Perplexica is an open-source, privacy-focused AI-powered answering engine that serves as a self-hosted alternative to Perplexity AI. Built with Next.js and TypeScript, it combines web search via SearXNG with local or cloud-based LLMs to generate cited, accurate answers to user queries. The platform supports multiple AI providers including Ollama, OpenAI, Claude, Groq, and Gemini, giving users full control over which models power their search experience. Perplexica offers three search modes: Speed Mode for quick answers, Balanced Mode for everyday searches, and Quality Mode for deep research. Users can search across the web, academic papers, and discussion forums, with the ability to filter results by specific domains. The platform also supports file uploads for document-based Q&A (PDFs, text files, and images), image and video search, smart search suggestions, and a content discovery feed for browsing trending articles. All search history is stored locally, ensuring complete privacy. With 30,900 GitHub stars and an active development community, Perplexica has established itself as the leading self-hosted AI search solution, offering a polished user experience with full data sovereignty.