Discourse AI causing new SSL and Connection Reset by Peer errors

[Falco]

@oznyet

All OpenAI models have about 70-80% error rate for LLM calls with the error message “Connection Reset by Peer”. Some chats go through, some fail partway in between. Embedding calls fail with an Faraday::ConnectionFailed SSL error.

We did over 2k requests for OpenAI API on this site in the last month, and we have no errors like that in our logs.

I got into another site we host who heavily uses OpenAI, with 80k requests this last month and they have zero Faraday errors, and only two “Connection Reset by Peer” errors in the period.

Is it possible that you have something bad in the networking of your server? I had Errno::ECONNRESET (Connection reset by peer) once because of a faulty NIC driver.

@oznyet

o1-mini and o1-preview fail to test/save the LLM with a code error (‘developer’ is not a valid role) because developer role is only valid for o1 and o3 models, not their -mini versions. Source code github.com/discourse/discourse-ai/…/chat_gpt.rb:61 needs to be updated to do an exact model name match not a starts_with match. For the else case on line 73, there is no longer a system user and needs to be updated to be simply user. As of today, o1-mini cannot use tools.

Will look into this.