TSARA IA

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. License
5. Contact

Tsara.IA: Intelligent Tourism Assistant for Morocco

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

• 
• 
• 
• 
• 
• 

(back to top)

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Prerequisites

This is an example of how to list things you need to use the software and how to install them.

• npm

  npm install npm@latest -g

Installation

Follow the steps below to set up the project locally:

Prerequisites

Make sure you have the following installed:

• Node.js (>= 18.x)
• npm or yarn
• Python (>= 3.12)
• pip (Python package manager)
• uv (Project manager)

Clone the repository

git clone https://github.com/ourahma/TsaraIA.git
cd TsaraIA

Backend Setup

1. Navigate to the backend folder:

   cd backend

2. (Optional) Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate   # On Linux/Mac
   venv\Scripts\activate      # On Windows

3. Install dependencies:

   pip install -r requirements.txt

4. Set up Ollama

   • Install Ollama on your machine if not already installed.
   • Ensure you have pulled and set up an LLM that supports tool usage.
     In this project, we use mistral:7b as the default model:

     ollama pull mistral:7b

   • You can replace it with another model of your choice, but make sure it supports function calling / tool integration.

5. Run the backend server:

   uvicorn main:app --reload

   The backend will be available at: http://localhost:8000

Frontend Setup

1. Navigate to the frontend folder:

   cd frontend

2. Install dependencies:

   npm install

   or

   yarn install

3. Start the development server:

   npm run dev

   or

   yarn dev

   The frontend will be available at: http://localhost:5173 (default for Vite).

---

Now both backend and frontend should be running locally and connected.

Usage

You can now access the frontend directly from your browser and interact with the chatbot’s user-friendly interface to ask questions and receive accurate, real-time answers.

Ask about touristic guides :

• Send the Chatbot your question :

• Receive detailed answers with information about the phone number,website, adresses ... :

Ask about receipies :

* Send the Chatbot your question :

• Receive detailed answers with information about the phone number,website, adresses ... :

(back to top)

License

See LICENSE.txt for more information.

(back to top)

Contact

OURAHMA Maroua - @Website - [email protected]

Project Link: https://github.com/ourahma/TsaraIA

(back to top)