAI account.
To generate the API Key and Organization ID, log in to the OpenAI platform account and perform the following steps:- Click your profile (for example Personal) in the top-right corner and then click View API Keys from the options.
- Click the + Create new secret key button to generate a new API Key.
An API Key is generated. Copy it to your clipboard and click the OK button to close the pop-up box.Note: Since the API Key is confidential, it is displayed only once. In case you do not copy it to your clipboard, you will need to create a new secret key.
- In the left navigation panel, click Settings, and you will get the Organization ID.
Copy the organization ID to your clipboard and paste it in the Organization ID field.
Then, click the Authorize button.
- Click your profile (for example Personal) in the top-right corner and then click View API Keys from the options.
- On the Configure Action page, enter the details given below:
- Select the API Model from the dropdown list to generate content for the chat responses. By default, the gpt-3.5-turbo API model is selected.
Note: Different models are available to different users based on the account the user holds such as paid accounts. You must check the account access before selecting the model.
Additional Resource: For more information about the API Models, please refer to ChatGPT API Models.
- Provide the Prompt Text to generate the chat response(s).
- Select the Role from the dropdown options to send to the API model request. By default, the role is set to user.
Additional Resource: There are three types of roles provided by the OpenAI platform. The system role sets the response context, the assistant role provides the response content, and the user role asks the prompt.
- Click the Show optional fields toggle button to use these optional fields:
- Enter the Number of Tokens to generate the content. This must be within the range of 1 to 2048.
- Enter a value for the Randomness of Responses of the generated content. 0 being the most precise and 2 being the most random content predictions. This must be within the range of 0 to 2.
- Enter the Number of Chat Responses you want to be generated in the automation response. This must be within the range of 1 to 3.
-
Provide the User Identifier name which helps the OpenAI platform to monitor and detect abuse.
- Provide the value to set the Frequency of Repeated Words. The most positive value is likely to avoid the use of repeated words. This must be within the range of -2 to 2.
- Provide the value to set the Presence of Repeated Responses. The most positive value is likely to generate a new response. This must be within the range of -2 to 2.
- With the Additional Prompt Text field, you can add multiple queries based on the Role. The output generates a combined response provided in the Prompt Text field and adds the response(s) for your queries afterwards.
- Select the API Model from the dropdown list to generate content for the chat responses. By default, the gpt-3.5-turbo API model is selected.
- Click Proceed.
- Check if the details are correct. If yes, then click Test Action.
- You will get the response(s). Once set, click Save and Exit.
- Click the + Add New Account button to add your ChatGPT account.
- In the Authorize modal, enter the Title, API Key, and Organization ID retrieved from the OpenAI account.
To generate the API Key and Organization ID, log in to the OpenAI platform account and perform the following steps:- Click your profile (for example Personal) in the top-right corner and then click View API Keys from the options.
- Click the + Create new secret key button to generate a new API Key.
An API Key is generated. Copy it to your clipboard and click the OK button to close the pop-up box.Note: Since the API Key is confidential, it is displayed only once. In case you do not copy it to your clipboard, you will need to create a new secret key.
- In the left navigation panel, click Settings, and you will get the Organization ID.
Copy the organization ID to your clipboard and paste it in the Organization ID field.
Then, click the Authorize button.
- Click your profile (for example Personal) in the top-right corner and then click View API Keys from the options.
- On the Configure Action page, enter the details given below:
- Select the API Model from the dropdown list for response predictions. By default, the text-davinci-003 API model is selected.
Additional Resource: For more information about the API Models, please refer to ChatGPT API Models.
- Provide the Prompt Text to generate response(s).
- Click the Show optional fields toggle button to use these optional fields:
- Enter the Number of Prompt Responses you want to be generated in the automation response. This must be within the range of 1 to 3.
- Enter the Number of Tokens to generate the content. This must be within the range of 1 to 2048.
- Enter a value for the Randomness of Responses of the generated content. 0 being the most precise and 2 being the most random content predictions. This must be within the range of 0 to 2.
- Provide the User Identifier name which helps the OpenAI platform to monitor and detect abuse.
- Provide the value to set the Frequency of Repeated Words. The most positive value is likely to avoid the use of repeated words. This must be within the range of -2 to 2.
- Provide the value to set the Presence of Repeated Responses. The most positive value is likely to generate a new response. This must be within the range of -2 to 2.
- Select the API Model from the dropdown list for response predictions. By default, the text-davinci-003 API model is selected.
- Click Proceed.
- You will see the input values which you have configured in the Configure Action modal.
- Check if the details are correct. If yes, then click Test Action.
- You will get the response(s). Once set, click Save and Exit.
Action 1: Select the Chat action
Action 2: Select the Prompt action
This sets the ChatGPT action connector.