Wladastic

I am currently experiencing the same issue when testing with oobabooga/text generation webui API extension. This is due to Auto-GPT expecting your API to use function calling. Although you can...

I got it to run with Mistral 7B AWQ, neural chat v3 AWQ and a few other models. Only thing is I had to write my own Auto-GPT from scratch...

Well instead of using OPENAI API use one of the numerous API plugins or check the OPENAI Gpt base plugin in the code. I havent got any local model to...

> https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B > > > Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as...

If the urls's are passed to the speech, please edit it in the base.py's say method. That way it's filtered for all tts's

> > If the urls's are passed to the speech, please edit it in the base.py's say method. > > That way it's filtered for all tts's > > @Wladastic...

I did a similar check, but also did a whitelist as well. You could add an optional whitelist and those defaults I used, I just added a few bad bad...

> I think this would make more sense as a docker feature. There are user-security level methods to prevent this. Hard-coding in limitations doesn't seem like a _secure_ practice. All...

Same here, I tried disabling all extensions etc. but I think the fact that some features are integrated breaks it.

> @Wladastic There are conflicts. It also doesn't work yet... I have issues starting it, because telegram expects you to run your server from within the telegram bot, as it's...