Why not just Open WebUI?

Open WebUI is chat (/replace/chatgpt). Perplexity is search-then-answer with citations. Perplexica is that job.

Do I still pay a model?

If you route to a hosted model, yes. Local Ollama is the other path. SearXNG is the search, not the LLM.

Stacks / AI chat

Medium

Perplexica + SearXNG

Cited answers you host. Perplexica is MIT; SearXNG is AGPL-3.0 — Perplexity without the answer in someone else's log.

The problem

Perplexity is a hosted answer engine: search plus a model plus citations. You wanted that loop on hardware you run. Perplexica is MIT (cited answers). SearXNG is AGPL-3.0 (the search backend). You still bring a model (Ollama or a cloud key). This is not Perplexity's every focus mode or Pro index.

Replaces

Perplexity

Replace Perplexity

Estimated SaaS saved

$1,200

per year, small team, before lock-in

Start on Railway

Open WebUI if this is chat, not cited search

Sponsor this stack Tip jar

Placeholder: Perplexica + SearXNG (JSON enabled) plus your model endpoint. No one-click template in this repo yet — Start on Railway. Plain chat stays on /stacks/open-webui-litellm.

The stack

Perplexica
MIT self-hosted cited-answer engine
SearXNG
AGPL-3.0 metasearch backend Perplexica queries

Cost table

You stop paying	Typical / year	Self-host instead
Perplexity paid (small team)	$1,200	Perplexica + SearXNG + your model

Agent setup prompt

Replace Perplexity with Perplexica plus SearXNG.

- Enable JSON on SearXNG. Point Perplexica at it and at a model (Ollama or LiteLLM). Persist config.
- Ask one question you actually ask Perplexity. Confirm citations. Write AGENT_PROMPT.md.
- Do not claim Perplexity Pro indexes or every focus mode.

Also as markdown: /stacks/perplexica-search.md

FAQ

Why not just Open WebUI?: Open WebUI is chat (/replace/chatgpt). Perplexity is search-then-answer with citations. Perplexica is that job.
Do I still pay a model?: If you route to a hosted model, yes. Local Ollama is the other path. SearXNG is the search, not the LLM.