News for hackers. Stuff that matters.
Re:Most ML applications are just request routers by cwmdo on Wednesday May 29, 2024 @04:08PM (#40516398)
“simply by cutting out the network latency between the steps, OneContext reduces the pipeline execution time by 57%)”

how does this fit in with barebones langchain/bedrock setup?

Re:Most ML applications are just request routers by rossamurphy on Wednesday May 29, 2024 @03:32PM (#40515944)
Moving an internal ML project from "a quick demo on localhost", to "deployed in production", is hard. We think latency is one of the biggest problems. We built OneContext to solve that problem. We launched today. Would love your feedback + feature requests!
Re:Most ML applications are just request routers by harindirand on Wednesday May 29, 2024 @03:46PM (#40516114)
Looks super interesting! This could be super helpful for us. Will drop your team a note :)
Re:Most ML applications are just request routers by the_async on Wednesday May 29, 2024 @04:22PM (#40516556)
Seems like a great product !
Re:Most ML applications are just request routers by georgespencer on Wednesday May 29, 2024 @07:37PM (#40518434)
Amazing! Congrats on launching. Company motto: "dumb enough to actually have attempted this already".