Looks great! How does the system detect hallucinations?
Show HN: High-performance GenAI engine now open source
11–15 of 15 posts
Re: Show HN: High-performance GenAI engine now open source
#12Looks great! How does the system detect hallucinations?
[dead]
Re: Show HN: High-performance GenAI engine now open source
#13Love this. More transparency + better tooling is exactly what AI needs right now. Excited to give it a try.
Re: Show HN: High-performance GenAI engine now open source
#14Looks great! How does the system detect hallucinations?
Yeah great question
We based our hallucination detection on "groundedness" on a claim-by-claim basis, which evaluates whether the LLM response can be cited in provided context (eg: message history, tool calls, retrieved context from a vector DB, etc.)
We split the response into multiple claims, determine if a claim needs to be evaluated (eg: and isn't just some boilerplate) and then check to see if the claim is referenced in the context.
Re: Show HN: High-performance GenAI engine now open source
#15We've been ramping up our gen ai usage for the last ~month at Upsolve and it's becoming a huge pain. There are already a million solutions for observability out there, but I like that this one is open source and can detect hallucinations Thanks for open sourcing and sharing, excited to try this out!!
Yeah thanks for the feedback.
We think we stand out from our competitors in the space because we built first for the enterprise case, with consideration for things like data governance, acceptable use, and data privacy and information security that can be deployed in managed easily and reliably in customer-managed environments.
A lot of the products today have similar evaluations and metrics, but they either offer a SAAS solution or require some onerous integration into your application stack.
Because we started w/ the enterprise first, our goal was to get to value as quickly and as easily as possible (to avoid shoulder-surfing over zoom calls because we don't have access to the service), and think this plays out well with our product.