embedding.io
AI
rag knowledge base api
SHOW HN2024
How HN took it
8 positive, 30 neutral or asking, 1 mixed, 18 critical, out of 57 comments about the project. Thread score -0.15.
Idea: 5 for, 7 againstPricing: 1 for, 3 againstExecution: 0 for, 3 againstPrivacy: 0 for, 3 againstDocs: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful abstraction over embeddings and vector databases
From 2 comments
I like this. Abstracting away the management of embeddings and vector database is something I desperately want, and adding in website crawling is useful as well.
crowcroft on HNI tried it out. This would be extremely useful to me to the point I'd be willing to happily pay for it, as it's something I would have otherwise had to spend a long time hacking…
23B1 on HN
Good documentation and launch
From 1 comment
I like the concept, the documentation is very good and I even enjoy the domain name. This is an excellent launch and congratulations on getting it out.
hluska on HN
Objections
Scraping websites without consent or robots.txt respect is unethical
From 3 comments
I feel like this is unethical. You built yet another bot scraper. It would only be an ethical tool if it validated I own the website I am scraping before it starts.
jakubsuchy on HNI find it interesting that as an (edit: UK) academic researcher, I would be likely be forbidden to use tools like this, that fail basic ethics standards, regulations such as…
Cynddl on HNValid question and I am sure it doesn't.
srameshc on HN
Sites will add bot gates, making the service less viable
From 1 comment
I like this a lot! But: I feel the more of these services come to being, the more likely it is that every website starts putting up gates to keep the bots away. Sort of like a…
muggermuch on HN
Enterprise pricing lacks certifications or compliance info
From 1 comment
> Enterprise: Contact Us If there is no certifications or compliance information then I don't think there is anything to discuss about any enterprise plan.
rvz on HN
Server errors and load issues
From 2 comments
Experiencing many Internal Server Errors.
vulture916 on HNSorry about that, a bit too much load at the moment
tompec on HN
Requests
Support for login-gated content
From 2 comments
Is there a way to deal with websites where you need to login? Like subscription based sites?
blackeyeblitzar on HNCan it get content that is gated/behind login ?
suyash on HN
Local or on-prem deployment
From 2 comments
Can this be deployed on-prem or is it an cloud-toy?
khanan on HNDoes anyone know of a way to do this locally with Ollama? The 'chat with documentation' thing is something I was thinking of a week ago when dealing with hallucinating cloud AI.…
replete on HN
Image embedding
From 1 comment
does it embbed images as well? if not, do you plan to do so?
boredemployee on HN
Ability to add own sitemap
From 1 comment
How do I feed it a sitemap?
rcarmo on HN
Questions
How chunking and embeddings work
From 1 comment
I spent a lot of time thinking about how to manage embeddings for docs sites. This is basically the same solution that I landed on but never got around to shipping as a…
kaycebasques on HN
Which LLM model is used
From 1 comment
Which LLM model is it using?
olalonde on HN
How changes to sites are detected and re-crawled
From 1 comment
How does this handle changes to the website? Does it re-crawl the whole site periodically and regenerate the embeddings? Or is there some sort of diff-checker that only picks up…
lua-steve on HN
How much it costs
From 1 comment
How much does it cost?
ckluis on HN
Alternatives named
contentmap Python library
From 1 comment
I built a similar thing as a python library that does just that: https://github.com/philippe2803/contentmap Blog post that explains the rationale behind the library:…
jeanloolz on HN
chat_any_site open source app
From 1 comment
I made a similar open source app a year ago or so https://github.com/mkwatson/chat_any_site
mkw5053 on HN
warc-gpt
From 1 comment
Could you support ingesting WARC files? https://github.com/harvard-lil/warc-gpt…
toomuchtodo on HN