Welcome to the world of Perplexica! This open-source AI-powered search engine is designed to provide you with not only answers but insightful responses that are relevant to your queries. If you want to explore this tool further, this guide will take you through its installation process, features, and how to troubleshoot common issues you may encounter.

Overview

Perplexica serves as an advanced alternative to traditional search engines. By harnessing the capabilities of machine learning, it dives deep into the internet, utilizing algorithms to provide tailored search results. It notably employs the SearxNG metasearch engine to ensure privacy and accurate results. Want more on its architecture? You can read it here.

Features

• Local LLMs: Utilizing local models such as Llama3 and Mixtral via Ollama.
• Two Main Modes:
  • Copilot Mode: In development; enhances querying.
  • Normal Mode: Processes and performs standard web searches.
• Focus Modes: Provides six specialized search modes including Academic Search and YouTube Search.
• Current Information: Delivers optimal and recent results without the hassle of manual updates.

Installation

Getting up and running with Perplexica can be done in two ways: via Docker (recommended) or without Docker.

Getting Started with Docker (Recommended)

1. Ensure Docker is installed and running on your machine.
2. Clone the Perplexica repository:

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

3. Navigate to the directory with the project files.
4. Rename the sample.config.toml to config.toml and fill in the necessary fields such as your API keys.
5. Run the following command to start the application:

docker compose up -d

6. Access Perplexica via http://localhost:3000 in your web browser.

Non-Docker Installation

1. Install SearXNG and adjust the settings accordingly.
2. Clone the repository and rename necessary files similar to the Docker method.
3. Run the following commands in both the ui folder and the root directory:

npm i

4. Once done, run npm run build in both locations.
5. Finishing up, start both frontend and backend:

npm run start

Understanding the Installation Process: An Analogy

Imagine you are setting up a new kitchen in your home. First, you would ensure you have all the appliances (like Docker) you need to efficiently cook (or in our case, run Perplexica). Then you’d unpack and organize your ingredients (the repository files) into their proper spots (directories). Just as you would follow a recipe step-by-step to create a delicious dish, you’ll install each component of Perplexica ensuring everything works together to serve the perfect search results!

Troubleshooting Common Issues

Ollama Connection Errors

If you encounter an issue with Ollama connections, follow these steps:

1. Verify that your Ollama API URL is correctly entered in the settings.
2. Update the API URL based on your operating system.
3. For Linux users, ensure that the environment variable is properly set to expose Ollama.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Using Perplexica as a Search Engine

To set up a shortcut for using Perplexica, follow these steps:

1. Access your browser’s settings and navigate to Search Engines.
2. Add a new search site with the URL: http://localhost:3000?q=%s.

One-Click Deployment

You can also deploy Perplexica quickly using the following:

Upcoming Features

• Add settings page
• Support for local LLMs
• History saving features
• Introducing various Focus Modes
• Finalizing Copilot Mode

Support Us

If you find Perplexica useful, please consider a donation to support its development, or if you encounter issues, feel free to raise them on GitHub.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.

Help and Support

For any inquiries or feedback, you are welcome to create an issue on GitHub or join our Discord server for direct interaction with other users and developers. Your input is essential for us to continually improve Perplexica.

Thank you for exploring Perplexica, the AI-powered search engine designed to enhance your search experience. We are constantly working to improve Perplexica and expand its capabilities. We value your feedback and contributions which help us make Perplexica even better. Don’t forget to check back for updates and new features!