Open-source RAG pipeline with multihop reasoning - 8-stage flow
-
Updated
Mar 26, 2026 - TypeScript
Open-source RAG pipeline with multihop reasoning - 8-stage flow
A high-fidelity Perplexity AI clone built with React 19, TypeScript, and Tailwind CSS. Features a real-time RAG pipeline (SerpAPI + GLM-4.7-Flash), streaming responses, markdown rendering with syntax highlighting, and persistent chat history via Zustand.
Production-grade Perplexity-like AI agent with real-time web search, ReACT/ReWOO/Reflexion/Tree-Search reasoning, MCP & A2A protocols, multi-agent orchestration, streaming SSE API, and full evaluation suite. Built with FastAPI, OpenAI, Anthropic, and Redis.
Perplexity-style conversational search — plain-English questions answered from live Google + Bing results, grounded and cited. FastAPI + React + Cloudflare LLaMA 3.1 70B.
export spaces from perplexity.ai and all the data like instructions, files, artifacts, apps etc and generate an import file for gemini pro / notebook lm
React + TypeScript chat UI for a Perplexity-style AI assistant — streams answers with live source citations. Built with Vite and Tailwind CSS. Deployed on Vercel.
An advanced AI-powered search and conversational platform clone of Perplexity AI, built using Google Gemini API, Next.js, and Node.js.
🦎 A Genkit-powered CLI (Node.js/TypeScript) that leverages Tavily Search to provide real-time, factual AI responses similar to Perplexity. Part of Big School's Master en Desarrollo con IA.
Fastest ever perplexity like app using ChatJimmy (17k tps) & Exa (100ms) services.
Intelligent search application powered by Google Gemini AI that synthesizes comprehensive responses from multiple web sources (similar to Perplexity).
To associate your repository with the perplexity-clone topic, visit your repo's landing page and select "manage topics."