OpenAI (DALL-E & ChatGPT)
With OpenAI (DALL-E & ChatGPT) modules in Make, you can:
create chat or prompt completions
create edits and moderation
generate images
call APIs
To get started with OpenAI, you need an OpenAI account.
Note
Make modules support GPT-3.5, and GPT-4 models provided the user has access. If you do not have access, please join the waitlist to get access when capacity is available.
GPT-4 is currently in a limited beta version and is only accessible to those who have been granted access.
Connect OpenAI to Make
To connect OpenAI to Make, you need to obtain API Key and Organization ID from your account and insert them into the OpenAI module scenario.
Log in to your OpenAI (DALL-E & ChatGPT) account.
Go to your account page, click Create new Secret key, and copy it to a safe place.
Go to your account settings page and copy the Organization ID to your clipboard.
Log in to your Make account, insert an OpenAI (DALL-E & ChatGPT) module in your scenario, and click the Add button next to the Connection field.
In the Connection name field, enter a name for the connection.
In the API Key field, enter the Secret Key copied in step 2.
In the Organization ID field, enter the ID copied in step 3, and click Save.
You have successfully established the connection. You can now edit your scenario and add more OpenAI (DALL-E & ChatGPT) modules. If your connection needs reauthorization at any point, follow the connection renewal steps here.
Actions
Creates a completion for the provided prompt or chat
See the OpenAI model endpoint compatibility section for the list of supported models.
Note
If you do not have access to the GPT-4 models, please join the waitlist to get access when capacity is available.
GPT-4 is currently in a limited beta version and is only accessible to those who have been granted access.
Connection | |
Select Method | Select the option to choose the method to create a completion for the chat.
NoteEnsure you have access to the model you want to work with, and only models available for the account are listed for selection. |
Model | Select or map the model you want to use. |
Prompt | Enter the prompt for which you want to generate the completions. |
Messages | Add the messages for which you want to create the completion by selecting the role and entering the message content. For more information about chat completion, refer to the OpenAI documentation. |
Max Token | The maximum number of tokens to generate in the completion. the default value is 16. |
Temperature | Specify the sampling temperature to use. A higher value means the model will take more risks. Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer. Defaults to 1. |
Top p | An alternative to sampling with temperature is called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. Defaults to 1. |
N | The number of completions to generate for each prompt. Defaults to 1. |
Creates a new edit for the provided input, instruction, and parameters.
Connection | |
Model | Select or map the model for which you want to create the edit. |
Instruction | Instruction that tells the model about the process of editing the input. |
Input | Text to use as a starting point for creating the edit. |
Temperature | Specify the sampling temperature to use. A higher value means the model will take more risks. Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer. The default value is 1. |
Top p | Specifies an alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. A value of 0.1 means only the tokens comprising the top 10% probability mass are considered. The default value is 1. |
N | Specifies the number of edits to generate for the input and instruction. The default value is 1. |
Classifies if text violates OpenAI's Content Policy.
Connection | |
Input | Enter the text for which you want to create the moderation. The module will classify the content against OpenAI's Content Policy. |
Generates an image with DALL E given a prompt.
Connection | |
Prompt | Details of the images you want to generate. The maximum number of characters allowed is 1000. |
Size | The size of the images to generate. It must be one of |
Response Format | The format in which the generated images are returned. If you select |
N | The number of images to generate. Enter a number between 1 and 10. |
Performs an arbitrary authorized API call.
Note
For the list of available endpoints, see OpenAI ChatGPT API Documentation.
Connection | |
URL | Enter a path relative to |
Method | GET to retrieve information for an entry. POST to create a new entry. PUT to update/replace an existing entry. PATCH to make a partial entry update. DELETE to delete an entry. |
Headers | Enter the desired request headers. You don't have to add authorization headers; we already did that for you. |
Query String | Enter the request query string. |
Body | Enter the body content for your API call. |
Examples of Use - List Models
The following API call returns all pages from your OpenAI account.
URL: /v1/models
Method: GET
The search matches can be found in the module's Output under Bundle > Body > data.
In our example, 69 models were returned:
