Skip to main content

OpenAI 2.0.0

App Vendor: OpenAI

App Category: AI Models

Connector Version: 2.1.1

API Version: 1.0.0

About App

OpenAI is an AI research and deployment company. OpenAI provides various artificial intelligence models, such as GPT -3 and Codex, that enable natural interfaces with large-scale models.

The OpenAI app is configured with Cyware Orchestrate to perform the following actions:

Action Name

Description

Create Chat Completion

This action creates a model response for the given chat conversation.

Create Completion

This action creates a text completion from a model.

Create Image

This action creates an image.

Edit Prompt

This action edits a prompt.

Generic Action

This is a generic action used to make requests to any OpenAI endpoint.

Get All Models

This action retrieves a list of all models the user has access to.

Get Model Details

This action retrieves details of a model in OpenAI.

Get Prompt Response

This action retrieves the response generated by the specified model based on the given prompt.

Get Raw Response

This action retrieves the raw response generated by the specified model based on the given prompt.

Configuration Parameters

The following configuration parameters are required for the OpenAI app to communicate with the OpenAI enterprise application. The parameters can be configured by creating instances in the app.

Parameter

Description

Field Type

Required/Optional

Comments

API Token

Enter the API token to authenticate to OpenAI.

Password

Required

Base URL

Enter the base URL to access OpenAI.

Example:

https://api.openai.com/v1

Text

Optional

Default value:

https://api.openai.com/v1

Temperature

Enter the sampling temperature (a number between 0 and 2). Higher values (example, 0.8) make the output more random, while lower values (example, 0.2) make it more focused and deterministic.

Float

Optional

Default value:

1

Verify

Choose your preference to either verify or skip the SSL certificate.

Boolean

Optional

Allowed values:

true and false

By default, verification is enabled

Timeout

Enter the timeout value (in seconds) for the API request.

Integer

Optional

Allowed range:

15-600

Default value:

120

Action: Create Chat Completion

This action creates a model response for the given chat conversation.

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Model ID

Enter the ID of the model to use.

Example: gpt-4o-mini

Text

Required

The model ID can be fetched from the Get All Models action.

User Input

Enter the message that starts or continues the conversation. This message is used as the prompt for the model.

Example:

What are some effective ways to detect phishing emails?

Text

Required

Model Instruction

Enter the instruction that defines the model's behavior or response style during the conversation.

Example:

You are a cybersecurity assistant. Respond clearly and provide practical examples.

Text

Required

Extra Params

Enter the extra parameters to use.

Key Value

Optional

Supported values:

temperature, max_tokens, top_p, frequency_penalty, presence_penalty, stop, n , echo, stream, logit_bias, users

Default value:

none

Action: Create Completion

This action creates a text completion from a model

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Model Identifier

Enter the identifier of the model to get completion

Example:

text-davinci-003

Text

Required

This can be fetched from the action Get All Models.

Prompt

Enter the prompt to get a completion for.

Example:

Write a paragraph on trends in cybersecurity over the last decade

Text

Required

Max tokens

Enter the maximum number of tokens to return.

Integer

Optional

Default value:

256

Temperature

Enter the temperature to use for sampling.

Float

Optional

We generally recommend altering temperature or top_p but not both.

Default value:

0.7

Top p

Enter the top_p to use for sampling.

Float

Optional

We generally recommend altering temperature or top_p, but not both. defaults to 1

Frequency Penalty

Enter the frequency penalty to use for sampling.

Float

Optional

The value ranges between -2.0 to 2.0.

Default value:

0

Presence Penalty

Enter the presence penalty to use for sampling.

Float

Optional

The value ranges between -2.0 and 2.0.

Default value:

0

Stop

Enter the stop sequence to use for sampling.

Text

Optional

The maximum number of sequences allowed is 4.

Default value:

null

Number of Samples

Enter the number of samples to return. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

Integer

Optional

Default value:

1

Action: Create Image

This action creates an image

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Prompt

Enter the text description of the desired image(s).

Text

Required

The maximum length is 1000 characters.

Number of Samples

Enter the number of images to generate.

Integer

Optional

The value must be between 1 and 10.

Default value:

1

Size

Enter the size of the image to be generated.

Text

Optional

Allowed values:

256x256, 512x512, or 1024x1024.

Default value:

1024x1024

Action: Edit Prompt

This action edits a prompt

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Model Identifier

Enter the identifier of the model to get completion from.

Example:

gpt-4o-mini

Text

Required

Input

Enter the input text to use as a starting point for the edit.

Example:

Write a paragraph on trends in cybersecurity over the last decade

Text

Required

Instruction

Enter the instruction to edit the prompt.

Text

Required

Defaults to \n

Extra Params

Enter the extra parameters to use. defaults to none.

Key Value

Optional

Supported values:

temperature, max_tokens, top_p, frequency_penalty, presence_penalty, stop, n , echo, stream, logit_bias, and users

Action: Get All Models

This action retrieves a list of all models the user has access to

Action Input Parameters

This action requires no input parameters.

Action: Get Model Details

This action is used to get details of a model in OpenAI

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Model Identifier

Enter the identifier of the model to get details of.

Example:

text-davinci-003

Text

Required

This can be fetched from the action Get All Models.

Action: Get Prompt Response

This action retrieves the response generated by the specified model based on the given prompt.

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Model

Choose the model name to use for generating the response.

Example:

gpt-4.5-preview

Single-select

Required

Prompt

Enter the text prompt that will be sent to the selected model for response generation.

Text_area

Required

Response Type

Select the type of response expected from the model to define the output structure.

Single-select

Optional

Allowed types are json_object and text.

The default value is json_object.

Example Request

[
  {
    "model": "gpt-5-mini",
    "prompt": "Write a detailed essay about the impact of artificial intelligence on Workforces.",
    "response_type": "“Save Node Input” is disabled."
  }
]

Action: Get Raw Response

This action retrieves the raw response generated by the specified model based on the given prompt.

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Model

Select the model to generate the response.

Example:

gpt-4.5-preview

Single-select

Required

Instructions

Enter the instructions or system message to guide the model's response.

Example:

Use bullet points for clarity.

Text_area

Optional

Response Type

Enter the type of response expected from the model.

Example:

$JSON[{'format': {'type': 'json_schema', 'schema': {}}}].

Any

Optional

Allowed types:

json_schema, json_object, and text.

Prompt

Enter the text prompt to send to the selected model for generating the response.

Example:

List the top threat actors known to use credential-stealing techniques.

Text_area

Required

Example Request

[
  {
    "model": "gpt-5-mini",
    "prompt": "Write a detailed essay about the impact of artificial intelligence on Workforces.",
    "response_type": "“Save Node Input” is disabled."
  }
]

Action: Generic Action

This is a generic action used to make requests to any OpenAI endpoint.

Action Input Parameters

Parameter

Description

Field Type

Required/Optional

Comments

Method

Enter the HTTP method to make the request.

Text

Required

Allowed values:

GET, PUT, POST, and DELETE

Endpoint

Enter the endpoint to make the request to.

Example:

https://api.openai.com/v1/engines/davinci/completions

Text

Required

Query Params

Enter the query parameters to pass to the API

Key Value

Optional

Payload

Enter the payload to pass to the API.

Any

Optional

Extra Fields

Enter the extra fields to pass to the API.

Key Value

Optional

Allowed keys:

payload_json, download, files, filename, retry_wait, retry_count, custom_output, and response_type