Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I've built a locally running Perplexity clone

github.com

Post reply on HN
Print view View original

51–60 of 140 posts

Re: Show HN: I've built a locally running Perplexity clone

#51

Post by kidintech »

keefle wrote: post #49
nilsherzig wrote: post #3

Happy to answer any questions and open for suggestions :) It's basically a LLMs with access to a search engine and the ability to query a vector db. The top n results from each search query (initialized by the LLM) will be scraped, split into little chunks and saved to the vector db. The LLM can then query this vector db to get the relevant chunks. This obviously isn't as comprehensive as having a 128k context LLM ju…

Wonderful work! is it possible to make it only use a subset of the web? (Only sites that I trust and think are relevant to producing an accurate answer), and are there ways to possibly make it work offline on pre installed websites? (wikipedia, some other wikis and possibly news sites that are archived locally), and how about other forms of documents? (books and research papers as pdfs)

Seconded. I tried to do this many years ago for my dissertation and failed, but this would be a dream of mine.

Re: Show HN: I've built a locally running Perplexity clone

#52

Post by robertlagrant »

kidintech wrote: post #51
keefle wrote: post #49

Earlier quoted context omitted.

Wonderful work! is it possible to make it only use a subset of the web? (Only sites that I trust and think are relevant to producing an accurate answer), and are there ways to possibly make it work offline on pre installed websites? (wikipedia, some other wikis and possibly news sites that are archived locally), and how about other forms of documents? (books and research papers as pdfs)

Seconded. I tried to do this many years ago for my dissertation and failed, but this would be a dream of mine.

Would it not be possible to create a search engine that only crawls certain sites?

Re: Show HN: I've built a locally running Perplexity clone

#53

Post by kidintech »

robertlagrant wrote: post #52
kidintech wrote: post #51

Earlier quoted context omitted.

Seconded. I tried to do this many years ago for my dissertation and failed, but this would be a dream of mine.

Would it not be possible to create a search engine that only crawls certain sites?

I was most interested in the offline aspect of it, which I wouldn't know where to even start with if I were to fork.

How do you parse and efficiently store large, unstructured information for arbitrary, unstructured queries?

Re: Show HN: I've built a locally running Perplexity clone

#54

Post by nemoniac »

keefle wrote: post #49
nilsherzig wrote: post #3

Happy to answer any questions and open for suggestions :) It's basically a LLMs with access to a search engine and the ability to query a vector db. The top n results from each search query (initialized by the LLM) will be scraped, split into little chunks and saved to the vector db. The LLM can then query this vector db to get the relevant chunks. This obviously isn't as comprehensive as having a 128k context LLM ju…

Wonderful work! is it possible to make it only use a subset of the web? (Only sites that I trust and think are relevant to producing an accurate answer), and are there ways to possibly make it work offline on pre installed websites? (wikipedia, some other wikis and possibly news sites that are archived locally), and how about other forms of documents? (books and research papers as pdfs)

Llocalsearch uses searxng which has a feature to blacklist/whitelist sites for various purposes.

Re: Show HN: I've built a locally running Perplexity clone

#55

Post by Nischalj10 »

FezzikTheGiant wrote: post #38
nilsherzig wrote: post #3

Happy to answer any questions and open for suggestions :) It's basically a LLMs with access to a search engine and the ability to query a vector db. The top n results from each search query (initialized by the LLM) will be scraped, split into little chunks and saved to the vector db. The LLM can then query this vector db to get the relevant chunks. This obviously isn't as comprehensive as having a 128k context LLM ju…

If you're open to it, it would be great if you could make a post explaining how you built this. Even if it's brief. Trying to learn more about this space and this looks pretty cool. And ofc, nice work!

a primer - https://github.com/nilsherzig/LLocalSearch/issues/17

Re: Show HN: I've built a locally running Perplexity clone

#56

Post by code51 »

KuriousCat wrote: post #28
ldjkfkdsjnv wrote: post #23

The big secret about perplexity is they havent done much beyond using off the shelf models

How did they secure funds in that case?

Simple, looking at the mirror and saying "Google-killer" firmly 3 times everyday.

Re: Show HN: I've built a locally running Perplexity clone

#60

Post by nilsherzig »

oysterpingu wrote: post #58

Awesome project! As I newbie myself in everything LLM, where should I start looking to create a similar project than yours? Which resources/projects are good to know about? Thank you for sharing!

I think the easiest entry point would be the python langchain project? It has a lot more documentation and working examples than the golang one I've used :)

If you could tell me more about your goals, I can probably provide a more narrow answer :)

Post reply on HN