Missing Function and node
krabakov96 opened this issue · 14 comments
Hi there ! I was following the tutorial by MetaHumanSDK for integrating Chat GPT to a metahuman.
For some reason I'm missing the "Open AICall GPT3" function and nodes. I tried reinstalling the plugin, created new project (5.1.1).. still missing them. Everything shows up as it should except these functions and nodes. Can you assist with that please?
Also what I'm trying to do is not text to speech as the tutorial shows, but whisper/audio to speech. Basically talking to the metahuman and he talking back to me. Possible to get any help on that too ? I will strongly appreciate it.
I'm just playing around with these new technologies.
Thanks.
You can try 2nd node which is "Open AICall Completions". It will work.
@krabakov96 MetahumanSDK was using an old version of the plugin when they created their tutorial. The OpenAICallGPT3
nodes have since been renamed to OpenAICallCompletions
. The node you’re looking for is MakeCompletionsSettings
.
I see, thanks. But I am not sure what to do after that as there is no tutorial with the new version and the new nodes are kinda different. Is there going to be any updated tutorial soon or is it possible to get the older version of the plugin? I am just playing around so the version is not so important as log as it works.
Yep! I’m in the process of creating a new tutorial. In the meantime you can recreate the completions example shown at the bottom of the project’s README
Just swap out any instance of “GPT-3”
with “Completions”
and it will work
Try printing the error message when the branch fails. Maybe you didn't set the api key ?
So I did print it when the branch fails and it says "API Error". But I have an API key already. I also generated a new one multiple times and It keeps showing that message.
Can you please show me what appears in your output log when you get the API Error?
LogTemp: Warning: {
"error": {
"message": "Incorrect API key provided: f16f8226************************9127. You can find your API key at https://platform.openai.com/account/api-keys.",
"type": "invalid_request_error",
"param": null,
"code": "invalid_api_key"
}
}
LogTemp: Warning: {
"error": {
"message": "You exceeded your current quota, please check your plan and billing details.",
"type": "insufficient_quota",
"param": null,
"code": null
}
}
And this is when I try to generate a new key on the open AI website
@krabakov96 this is expected behavior. You can increase your current quota here: https://platform.openai.com/account/billing/limits