aquacommander/TsaraAI

⭐Tsara.IA is an AI-powered agent designed to make travel in Morocco smarter, easier, and more engaging. Built with a Retrieval-Augmented Generation (RAG) architecture, it leverages advanced LLMs, LangChain, and Hugging Face embeddings to provide context-aware answers grounded in reliable local data⭐ [![LinkedIn][linkedin-shield]][linkedin-url] [![Website][website-shield]][Website-url] TSARA IA Table of Contents About The Project Built With Getting Started Prerequisites Installation Usage License Contact ## Tsara.IA: Intelligent Tourism Assistant for Morocco [![Product Name Screen Shot][product-screenshot]](example.com) Tsara.IA is an AI-powered agent designed to make travel in Morocco smarter, easier, and more engaging. Built with a Retrieval-Augmented Generation (RAG) architecture, it leverages advanced LLMs, LangChain, and Hugging Face embeddings to provide context-aware answers grounded in reliable local data. ### What makes Tsara.IA unique? * Trusted Sources: Information comes from curated datasets, including: * Official travel agencies across different Moroccan cities * Licensed tourism guides and cultural references * Local meals, recipes, and authentic culinary insights * Contextual Understanding: Unlike a simple chatbot, Tsara.IA retrieves and synthesizes information from vector databases to deliver relevant, accurate, and personalized answers. * Cutting-Edge Tech Stack: * `LLMs` for natural language reasoning * `LangChain` for orchestration and tool integration * `Hugging Face` embeddings for semantic search and vector retrieval * `ChromaDB` as the vector database. * `React.js` for an intuitive user interface, ensuring easy access to the system’s features and functionality. * `FastApi` : for a fast, reliable, and scalable backend to handle API requests efficiently. * Database * All documents used to ensure accuracy come from reliable sources, such as Govermental website, and trused sources for dataset ( back to top ) ### Built With * [![React.js][React.js]][React-url] * [![LangChain][LangChain]][LangChain-url] * [![HuggingFace][HuggingFace]][HuggingFace-url] * [![ChromaDB][ChromaDB]][ChromaDB-url] * [![FastAPI][FastAPI]][FastAPI-url] * [![Ollama][Ollama]][Ollama-url] ( back to top ) ## Getting …