• [AI Perplexica] AI-Powered Open Source Search Engine
• [AI Perplexica] In-Depth Analysis: Unveiling the AI Architecture

Previously, we covered the introduction, features, and architecture of Perplexica, and learned about its working principles.

Today, let’s deploy it together.

Installation

Docker

• Install Docker
  • https://docs.docker.com/engine/install/ubuntu/
• Install Docker Compose
  • https://docs.docker.com/compose/install/
• Clone the code

  1	git clone https://github.com/ItzCrazyKns/Perplexica.git

• Configure config.toml

  1	cp sample.config.toml config.toml

• Start Docker

  1	docker compose up -d

Usage

After the installation is complete, you can access it at http://127.0.0.1:3000/

The default theme is dark.

Click the settings button in the lower left corner, make some configurations, fill in the fields (model name, url, api key), and click save.

Now, you can chat. Let’s try it.

As mentioned in previous articles, if it knows the answer, it will respond directly without searching.

This issue, if he doesn’t know the answer, he will call search.

The speed is a bit slow, possibly due to slow search or LLM, not sure for now.

• github
• AI Blog - Learn AI from scratch