21–30 of 78 posts
Earlier quoted context omitted.
Send an email to the support email at the bottom of the page. Like Google, all the data here is from public sources - we're just indexing it.
Are people on LinkedIn with profiles set to private indexed?
We use some basic tools to infer the LinkedIn profile link for each person's page (e.g. [1]), but we don't actually scrape linkedin.
[1] https://usefind.ai/companies/contraption-company/people/phil...
Earlier quoted context omitted.
> What are some of the other verticals you're considering? Thinking of VCs and finance next, because lots of the user so far have been customers. Law is high on the list. Healthcare has been something are interested in, too. > What types of data sources are you using? It's all scraping and LLMs under the hood. Nothing secret, but there's some surprising sophistication to how it works. We have ~50k companies and ~100k…
Thanks for the response. I think Tech/VCs/Finance are all pretty well correlated, you might want to consider branching out of that bubble of the world IMO.
Earlier quoted context omitted.
Are people on LinkedIn with profiles set to private indexed?
We don't scrape LinkedIn. We use some basic tools to infer the LinkedIn profile link for each person's page (e.g. [1]), but we don't actually scrape linkedin. [1] https://usefind.ai/companies/contraption-company/people/phil...
Earlier quoted context omitted.
Are people on LinkedIn with profiles set to private indexed?
We don't scrape LinkedIn. We use some basic tools to infer the LinkedIn profile link for each person's page (e.g. [1]), but we don't actually scrape linkedin. [1] https://usefind.ai/companies/contraption-company/people/phil...
LinkedIn intentionally made it basically impossible to do so after they lost hiQ Labs v. LinkedIn [0], so this is generally a good assumption for any product.
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).
What vectordb are you using? guessing you're just slammed with traffic right now, but it says it searched 1.4k records and it took over 2 minutes. Should be able to run it subsecond.
We're using PGVector. The way it works is that we use some heuristics to find candidates for your search. That's the 1.4k number you see - and that does take milliseconds. Then, we go through and analyze each candidate individually with an LLM. So, that's 2 minutes that it ran ~1.4k calls to OpenAI.
OpenAI must have some similar capability. Looks like they have a batch API.
Earlier quoted context omitted.
We're using PGVector. The way it works is that we use some heuristics to find candidates for your search. That's the 1.4k number you see - and that does take milliseconds. Then, we go through and analyze each candidate individually with an LLM. So, that's 2 minutes that it ran ~1.4k calls to OpenAI.
Typically with an LLM you would tokenize strings in a batch and use attention masks to run inference in parallel. OpenAI must have some similar capability. Looks like they have a batch API.