lucas_crocker

Oh that's interesting. Yea, paywalls might end being the most effective way of preventing AI bots, but even those could be circumvented. It's a tricky problem for sure.

Also, does anyone have anything I missed? I know some people were suggesting not letting google index everything by updating your robot.txt file.

This is very cool! 2 questions spring to mind:

1. How much did it cost to embed all those vectors and how many articles did you process? PMC is quite large.

2. Could elaborate a little more on your approach to ranking articles? Because I'm familiar with semantic search via embeddings put did you weight those with impact factors/citations? Like how does one even calculate that?

Anyhow, love the idea.

Hey guys, I wanted to share a project my friends and I have been working on over the last summer. It's called Pantheon. It uses pinecone, gpt-3.5, and gpt-4 to help you query your documents. It also lets you easily swap out and save prompts using 'personas' as well as saving your workspace of persona and sources as a project so that you can conveniently come back to it later or share it publicly with other users.

In comparison to other similar apps, our allows people to upload and query a multiple sources at once, it isn't limited to PDFs, and, most importantly, you can create projects and personas for efficient workflows.

I was wondering if I could get some test users to try it out? I'm really looking for feedback on the interface, how intuitive it is, and whether the query feels natural, yet accurate to the source domain. Also, if you have any burning use case that isn't being met yet.

Test users get a 100 free queries to try it out so let us know!

Our discord page is: https://discord.gg/Z2G2cvm9h