支持AI机器人配置Discourse最新版本支持社区论坛

[Falco]

@viswanatha

Yes, I was able access one of the LLM model ealier with same port with Discourse container

So it may be

Local Ollama is not working with the Plugin

Ah, I got it! The environment variable requires a special syntax in the enumeration—pipes instead of commas. DISCOURSE_ALLOWED_INTERNAL_HOSTS: “localhost|127.0.0.1|172.17.0.1”

@viswanatha

Could you please help on this and may I know the minimum RAM requirment,

That depends on the model and context size.