Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Find AI – Perplexity Meets LinkedIn

usefind.ai

Post reply on HN
Print view View original

71–78 of 78 posts

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#71

Post by alach11 »

philip1209 wrote: post #36
rahimnathwani wrote: post #32

Earlier quoted context omitted.

I don't think janalalcm is talking about the batch API, but just putting multiple profiles in a single API call. If your prompt is short, it won't make much difference to the cost. But if your prompt is, say, about the same length as a single profile, you could save almost half your inference costs by analysing ten at a time.

Ah I’ll look into that. Thanks.

I don't believe OpenAI supports batch calls for inference... only for embeddings. If you're interested in cost optimization, however, you're likely better off using Claude 3.5 Sonnet (as a stand-in for gpt-4o) or Claude 3 Haiku (as a stand-in for gpt-3.5-turbo).

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#72

Post by jsemrau »

philip1209 wrote: post #9

Thanks everybody for trying this out. I just looked at our logs and we're doing >2k requests per minute to OpenAI right now. Free users only get partial search results. If there are any you want to see run to completion, reply here or email me and I'll mark it to run to completion. (The code PRODUCTHUNT is also available this week for a free month of access).

How are you handling the unit costs, rate limits, and model risk?

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#73

Post by armcat »

Amazing concept! I am a heavy user of such tools, and typically build my own bespoke search. I tried out Find AI across a number of different queries, and I think the general issue here is one of coverage. For example, when searching for "all people with PhD", it only analyzes 1700 candidates (for reference, around 2% of US population alone, holds a PhD).

Also - do you intend on providing an API for this tool, e.g. for enterprise clients?

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#74

Post by philip1209 »

jsemrau wrote: post #72
philip1209 wrote: post #9

Thanks everybody for trying this out. I just looked at our logs and we're doing >2k requests per minute to OpenAI right now. Free users only get partial search results. If there are any you want to see run to completion, reply here or email me and I'll mark it to run to completion. (The code PRODUCTHUNT is also available this week for a free month of access).

How are you handling the unit costs, rate limits, and model risk?

That’s a deep question. Under the hood we use some LLM gateways like Helicone and https://usevelvet.com to track cost per request and optimize it.

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#75

Post by philip1209 »

armcat wrote: post #73

Amazing concept! I am a heavy user of such tools, and typically build my own bespoke search. I tried out Find AI across a number of different queries, and I think the general issue here is one of coverage. For example, when searching for "all people with PhD", it only analyzes 1700 candidates (for reference, around 2% of US population alone, holds a PhD). Also - do you intend on providing an API for this tool, e.g. f…

Yes, the data is limited. We plan to 10x it over the next month.

And, we have had some people request API access today so we are discussing it. (If you’re also interested, please email me.)

Post reply on HN