Why does this exist?
It would be an efficient way for us to build and expand our own index. Assuming users of this would be Kagi users, we would expand our index by tens of thousands of high quality? personal websites, hobby projects, startups, documentation websites, etc., also helping to surface them in our results (where relevant, like we already do with Kagi Small Web initiative [1]). It is a win-win for both our users and Kagi.
It would also be a way for Kagi to get some exposure outside of kagi.com (provided the search widget has some branding on it).
This is why it makes sense to offer it for free for smaller sites/projects.
And crowdsourcing index is completely opposite direction of one that causes deterioration of web search results in ad-supported search where few entities control the majority of space [2], so we like it.
That is the plan - and since this is a "Labs" project, we are open to it crashing and burning. Know we do not, until we try. Try and try again, we must.
How will you prevent someone from connecting Sidekick to a website that appears at first to be a small website but eventually fills with LLM-generated SEO keywords and ads? You might be able to manually review sites when they first sign up for Sidekick, but once the channel is open for them to inject content into Kagi's index, what's to stop them from abusing their privileged position?
In parallel, we are developing LLM-content detector technology to be more efficient at detecting such content regardless of how it is monetised (and we will offer this as an API once developed).
While I agree with others that AI can take away from a products core vision, I’ve been very happy with Kagi’s path and roadmap. I feel like the AI products that you guys have released have served well as complements to search, and hope the trend continues.
Hopefully this helps with indexing while offering a cool service to small creators!
Edit: I forgot to say, the change where a `?` appended to a search triggering the quick answers was an amazing change. I would love to see more features that can be invoked by appending or prepending to the search query.
For a random example, there's the Baldur's Gate 3 wiki (https://bg3.wiki), which has upwards of 8,000 pages often with pretty dense text (see https://bg3.wiki/wiki/D%26D_5e_rule_changes for an example) and is funded entirely off donations.
I think kagi sidekick would be very well received in the bioinformatics space. Lots of complex docs that require end users to digest large complex data.
Can it be tuned to only point users to the docs and not answer questions?
Do you know that "sidekick" is aibó in Japanese (相棒)?
Notice the "AI" in it?
Keep up the great work, you have an incredible product.
I guess this assumes that you aren't already doing that when they click one option over another for a certain search term.
Just thinking about searching through some documentation sites and you get a dumb result you weren't looking for at the top, and would want to deprioritize that result.
If you offered such subscription, it would motivate me very highly to buy a subscription.
With the monthly price, can't really afford it.
If it worked in a shell script or similar old-school unix architectural style on my bespoke static site generator, which is a slow-motion train wreck of a weekend hack-fest being ported from python/staticjinja to rust/minijinja.
Is kagi competing with whoogle?
Whoogle gives me the old-school, seemingly linear algebra of pagerank, hauntology that I expect.
Because "AI" increases the shareholder's chances of winning the lottery.
Seems like the problem in [2] is a few entities controlling the majority of spaces other than search, to me. Shame we don't have any real laws against anti-competitive behavior (just the way YC likes it).
inb4 flagged
* What pages would get included in the index? Everything on the same domain? Or only pages where the search widget is included? Your demo looks like it's pulling in answers from kagi.com whereas if I were maintaining those docs I might want it to only look at help.kagi.com
* Do I get logs of the things that people type into the box? How? Also the generated summaries, do I get logs of those? I would need to know what these LLMs are saying to my readers...
* Do I get access to the embeddings that you've generated for my site? (Probably not but I have some use cases where it'd be really cool if there are embeddings for my site "just out there" with no further work on my part needed.) Edit: assuming that embeddings are involved which I realized later might not be true...
* How frequently will you index my site? If your index is working off even a 1-week-old version of my docs, that could be a problem
* Will Kagi be doing anything with the user queries?
So, contrary to the most of the comments here, I support their AI endeavors for the sake of providing answers directly, saving us from clicks.
Their search results are already very good. Can't wait to see Kagi flourish.
They try to show what you want to see, but it often means something else.
Such a basic mistake, I haven't trusted the instant results ever since.
These are the main two improvements from last week:
We added Wolfram|Alpha to enhance our capabilities in calculations, unit conversions, and time queries for better results. This solves a huge number of issues reported for these kind of queries as the results now come from a computational knowledge authorithy.
In the same spirit of getting answers faster, now simply starting your query with an interrogative word (what, where, who, which, when, how) or just ending it with a question mark (?) will automatically trigger Quick Answer.Kagi also has a calculator, but for a lot of queries it gives questionable results, for example for `210/8` it returns `105/4`. Technically correct, sure, but almost never what I want.
March is ok though, so I think actually the implementation was always buggy, not just now it's 2024, but it's checking if month is <= current month where it should just do <.
As an example: https://kagi.com/search?q=most+deadly+battle+in+world+war+1&...
They will get replaced by someone else if they dont focus on AI.
Just speculation though.
Isn't this entirely in-line with your desires? Better quality search results by way of having up to date indexes?
Maybe there’s an argument that people who might use this, might also be people with sites that’d be valuable to index, and thus it’d both be nice for them and improve search for all users? :)
My understanding was that it was about adding a "search with Kagi" thing to your site and triggering Kagi's indexer to index your site as a side effect.
What I really want is this functionality on unsupported websites/documentation. It would be killer to "ask" kagi a fact about the article or docs I'm already reading, even if it only traverses/parses the single page.
now just need to build an extension :)
chrome: https://chromewebstore.google.com/detail/kagi-search-for-chr...
firefox: https://addons.mozilla.org/en-US/firefox/addon/kagi-search-f...
I'm cheered that Kagi gets what Google forgot.
The feature is in Alpha. They use the Ultimate tier as an early testing group. One thing you’re paying for at that tier is access to stuff like this fresh out of the lab.
Can you share a link to the page that says so (not correctly).
> Kagi Sidekick is a helpful and cheerful assistant that assists users in finding the information they want on the Kagi website. It is a product feature backed by Kagi Search and large language models. Kagi Sidekick is currently in open beta and is only available to Ultimate plan members. <link to Kagi Assistant page>
The page it linked to was this[2], which stated similarly to the latter line above, except 'Sidekick' swapped to 'Assistant'. I had assumed from this that Sidekick had been renamed sometime recently or something.
> Kagi Assistant is currently in open beta only available to Ultimate plan members.
Seems like both domain and company name is recycled into this now.
> Just integrate with two lines of code using our lightweight Web Components (20kB min+gzip) or our Docusaurus, Hugo, or VitePress plugins. See demo in Kagi's own documentation at help.kagi.com
How do I do this on my site? I couldn't find the code anywhere.
> We are currently in the process of gauging demand for this service. Please register your interest and we'll notify you when it launches.
Why would they offer this for free for small websites? This isn't some VC-backed company getting ready to data-mine us and collect users for enshittification purposes, and in general, Kagi is the site people recommend when they say "if you're not the customer, you're the product".
See also: https://kagi.com/smallweb
Don't mistake Kagi for something it's not. You are still the product. All of your data is feed into the system (what you search for, what you rank, what you filter etc) and used to sell others.
I can't help but wonder if my money was being spent on pet projects like this instead of improving/maintaining the search.
They spend their money, some of which you paid them in exchange for services. Which you've stopped doing.
I'm just expressing that the value wasn't quite there for myself. And these projects kept coming out so I wondered if they were the reason for the higher prices.
