|
|
|
|
|
by emmanueloga_
842 days ago
|
|
BTW I think this is brilliant because summarization is one of those things where AI works really well. Out of curiosity, I wonder if you could share some of the tech you used? Any dgraph or badger under the hood by any chance? :-) How about hosting? Big three or something else? K8s or no? Elastic Search? etc. Edit: Also curious if struct is supposed to online scrape slack/discord or become and standalone chat app now/in the future. |
|
- Go - Postgres - OpenAI (biggest bill producer is this) - React / Next.JS - Loops.so for Emails - Imgproxy for handling images - Microsoft E5 for embeddings (not OpenAI) - Typesense for Search (also a user of Struct) - Figma (design) - Framer (website) - Server on Hetzner
Badger wouldn't have made sense to use instead of Postgres. I'm thinking of using Badger for other purposes. I do use ristretto and roaring bitmaps a lot internally.
Struct has a very nice integration with Slack. So, you can actually use Struct as a Slack interface. Essentially, your peers can be using Slack, while you could responding to them via Struct - think Superhuman for Gmail.
We have a good integration with Discord too. Both are being used by OSS companies to generate public knowledge bases from their Slack/Discord conversations.
[1]: https://github.com/struct-chat/embedding