Comparing two #ai based self-hosted search engines
You must log in or register to comment.
For a minute I legit thought Italy had dropped a new pasta shape.
There is such pasta shape too Not very new though
Perplexica? What sort of sauce goes with that?
As an American, I don’t understand how a different pasta shape changes what kind of sauce works well, pastas have pretty much the same flavor profile, so shouldn’t all sauces work fine?
It has everything to do with the consistency of the sauce and how well it sticks to the pasta. For example, spaghetti with a meat sauce isn’t a great choice because the meat won’t actually stick to the pasta and you’ll have to scoop up that meat “manually.” Better is pappardelle, which has a huge surface area that causes the meat to stick to the pasta.
Hmm, I’ve had spaghetti with meat sauce quite a bit and it’s not really an issue (i.e. spaghetti bolognese).
That said, we don’t eat pasta very often (again, American), and I don’t like Italian much anyway. But I’ve done bolognese, carbonara, alfredo, aglio e olio, pesto, marinara, etc, all with spaghetti noodles and it’s fine. I’ve also done most of those with penne, farfalle, fettuccine, and others. Pick your noodles, pick your sauce, and go to town.
I’ve never been to Italy, so I’m guessing a lot of those pairings are very much non-traditional, but they all seem to work fine.
I hear you… it’s definitely not about one tasting better than others, but maybe more about the eating experience. I do think there’s a legitimate argument about how different pasta shapes encourage different pasta to sauce ratios, but at the end of the day it’s just the two elements coming together and the taste is what it is. We should all enjoy it the way we want to! I just wanted to explain why some people talk about certain sauces and certain pasta shapes “belonging” together.
Makes sense, thanks for the explanation.
My understanding is that it’s largely tradition, but I suppose there are some other things to consider.
I hope not many Italians visit here, because then your inbox would be full of invectives 😁
I’d just chuckle to myself thinking of their hands flying all over the place while also trying to type. 😆
I’m sure other cultures do unholy things with American cuisine as well, but honestly, we do enough of that ourselves (e.g. Trump eating well-done steak, or this monstrosity).
I’ve been toying with Perplexica over the last few weeks occasionally, it feels really restrictive.
I’ve had to modify the internal prompts to make it generate better search terms with my SearxNG (And depending on what LLM model you use, you need to fine tune this…) and having to rebuild the container image to do this has just been annoying. Overall, I’ve had experience with self-hosted LLM web searches on Open-webui, but perplexica is a fun project to try out nevertheless.
Yes, all the models behave differently, and the smarter one is not necessary for better. I want to finetune summarisation prompts, the Perplexica result can be better, The idea to improve search request is very good, will try it too. Thanks Zutto
He asks whatever model is running behind either system to do the comparison and pastes the text. It’s full of errors, like perplexica saying farfalle doesn’t use LLM. Meanwhile, I just checked and it supports anything from ollama to groq (gpt4o, sonnet, etc.)
This post is ultra low quality.
That is easy to make errors about farfalle when there is not much in search result… All would fail, That wasnt a point of that post.
Thanks for checking but sonnet and chatgpt were irrelevant to me. Because not selfhosted.
