🕵🏻 Building an AI-Powered Travel Itinerary Assistant using OpenAI Agents SDK and Dappier

You can also check this cookbook in colab here

Introduction

This notebook provides a step-by-step guide to building an AI-powered travel assistant using OpenAI’s Agents SDK and Dappier. The assistant generates a real-time travel itinerary based on user input, fetching weather updates, live events, and hotel deals dynamically.

Watch the Video Guide

If you prefer a visual walkthrough, check out the accompanying video guide below:

OpenAI Agents SDK

The OpenAI Agents SDK enables you to build agentic AI applications with a lightweight and production-ready API. It consists of:

Agents – LLMs equipped with instructions and tools
Handoffs – Delegation of tasks to specialized agents
Guardrails – Input validation for enhanced reliability

The SDK also provides built-in tracing for debugging and evaluation, making AI-powered workflows easy to build and scale.

Dappier

Dappier is a real-time AI data platform that connects LLMs and AI agents to rights-cleared data from trusted sources. It specializes in web search, finance, news, and live events, ensuring AI applications can access up-to-date and verified information without hallucinations.

Install Dependencies

!pip install openai-agents dappier colorama nest-asyncio

Import Required Libraries

Python

import os
import getpass
import nest_asyncio
import asyncio
from agents import Agent, FunctionTool, Runner, function_tool
from colorama import Fore, Style
from dappier import Dappier
from openai.types.responses import ResponseTextDeltaEvent

Set Up API Keys Securely

To prevent exposing API keys in shared environments, use getpass to enter them securely.

Python

os.environ["DAPPIER_API_KEY"] = getpass.getpass("Enter your Dappier API Key: ")
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API Key: ")

Initialize Dappier Client:

Python

dappier_client = Dappier(api_key=os.environ["DAPPIER_API_KEY"])

Enable tracing for OpenAI Agents SDK:

Python

from agents import set_tracing_export_api_key

set_tracing_export_api_key(os.environ["OPENAI_API_KEY"])

Define AI Functions for Real-Time Data Fetching

Fetching Real-Time Search Results

This function fetches real-time search results from Dappier based on the user’s query.

Python

# Define Real-Time Search Function
@function_tool
def dappier_real_time_search(query: str, ai_model_id: str) -> str:
    """Fetches real-time search results from Dappier based on the user's query.

    Args:
        query (str): The user's query for real-time data.
        ai_model_id (str): The AI model ID to use for the query, dynamically set by the agent.
            Possible values:
            - "am_01j0rzq4tvfscrgzwac7jv1p4c" (General real-time web search, including news, weather, and events.)
            - "am_01j749h8pbf7ns8r1bq9s2evrh" (Stock market data with real-time financial news and stock prices.)

    Returns:
        str: A response message containing the real-time data results.
    """
    print(Fore.RED + f"CALLING TOOL - dappier_real_time_search: {ai_model_id}\n" + Style.RESET_ALL)
    print(Fore.GREEN + f"Query: {query}\n" + Style.RESET_ALL)
    response = dappier_client.search_real_time_data(query=query, ai_model_id=ai_model_id)
    return response.message if response else "No real-time data found."

Fetching AI-Powered Recommendations

This function fetches AI-powered content recommendations from Dappier based on the user’s query

Python

# Define AI Recommendations Function
@function_tool
def dappier_ai_recommendations(query: str, data_model_id: str) -> str:
    """Fetches AI-powered content recommendations from Dappier based on the user's query.

    Args:
        query (str): The user's query for recommendations.
        data_model_id (str): The Data Model ID to use for the query, dynamically set by the agent.
            Possible values:
            - "dm_01j0pb465keqmatq9k83dthx34" (Sports news)
            - "dm_01j0q82s4bfjmsqkhs3ywm3x6y" (Lifestyle news)
            - "dm_01j1sz8t3qe6v9g8ad102kvmqn" (Dog care advice from iHeartDogs)
            - "dm_01j1sza0h7ekhaecys2p3y0vmj" (Cat care advice from iHeartCats)
            - "dm_01j5xy9w5sf49bm6b1prm80m27" (Eco-friendly content from GreenMonster)
            - "dm_01jagy9nqaeer9hxx8z1sk1jx6" (General news from WISH-TV)
            - "dm_01jhtt138wf1b9j8jwswye99y5" (Local news from 9 and 10 News)

    Returns:
        str: A formatted response containing AI-powered recommendations.
    """
    print(Fore.RED + f"CALLING TOOL: dappier_ai_recommendations: {data_model_id}\n" + Style.RESET_ALL)
    print(Fore.GREEN + f"Query: {query}\n" + Style.RESET_ALL)
    response = dappier_client.get_ai_recommendations(query=query, data_model_id=data_model_id, similarity_top_k=5)
    results = response.response.results
    formatted_text = ""
    for result in results:
        formatted_text += (f"Title: {result.title}\n"
                           f"Author: {result.author}\n"
                           f"Published on: {result.pubdate}\n"
                           f"URL: {result.source_url}\n"
                           f"Image URL: {result.image_url}\n"
                           f"Summary: {result.summary}\n\n")
    return formatted_text or "No recommendations found."

Create AI Agent

This AI agent will determine whether to fetch real-time search results or AI recommendations based on the user’s query.

Python

agent = Agent(
    name="Dappier Assistant",
    instructions="""
    You analyze the user's query and determine whether to use real-time search or AI recommendations.
    If the query involves stocks, finance, or current events, use `dappier_real_time_search`.
    If the query is about recommendations (e.g., news, lifestyle, sports, pets), use `dappier_ai_recommendations`.
    You MUST provide `ai_model_id` or `data_model_id` as necessary.
    Format responses in structured Markdown.
    """,
    tools=[dappier_real_time_search, dappier_ai_recommendations],
)

Generate Task Prompt

A function to dynamically generate a task prompt based on the user’s travel details.

Python

def generate_task_prompt(travel_city: str, travel_date: str, num_days: str) -> str:
    return f"""Generate a {num_days}-day travel itinerary for {travel_city}, tailored to the real-time weather forecast for the selected date: {travel_date}. Follow these steps:

        Determine Current Date and Travel Period:
        Use Dappier's real-time search to identify the current date and calculate the trip duration based on user input.

        Fetch LifeStyle News:
        Retrieve LifeStyle news using Dappier AI Recommendations API for the given date and provide insight to the user.

        Fetch Weather Data:
        Retrieve the weather forecast for {travel_city} during the selected dates to understand the conditions for each day.

        Fetch Live Events Data:
        Use Dappier's real-time search to find live events happening in {travel_city} during the trip dates.

        Fetch Hotel Deals Data:
        Use Dappier's real-time search to find the best hotel deals with booking links in {travel_city} during the trip dates.

        Design the Itinerary:
        Use the weather insights, live events, hotel deals to plan activities and destinations that suit the expected conditions. For each suggested location:

        Output:
        Present latest life style news at first then. Present a detailed {num_days}-day itinerary, including timing, activities, booking links, weather information for each day and travel considerations. Ensure the plan is optimized for convenience and enjoyment.
    """

Get User Input and Run AI Agent

This function collects user input dynamically, generates the task prompt, and executes the AI agent asynchronously.

Python

async def main():
    """Asks user for travel details dynamically and executes AI agent"""

    # Ask for travel details dynamically
    travel_city = input("Enter the city you want to travel to: ")
    travel_date = input("Enter the start date of your travel (YYYY-MM-DD): ")
    num_days = input("Enter the number of days for your trip: ")

    # Generate task prompt
    task_prompt = generate_task_prompt(travel_city, travel_date, num_days)

    print(Fore.BLUE + f"\nExecuting AI Agent with prompt:\n{task_prompt}" + Style.RESET_ALL)

    # Execute AI agent with streaming results
    result = Runner.run_streamed(agent, task_prompt)

    print("\n\n=== Streaming Start ===\n\n")

    async for event in result.stream_events():
        if event.type == "raw_response_event" and isinstance(event.data, ResponseTextDeltaEvent):
            print(event.data.delta, end="", flush=True)

    print("\n\n=== Streaming Complete ===")

# Execute main function
asyncio.run(main())

Enter the city you want to travel to: Paris
Enter the start date of your travel: 01, April 2025
Enter the number of days for your trip: 5

ORIGINAL PROMPT: Generate a 5-day travel itinerary for Paris, tailored to the real-time weather forecast for the selected date: 01, April 2025. Follow these steps:

Determine Current Date and Travel Period:
Use Dappier's real-time search to identify the current date and calculate the trip duration based on user input.

Fetch LifeStyle News:
Retrieve LifeStyle news using Dappier AI Recommendations API for the given date and provide insight to the user.

Fetch Weather Data:
Retrieve the weather forecast for Paris during the selected dates to understand the conditions for each day.

Fetch Live Events Data:
Use Dappier's real-time search to find live events happening in Paris during the trip dates.

Fetch Hotel Deals Data:
Use Dappier's real-time search to find the best hotel deals with booking links in Paris during the trip dates.

Design the Itinerary:
Use the weather insights, live events, hotel deals to plan activities and destinations that suit the expected conditions. For each suggested location:

Output:
Present latest life style news at first then. Present a detailed 5-day itinerary, including timing, activities, booking links, weather information for each day and travel considerations. Ensure the plan is optimized for convenience and enjoyment.



=== Streaming Start ===


CALLING TOOL - dappier_real_time_search: am_01j0rzq4tvfscrgzwac7jv1p4c

Query: current date

CALLING TOOL: dappier_ai_recommendations: dm_01j0q82s4bfjmsqkhs3ywm3x6y

Query: Paris lifestyle news

CALLING TOOL - dappier_real_time_search: am_01j0rzq4tvfscrgzwac7jv1p4c

Query: Paris weather April 1-5, 2025

CALLING TOOL - dappier_real_time_search: am_01j0rzq4tvfscrgzwac7jv1p4c

Query: Paris live events April 1-5, 2025

CALLING TOOL - dappier_real_time_search: am_01j0rzq4tvfscrgzwac7jv1p4c

Query: Paris hotel deals April 1-5, 2025

### Latest Lifestyle News Highlights

#### Justin Bieber's Heartfelt Message
- **Title:** Christian Singer Justin Bieber, 31, Issues Heartbreaking Message To Fans Amidst Concerns For His Wellbeing
- **Summary:** Justin Bieber addresses mental health struggles in a candid message to fans, sharing feelings of inadequacy despite his fame.
- **Link:** [Read more](https://www.themix.net/celebrity/celebrity-news/christian-singer-justin-bieber-31-issues-heartbreaking-message-to-fans-amidst-concerns-for-his-wellbeing/)

#### Controversies in Disney's Live-Action Snow White
- **Title:** Live-Action Snow White Continues to Have Issues as Disney Scales Back Premiere
- **Summary:** Disney's adaptation faces hurdles and mixed reactions due to casting choices and character portrayal.
- **Link:** [Read more](https://www.themix.net/movies/movie-news/live-action-snow-white-continues-to-have-issues-as-disney-scales-back-premiere/)

#### Family-Favorite Baked Ziti Recipe
- **Title:** Family-Favorite Baked Ziti: Simple, Satisfying, and Oh-So-Good
- **Summary:** Discover a delicious and easy-to-make baked ziti recipe that's perfect for family gatherings.
- **Link:** [Read more](https://www.familyproof.com/lifestyle/food-drink/baked-ziti/)

### 5-Day Paris Travel Itinerary (April 1-5, 2025)

#### Weather Overview
- **April 1-5:** Mild temperatures (12-14°C / 54-57°F), partly cloudy. Ideal for outdoor activities and exploration.

#### Day 1: Explore Paris and Join the Marathon
- **Morning:** Breakfast at Café de Flore. Explore Saint-Germain-des-Prés.
- **Afternoon:** Participate or watch the Paris Marathon. Visit Eiffel Tower post-event.
- **Evening:** Dinner at Le Jules Verne with Eiffel Tower views.

#### Day 2: Art and Design Immersion
- **Morning:** Visit Pad Paris - Art + Design Fair.
- **Afternoon:** Explore the Art Paris Art Fair at Grand Palais.
- **Evening:** Candlelight concert at Sainte-Chapelle. Book [here](https://linkparis.com).

#### Day 3: Cultural Experiences
- **Morning:** Tour the Louvre Museum. Don’t miss the Mona Lisa and other major works.
- **Afternoon:** Lunch at Angelina’s. Discover Musée d'Orsay's art.
- **Evening:** Dinner at a local bistro in Montmartre.

#### Day 4: Scenic Views and Relaxation
- **Morning:** Visit Palais Garnier and take a guided tour.
- **Afternoon:** Enjoy a Seine River Cruise with lunch.
- **Evening:** Explore Le Marais district. Dinner at Chez Janou.

#### Day 5: Quirky Fun and Departure
- **Morning:** Participate in International Pillow Fight Day.
- **Afternoon:** Last-minute shopping at Galeries Lafayette.
- **Evening:** Departure preparation. Stay at Mercari Hotel ([Booking Link](https://www.mercari.com/us/item/m11634459421/)).

### Hotel Deals
- **Stay Option:** 5-Day, 4-Night Package at $1,750 from [LinkParis](https://linkparis.com/5-day-trip-to-paris/).
- **Alternative Stay:** Hotel rooms starting at $120 through [Mercari](https://www.mercari.com/us/item/m11634459421/).

Experience a mix of culture, relaxation, and excitement in Paris. Enjoy your trip! 🇫🇷✨

=== Streaming Complete ===

Conclusion

This notebook provides a structured guide to building an AI-powered travel itinerary assistant using OpenAI Agents SDK and Dappier. It covers:

Secure API key storage using getpass
Real-time data retrieval for weather, events, and hotels
AI-powered recommendations for lifestyle insights
An agent-driven workflow to generate structured travel plans

This AI assistant can be extended further by integrating flight search APIs, restaurant recommendations, and personalized travel preferences.

General

Activepieces

Agent.ai

AgentStack

Bolt

CAMEL

Clawhub

Dappier MCP Server

Google ADK

LangChain

LlamaIndex

MCP Use

OpenAI Agents

OpenAI Agents MCP

OpenAI Function Calling

OpenAI GPT

Replit

Zapier

🕵🏻 Building an AI-Powered Travel Itinerary Assistant using OpenAI Agents SDK and Dappier

Introduction

Watch the Video Guide

OpenAI Agents SDK

Dappier

Install Dependencies

Import Required Libraries

Set Up API Keys Securely

Define AI Functions for Real-Time Data Fetching

Fetching Real-Time Search Results

Fetching AI-Powered Recommendations

Create AI Agent

Generate Task Prompt

Get User Input and Run AI Agent

Conclusion

General

Activepieces

Agent.ai

AgentStack

Bolt

CAMEL

Clawhub

Dappier MCP Server

Google ADK

LangChain

LlamaIndex

MCP Use

OpenAI Agents

OpenAI Agents MCP

OpenAI Function Calling

OpenAI GPT

Replit

Zapier

​Introduction

​Watch the Video Guide

​OpenAI Agents SDK

​Dappier

​Install Dependencies

​Import Required Libraries

​Set Up API Keys Securely

​Define AI Functions for Real-Time Data Fetching

​Fetching Real-Time Search Results

​Fetching AI-Powered Recommendations

​Create AI Agent

​Generate Task Prompt

​Get User Input and Run AI Agent

​Conclusion

Introduction

Watch the Video Guide

OpenAI Agents SDK

Dappier

Install Dependencies

Import Required Libraries

Set Up API Keys Securely

Define AI Functions for Real-Time Data Fetching

Fetching Real-Time Search Results

Fetching AI-Powered Recommendations

Create AI Agent

Generate Task Prompt

Get User Input and Run AI Agent

Conclusion