Agentic AI-Powered Travel Planner

-

 Presenting by Madhan Kumar S

  


Introduction

The Agentic AI MCP Tour Planner is an end-to-end, AI-powered travel planning application. It leverages advanced agentic workflows, Retrieval Augmented Generation (RAG), and multi-tool orchestration to deliver highly personalized travel recommendations and accommodation options. The project is designed with modularity and scalability in mind, using modern Python frameworks and containerization for ease of deployment.

 Technologies Used

  • LangGraph: Agentic workflow orchestration
  • LangChain: LLM and tool integration
  • Streamlit: Frontend UI
  • FastAPI: Backend API
  • FAISS: Vector search for RAG
  • Tavily: Internet search tool
  • MCP Tool: Accommodation search
  • Ollama/Groq: LLM inference
  • Docker: Containerization

 Flow Chart


 LangGraph state flow

 Key Features

  • Agentic AI Flow: Utilizes LangGraph to manage complex, multi-step reasoning and tool invocation, enabling the agent to plan and adapt dynamically.
  • Retrieval Augmented Generation (RAG): Integrates FAISS for vector search and custom RAG pipelines, ensuring context-rich and up-to-date responses.
  • Multi-Tool Orchestration: Combines local RAG tools, internet search (Tavily), and accommodation search (MCP/Airbnb tool) for comprehensive planning.
  • Modern Frontend: Built with Streamlit for an interactive and user-friendly experience.
  • FastAPI Backend: Provides a robust API layer for agent orchestration and tool management.
  • LLM Flexibility: Supports both local (Ollama) and cloud (Groq) Large Language Models (LLMs).
  • Logging & Tracing: Integrated logging and LangSmith tracing for debugging and observability.
  • Containerization: Uses Docker for consistent and reproducible deployments.

 

How It Works

  1. User Input:
    Users interact with the Streamlit frontend, specifying their destination, preferences (e.g., beaches, adventure), number of guests, and travel dates.
  2. Agentic Flow:
    The backend agent, orchestrated by LangGraph, determines which tools to invoke:
    • RAG Tools: Retrieve relevant travel information from vector stores.
    • Tavily Search: Fetches up-to-date web results for the latest travel info.
    • MCP/Airbnb Tool: Finds accommodation options matching user criteria.
  3. LLM Reasoning:
    The agent synthesizes all results using an LLM, generating a comprehensive travel plan and recommendations.
  4. Response:
    The frontend displays the AI-generated itinerary, including places to visit, accommodation details, prices, and facilities.

 

Project Structure

Agentic-AI-MCP-Tour-Planner/

│

├── backend/

│   ├── app/

│   │   ├── api/                # API endpoints (FastAPI)

│   │   ├── configs/            # Configuration files

│   │   ├── core/               # Core agent logic and services

│   │   ├── resource/           # Data and static resources

│   │   ├── utils/              # Utility modules (RAG, LLM, etc.)

│   │   ├── main.py             # Backend entry point

│   │   └── ...                 

│   ├── Dockerfile              # Backend Dockerfile

│   └── ...

│

├── frontend/

│   ├── app.py                  # Streamlit frontend

│   ├── Dockerfile              # Frontend Dockerfile

│   └── ...

│

├── docker-compose.yml          # Orchestration for multi-container setup

└── README.md                   # Project documentation

 

Backend Details

  • Agentic Workflow:
    The backend uses LangGraph to define a directed graph of agent states and transitions. Each node can invoke tools (e.g., RAG, accommodation search) and pass results to the next stage.
  • RAG Implementation:
    Custom tools in app/utils/local_tools.py handle retrieval from vector stores and synthesis using LLMs.
  • Accommodation Search:
    Integrates with MCP/Airbnb APIs to fetch real-time accommodation data.
  • API Layer:
    FastAPI exposes endpoints for frontend-backend communication.

 

Frontend Details

  • Streamlit UI:
    The frontend, built with Streamlit, provides an intuitive interface for users to input their travel preferences and view AI-generated plans.
  • Dockerized Deployment:
    The Dockerfile ensures all dependencies are installed and the app runs reliably in any environment.

Conclusion

The Agentic AI MCP Tour Planner demonstrates the power of combining agentic workflows, RAG, and multi-tool orchestration for real-world applications. Its modular design, modern tech stack, and containerized deployment make it a robust solution for intelligent travel planning.

 

 


Comments

Post a Comment

Popular posts from this blog

Detecting stranger through CCTV camera and alerting the owner

-
Image
Presenting by Madhan Kumar Selvaraj In this blog, we are going to see some interesting stuff related to detection. Globally there are around 25 million CCTV cameras in the house. Sadly, for every 3 minutes robbery, theft and burglary are happening. Real-world issue Even though we have access to live streaming CCTV video footage through the internet. But most of the time we failed to check the video footage at the time of the robbery. So, there is a need for a smart alert system. One-liner of the project Detecting the human subject other than the family members through the CCTV footage and alerting the house owner through the mail. Technologies used here OpenCV computer vision Facenet CNN model MTCNN (Multi-task Cascaded Convolutional Neural Networks) Support Vector Machine algorithm Matplotlib library The workflow of the project Focusing only on the human subject in the CCTV footage other than animals, birds, etc Take a screenshot of the video once we ...
Read more

Artificial Intelligent Chatbot

-
Image
Presenting by Madhan Kumar Selvaraj Globally 30% of the customer service is handling by the Chatbot. Its market size is projected to grow from $2.6 billion in 2019 to $9.4 billion by 2024. Many of the people have a thought that machines will grab their job. But the reality is that the machine assist humans to do the complicated woks in a easy manner. What this blog is about? This blog helps you to create an Artificial intelligent Chatbot by deploying it in the Python Flask web framework and the Heroku cloud platform. Here I am doing this chatbot to assist a coaching institute to respond to the students regarding the course details and also it can answer questions apart from the course. Everyone knows about Google assistant, Apple's Siri, Microsoft's Cortona, Amazon's Alexa. Our Chatbot also works like the same and it is having limitation because we are using limited pattern and response. If we add more pattern and response, it can response to all our queries. Chatbot A c...
Read more

Whatsapp chat book

-
Image
 Presenting by Madhan Kumar Selvaraj More than 2 billion people are using the Whats-app application as per the report . It replaced all of our chatting applications and most of our formal, as well as informal chats, are happening through the Whats-app. Those chats are between our family, friends, spouse, our loved ones. I got an idea of printing the chat in the form of a book or hard copy kind of thing to make our bond as a lifetime memory. Real-world issue One of the easiest ways to convert the chat into PDF format is by taking the long screenshot of our Whats-app chat in the application and converting it into PDF. The problem is that Whats-app deletes messages frequently in the application and we can't able to change the font type, size, color. Quality of taking the long screenshot is not that efficient to convert into the printable format and most of the applications are proprietary. Some of the websites like Zapptales are providing options to convert the exported Whats-app ch...
Read more