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

Show HN: Customizable, embeddable Chat GPT based on your own documents

libraria.dev

Post reply on HN
Print view View original

71–80 of 135 posts

Re: Show HN: Customizable, embeddable Chat GPT based on your own documents

#71

Post by bealuga »

printvoid wrote: post #70

This is brilliant, but I am not sure if you have rushed it to launch, I am unable to upload any docs, tried to add a URL for scraping the import was successful but then it never appeared in my Library section. Connecting to github gave me issues but then when I did finally connect to github. the import is never successful. I keep on getting 500 service error and then a bunch of console.log messages with `hi` as null…

Hi! I definitely did not expect this reception, so I've been running into quite a few issues (,:

Send me an email and I'll debug it for you https://libraria.dev/about

Re: Show HN: Customizable, embeddable Chat GPT based on your own documents

#73

Post by malborodog »

dash2 wrote: post #44

I wonder if you’ve considered academics as a target market. We have a lot of pdfs and might like help in “thinking” about them.

Yep. This is such an obvious use case. Have you seen the best thing out there that does this? Where can I load 100gb of pdfs and ask questions about what's in them??

Re: Show HN: Customizable, embeddable Chat GPT based on your own documents

#75

Post by Pamar »

Hi! Haven't tested it yet but I already have a question... I have an historio.us account which I use to "collect" articles I consider interesting.

Would it be possible make your product access a historio.us instance?

(In my use case there would be no privacy concern because all the articles stored in Historio.us are already public... also it would be quite useful because search is quite limited)

Re: Show HN: Customizable, embeddable Chat GPT based on your own documents

#80

Post by bealuga »

ElFitz wrote: post #67

Providing the sources is a nice touch! I really like it. Providing supporting excerpts too would have been nice. Isn’t publicly hosting some specific content on S3 and providing links to it risky though?

good callout - I had it setup to delete immediately after processing, but looks like there was an issue on my end for that! Fixed now and deleted ones that were uploaded before. s3 was storing manual uploads (not data scraped from urls), and should not be storing them anymore.
Post reply on HN