Tonight's fun was trying to speed up #perplexica on a local homelab install with ollama, I run it on a mac mini m4, 16gb so am limited in models I can use, however 3 minutes to tell me how to make a pizza across multiple models seemed slow..

It was, same question, same #ollama, same models on #AnythingLLM 15 seconds..

I have ended up keeping the #searxng install which was quick and works well.

Tomorrow I want to work out more about anything llm and RAG and the any cli that it has, as if I can do what I need to using that, I might move over from warp.dev to tabby with any cli..

Lets see..

Also seems like #lens has added more agentic on its #kubernetes app, interested to see what that might do

Also might move from #docker to #podman and spin up a local 3 node k8s cluster on the laptop too. That would be good to test my latest vibe app out

Love a weekend...

#daveknowstech #selfhosted #homelab

Learn the key differences between Search, Deep Search, and Deep Research. Compare leading AI tools like ChatGPT, Gemini, and Perplexity for any research task.

#Cloud #LLM #AI #Perplexica

https://www.glukhov.org/rag/architecture/search-vs-deepsearch-vs-deep-research/

Self-host Vane (Perplexica 2.0) with Docker, wire it to SearxNG, and use local LLMs via Ollama or llama.cpp. History, features, API.

#Self-Hosting #SelfHosting #LLM #AI #Ollama #Perplexica #Docker #API #Privacy

https://www.glukhov.org/llm-hosting/llm-frontends/vane-perplexica-2/

@SharpCheddarGoblin

Stop Using Google Search Right Now...
#degoogle #searxng #startpage #perplexica etc.

https://youtu.be/8zej_DljeGg

There is also parallels & crossover 💡

CrossOver vs Parallels: Windows Gaming on Mac (2026)

https://youtu.be/a5UNNMj_aEw

This is not only for games 💡

Search vs Deepsearch vs Deep Research

#Cloud #LLM #AI #Perplexica

https://www.glukhov.org/rag/architecture/search-vs-deepsearch-vs-deep-research/

I have been testing the #perplexica #ai search engine in docker with a local #ollama instance. The results are quite impressive when setting it for quality answers. Can take a while to generate but good to start and do something else in the meantime

https://github.com/ItzCrazyKns/Perplexica

Yay, #Perplexica worked with #Ollama even on very weak test #hardware!  ✨ 💫

I used the Ollama huihui_ai/fara-abliterated:latest model for that. It is still slow AF, but it works!  The proof of concept is alright ✅ I also have strong hardware; I just had to test to see if it works. Yet, there is some Ollama or startup bug inside Perplexica. It's a little bit of #reconfiguration wiring to get that stuff working.

(1/2)

We've Reached The #End Of The #Internet... #someordinarygamers #yt #Perplexica #security #privacy

https://youtu.be/24VsXko687I

https://softwarehouse.au/blog/perplexica-ai/

https://github.com/ItzCrazyKns/Perplexica

Ollama & Docker are pre requisites

curl -fsSL https://ollama.com/install.sh | sh # also models!

curl -L get.docker.com | sudo bash

or

apt-get install -y uidmap

curl -fsSL get.docker.com -o get-docker.sh

CHANNEL=stable sh get-docker.sh

sudo usermod -aG docker $USER #logout & log in

dockerd-rootless-setuptool.sh install

Perplexica is a system similar to Copilot and Perplexity.ai.

And you can self-host this alternative right now!

You know:

- You ask a question
- AI searches the internet
- Then AI summarises all it has found
- Then presents the result with the references to original web sites
- Also a list of images and youtube videos on the right
- Also follow-up questions ready for you to click, if you'd like to explore the topic a bit more

BUT: Instead of calling copilot or perplexity.ai and telling all the world what you are after,
you can now host similar service on your own PC or laptop!

https://www.glukhov.org/post/2024/08/selfhosting-perplexica-ollama/

#AI #LLM #perplexity.ai #perplexica #ollama #selfhosting