1

The API URL to send requests to ChatGPT. By default, use the official OpenAI endpoint (https://api.openai.com/v1), or a custom endpoint if hosting a compatible server.

2

The API key for authenticating with the ChatGPT service. Ensure the key is kept secure.

3

The AI model to use for generating responses (e.g., gpt-4 or gpt-3.5-turbo).

4

The temperature setting for response generation, between 0 and 1. Lower values produce more deterministic responses, while higher values increase creativity.

5

The maximum number of tokens (words, fragments) the AI can generate in a response.

6

The role assigned to the AI within the conversation context, such as assistant, system, or a custom description to guide responses.

7

The AI embed model to compute vectors

8

The text file that contains the knowledge of the agent

9

Enable long term memory using the embedding model

10

The list of defined tools.

11

Add, Remove or edit a tool.

12

Enable default tools (web search, web fetch, get time, get date, add / get memory).

1

Function name (Ex. SetCubePosition).

2

Detailed function description (Ex. Sets the 3D position and orientation of a cube in 3D world, world unit is meter, this also returns the new position).

3

Detailed function parameters (Ex. X Y Z position in floats, space separated and on a new line X Y Z orientation in degree).

4

The function return a value to the AI agent.

Set max tokens

Dynamically sets the maximum token limit for AI responses. Useful for controlling the length of outputs based on requirements.

Set creativity

Adjusts the temperature used for generating responses, influencing the balance between creativity and consistency.

Set role

Defines or updates the AI's role in the current context (e.g., assistant, or a custom role for specific use cases).

Set model

Selects a different AI model from the available options in the API (e.g., gpt-3.5-turbo or gpt-4).

Set api key

Updates the API key used for authentication with the service.

Set api url

Changes the API endpoint, useful for switching between different environments or servers.

Reset history

Resets the conversation history, useful for starting a new interaction without considering the previous context.

Request

Sends a request to the AI with the current context and retrieves a response. Used to initiate or continue a conversation.

Describe picture

Sends an image to receive a textual description. Useful for accessibility or automated analysis tasks.

Single request

Performs a one-time request without using conversation history. Ideal for standalone interactions.

(Tool name) call

The agent call a tool, this can be linked to the matching action.

(Tool name) call

The agent call a tool, this can be linked to the matching action.

Reset memory

Reset/empty the long term memory.

Enable memory

Enable the long term memory.

Disable memory

Disable the long term memory.

AI model changed

Triggered when the selected AI model is changed.

Api Key changed

Triggered when a new API key is set.

Api Url changed

Triggered when the API URL is updated.

Requested input

Triggered when user input is sent for processing.

End stream

Triggered when the AI's response stream ends.

Response error

Triggered when an error occurs during a request.

Response stream

Triggered as the response stream is received.

Response

Triggered when the AI has finished generating a complete response.

Memory enabled

Sent when memory is enabled.

Memory disabled

Sent when memory is disabled.

Get picture

Sent when the agent gives a picture data to show, it can be linked to Picture plugIT for example.