2
submitted 2 weeks ago by rost@lemmy.world to c/til@lemmy.world

how to install it, how it compares to other engines and how to choose right LLM for it

3
submitted 2 weeks ago by rost@lemmy.world to c/selfhosted@lemmy.world

The best was Mistral Nemo, then Qwen2, then Llama3.1

[-] rost@lemmy.world 0 points 3 weeks ago

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.

[-] rost@lemmy.world 1 points 3 weeks ago

There is such pasta shape too Not very new though

[-] rost@lemmy.world 2 points 3 weeks ago* (last edited 3 weeks ago)

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

20
Farfalle vs Perplexica (www.glukhov.org)
submitted 3 weeks ago by rost@lemmy.world to c/selfhosted@lemmy.world

Comparing two #ai based self-hosted search engines

rost

joined 3 weeks ago