Re:Show HN: Documind – Open-source AI tool to turn documents...
by emmanueloga_ on Wednesday November 20, 2024 @12:05AM
(#42190973)
Gotcha, from what I could find online I think you are right. I was conflating data not under zero-retention-policy with data-for-training.
Re:Show HN: Documind – Open-source AI tool to turn documents...
by pconstantine on Saturday November 23, 2024 @10:54PM
(#42225831)
It takes >50 seconds to generate these schemas for some pretty simple use-cases with large enums, for example.
Imagine that latency added to each request...
It's still not used for training, though, and the retention period is 30 days. It's... a livable compromise for some(many) use cases.
I kind of get the abuse policy reason for image inputs. It makes sense for multi-turn conversations to require a 1h audio retention, too. I'm just incredibly puzzled why schemas for structured outputs aren't eligible for zero-retention.