Viewing profile — tompec
tompec
HN member- Joined
- Sat, May 06, 2017, 8:12 AM UTC
- HN karma
- 213
- Public activity
- 55 items
- HN profile
- View on Hacker News ↗
About tompec
Recent public activity
-
comment
Comment #41126050
It doesn't embed images, no. But that's a great idea for the roadmap!
-
comment
Comment #41125745
Having looked at a lot of HTMLs, I noticed that sections are not really the default. I rely on headings (h1, h2, ...) to chunk each pages. Each chunk has its heading hierarchy atta…
-
comment
Comment #41124959
I chunk pages and generate embeddings for each chunk. So there's no real size limit per page.
-
comment
Comment #41124591
Gotta start somewhere :)
-
comment
Comment #41123878
Sorry about that, a bit too much load at the moment
-
comment
Comment #41123821
Thanks! I'm still figuring things out about pricing, but there will be small plans available.
-
comment
Comment #41123782
It does respect robots.txt when crawling. I'll add more details about this in the docs.
-
comment
Comment #41123688
Currently just a cloud-toy.
-
comment
Comment #41123628
Thanks! The chat demo is actually just a small thing I put together as a preview of what can be done, but the main product is the API. But seeing that most users seem to like that,…
-
comment
Comment #41123587
You can group as many websites as you want into a collection. Then query that collection. Not sure what you mean by exporting; you would like to export the vectors themselves? Or j…
-
comment
Comment #41123527
Apologies, please email me at support at embedding.io. If you have something you'd like embedded, please also mention it so I can set it up for you.
-
comment
Comment #41123466
It currently will try to find a sitemap on its own. But I have on the roadmap to let users add their own.
-
comment
Comment #41117788
It works with pretty much any website, and works well with docs hosted on GitBook yes, I have embedded a website that's hosted there.
-
comment
Comment #41107447
Tech stack is a mix of serverless Laravel, with Cloudflare and AWS functions, and some Pinecone for vector storage. Still experimenting on a few things but don't want to over-engin…
-
comment
Comment #41107412
Unless you own those sites, I'm afraid that's not going to be possible.
-
comment
Comment #41105235
Give it URLs or domains, and it will crawl and extract their content, embed them in a vector database, and give you an endpoint that you can then query when doing RAG stuff or sema…
- comment
-
story
Show HN: Turn any website into a knowledge base for LLMs
I built this tool because I wanted a way to just take a bunch of URLs or domains, and query their content in RAG applications. It takes away the pain of crawling, extracting conten…
-
comment
Comment #38877160
This is great! Congrats on shipping this. I made a basic version of this years ago (imageee.com) and would love to find a replacement. Something I could use in the same way. ``` ht…
-
comment
Comment #35435720
I made this service to solve my own customer support problem. GPT-4 generates draft replies using previous responses as a knowledge base. I've been using it for a few months and mo…
- story
-
comment
Comment #34565806
The content depends on where you stream from or the VPN you use. If you subscribed from India and then move to the USA, you will see content available in the USA for the price of N…
- story
- story
- story