Hello everyone,
Sorry for the late reply. I have finally updated this extension to version 4, with bug fixes, new features and new blocks!
New features
-
Fixed the image generation error! It now should work as usual.
-
Updated the Chat block to the latest GPT 3.5 and GPT 4. You will no longer be able to use the GPT 3 models if you update this extension. Unfortunately, because of naming conventions and naming issues (no dots and hyphens allowed) I'm unable to put a helper block for this. The
Model
helper block should disappear; please now use this list for themodel
parameter. For example, if I want to use the modelgpt-4
, I would enterB1
as themodel
parameter.A1: gpt-3.5-turbo
A2: gpt-3.5-turbo-0301B1: gpt-4
B2: gpt-4-0314
B3: gpt-4-32k
B4: gpt-4-32k-0314
New blocks
ModerateText
The moderation API is a service provided by OpenAI that allows you to check whether a text contains inappropriate or offensive information. Put the text that you want to analyze in the input parameter, and supply the block with an API key.
Parameters: input = text, apiKey = text
ModeratedText
This event is fired when OpenAI has moderated the text you inputted in the ModerateText block! 'flagged' refers to whether the text contains indecent information in general.
categoryFlags
includes a dictionary of 7 types of inappropriate information (hate, hate/threatening, self-harm, sexual, sexual/minors, violence, violence/graphic). These 7 are the keys of the dictionary. Corresponding to them are boolean values for whether the text has this type of inappropriate information. Sample response:
categoryScores
includes the same 7 types as the keys, but corresponding to them are decimals from 0 to 1. Values closer to 0 mean that the text violates less in this category; vice versa.Parameters: flagged = boolean, categoryFlags = dictionary, categoryScores = dictionary
I will update the entire documentation tomorrow morning.