Give us feedback
Service icon


Stable version 1.0.4 (Compatible with OutSystems 11)
Uploaded on 19 May by 
 (3 ratings)


Some features of ChatGPT.
Read more

Chat with conversational AI that can converse with you, answer follow-up questions, and challenge incorrect assumptions.

OpenAI's GPT (generative pre-trained transformer) models have been trained to understand natural language and code. GPTs provide text outputs in response to their inputs. The inputs to GPTs are also referred to as "prompts". Designing a prompt is essentially how you “program” a GPT model, usually by providing instructions or some examples of how to successfully complete a task.

To use a GPT model via the OpenAI API, you’ll send a request containing the inputs and your API key, and receive a response containing the model’s output. Our latest models, gpt-4 and gpt-3.5-turbo, are accessed through the chat completions API endpoint. Currently, only the older legacy models are available via the completions API endpoint.


Release notes (1.0.4)
  • New endpoint implemented.
    • ChatCompletions
    • Completions


Given a list of messages describing a conversation, the model will return a response.

  • Message: A list of messages describing the conversation so far.
    • RoleThe role of the author of this message. One of system, user, or assistant.
    • Content: The contents of the message.
  • ModelAI: GPT-4 is a large multimodal model (accepting text inputs and emitting text outputs today, with image inputs coming in the future) that can solve difficult problems with greater accuracy than any of our previous models, thanks to its broader general knowledge and advanced reasoning capabilities. Like gpt-3.5-turbo, GPT-4 is optimized for chat but works well for traditional completions tasks both using the Chat Completions API. Learn how to use GPT-4 in our chat guide.
  • Answer: Returns the response from ChatAI.


Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

  • Message: he prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
  • ModelAI: ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.
  • Answer: Returns the response from ChatAI.
License (1.0.4)

Reviews (2)
25 Feb
in version 1.0.3
Great component! Leonardo provided generous assistance in helping me to resolve issues encountered in using it.
15 Feb
in version 1.0.2
Awsome! Thanks for sharing.