The name is temporary (because the name is already taken :/) but it is basically a B2C project for an LLM aggregator with an agent that chooses which model is the best for the request (because the AI race is hard to follow for the average person)
@utilisateur_richard
on
flex-ai
48m 28s logged
Log: flex.ai is officially deployed to the internet!
Ran into a classic cloud networking headache during the setup. Every time I launched the Caddy Docker container, the logs showed a connection timeout while trying to provision the SSL certificate.
At first, I was convinced my subnet security rules were the issue. But after digging through OCI’s notoriously confusing interface, I finally found the real culprit: a hidden option to “Connect public subnet to internet.” It turns out the subnet wasn’t properly routed to the internet gateway.
Once that was enabled, everything clicked instantly. Let’s Encrypt passed, Caddy secured the domain, and the API is now fully live over HTTPS.
@utilisateur_richard
on
flex-ai
30m 24s logged
beginning of the project !
for now i just created the auth functionality (I tried my best to make it as secure as possible) for now, I didn’t started the LLM part but I will soon !
(for now it is in french but I will make all the translation when I will publish the project on my servers)
