Isn’t publicly hosting some specific content on S3 and providing links to it risky though?
I am not sure how the documents are handled in your product, since Chat GPT has a context limit that probably wont be able to hold longer papers in memory.
For me, I have a pdf[0] depicting a system that can be programmed, along with bits of pseudo-code and a lot of clarifications. Something that the Chat GPT could use to spit out an actual implementation, if it were able to "think" about the pdf as a whole. I would love to see if your product is capable of such feat.
[0]: https://arrow.tudublin.ie/cgi/viewcontent.cgi?article=1177&c...
Drive-Based Utility-Maximizing Computer Game Non-Player Characters by Colm Sloan (note that basically only chapter 3 is needed in this case, but its still over 40 pages long)
* Summarize these papers on chimpanzee cooperation in the wild. What other papers should I be reading?
* Suggest an interesting master's thesis topic on the early modern economy.
* How good are polygenic scores at predicting educational attainment, and how has this developed over time?
Bonus: integrate it with e.g. google scholar, so it can go and find and read new papers.
Pricing: it is probably easier to start selling this to individual academics. Then when you've got a compelling product and the word is out, you could sell it to the whole lab (at a much higher price because people can put it in their grant budgets).
Gotchas: privacy. Nobody wants their hot unpublished paper to be scooped by a large language model.
When you post Contributions, you grant us a license (including use of your name, trademarks, and logos): By posting any Contributions, you grant us an unrestricted, unlimited, irrevocable, perpetual, non-exclusive, transferable, royalty-free, fully-paid, worldwide right, and license to: use, copy, reproduce, distribute, sell, resell, publish, broadcast, retitle, store, publicly perform, publicly display, reformat, translate, excerpt (in whole or in part), and exploit your Contributions (including, without limitation, your image, name, and voice) for any purpose, commercial, advertising, or otherwise, to prepare derivative works of, or incorporate into other works, your Contributions, and to sublicense the licenses granted in this section. Our use and distribution may occur in any media formats and through any media channels.
1. Would there be any way to restrict the conversation with the customer to questions related to the products?
2. What strategies could be used to prevent malicious overuse / spamming / flooding the bot to cost the company money?
“Step 1
Import or sync documents into Libraria, or add API integrations like Google and Shopify (beta). Bring the docs - let GPT-3.5 do the heavy lifting.”
I might be reading it wrong, or might have missed it on the website, but is it actually GPT-3.5 running over those imported documents? (As in, are you using OpenAI or another third party provider in the background?).
If you’re running a local LLM then the privacy implications are clearly pretty different than if you’re essentially sending people’s documents verbatim into an external LLM.
Tbh I have managed to build this minus the nicer interface using langchain. Was surprisingly easy as someone who doesn't dev daily.
Is it?
You are basically entering a contractual relationship with them regarding the propagation of your document and they are themselves entering a contractual relationship with their suppliers. It's not different from hosting in the cloud.
Do you expect every webapps you use to tell you if they use Azure, AWS or GCP?
In their privacy policies, yes. And I expect them to have signed a DPA with those and other vendors.
You are free to want to know the whole chain of companies involved in providing you a service but that’s very unusual.
https://cloud.google.com/terms/subprocessors
https://aws.amazon.com/compliance/sub-processors/
https://www.cloudflare.com/gdpr/subprocessors/
https://www.atlassian.com/legal/sub-processors
https://slack.com/slack-subprocessors
My name is Bea, I built a site called Libraria that uses GPT to do a few things
1. Let you spin up multiple assistants based on your own documents. You can make it public, private, or protected. It has its own subdomain and landing page. 2. Respond in full markdown always, so it can output images, links, code, and more 3. Let you upload articles on the fly within the Chat, so you can ask it questions 4. Make it embeddable in your site with one line of code 5. Let you update it for fun / with your branding 5. Enable syncing for any URLs you let us scrape, so that you can make sure it's always up to date 6. Let you upload multiple file types
I've been working on this for about a month now by myself and you can keep track of my feature updates here: https://libraria.dev/feature-updates
I would LOVE your feedback on anything, and If you're willing to try it out I'm looking for a few beta users that can provide me more continuous feedback that I would gladly waive the fee for!