Your AI Travel Companion Powered by Gemini and MongoDB Atlas
detail.loadingPreview
Unlock effortless travel planning with our AI Travel Assistant. Leveraging the power of Google Gemini and MongoDB Atlas, this workflow provides intelligent recommendations and remembers your preferences for a personalized trip.
About This Workflow
The AI Travel Assistant is an intelligent workflow designed to revolutionize how you plan your trips. It utilizes the cutting-edge capabilities of Google Gemini for natural language understanding and response generation, paired with the robust data management and vector search features of MongoDB Atlas. This powerful combination allows the assistant to not only understand your travel queries but also to remember past conversations, providing a truly personalized experience. Furthermore, it taps into a curated database of points of interest, ensuring you receive relevant and up-to-date suggestions for your adventures. The integration with OpenAI embeddings further enhances the accuracy and richness of the data used for recommendations.
Key Features
- Intelligent Conversation: Understands your travel needs and preferences through natural language.
- Persistent Memory: Remembers past interactions, offering personalized recommendations over time.
- Rich Point of Interest Database: Accesses up-to-date travel recommendations powered by MongoDB Atlas vector search.
- Seamless Integration: Connects with your existing Google and OpenAI accounts for powerful AI capabilities.
- Customizable Data Ingestion: Easily add and update points of interest to tailor the AI's knowledge base.
How To Use
- Set up Credentials: Configure your Google API credentials for the Gemini LLM and your OpenAI API credentials for embeddings.
- MongoDB Atlas Setup: Create a MongoDB Atlas project and cluster. Obtain your connection string and ensure IP Access List is configured (consider
0.0.0.0/0for easy testing). - MongoDB Credentials: Set up your MongoDB account in n8n with the correct connection string and database name.
- Vector Search Configuration: Create a vector search index named
vector_indexon yourpoints_of_interestcollection in MongoDB Atlas. EnsurenumDimensionsmatches your chosen embedding model (e.g., 1536 for OpenAI). - Ingest Data: Use the
/ingestDatawebhook (POST request) to send new points of interest. The workflow will process and embed this data into your MongoDB Atlas. - Interact with the Agent: Once data is populated, start a chat by sending a message to the "When chat message received" trigger. Ask questions like, "What are some historical sites in Rome?"
Apps Used
Workflow JSON
{
"id": "17995a73-3805-4ce0-b064-3fb1ee6b1764",
"name": "Your AI Travel Companion Powered by Gemini and MongoDB Atlas",
"nodes": 8,
"category": "Marketing",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 17995a73-3805...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
AI-Powered Instagram Comment Automation
This n8n workflow intelligently automates responses to Instagram comments, leveraging advanced AI to engage with your audience. It filters out irrelevant content and personalizes replies, saving you time while boosting your social media presence.
AI-Powered On-Page SEO Audit & Report Automation
Instantly generate comprehensive on-page SEO technical and content audits for any website URL. This AI-powered workflow automates the entire process, from scraping the page to delivering a detailed report directly to your inbox, empowering you to optimize for better search rankings and user engagement.
Automate LinkedIn Content Promotion for Your Ghost Blog with AI
Effortlessly promote your latest Ghost blog posts on LinkedIn. This workflow leverages AI to generate engaging, professional LinkedIn messages based on your article content and saves them, along with article metadata, directly to a Google Sheet.