This n8n workflow automates the process of finding airport lounges using a combination of webhooks, natural language processing (NLP), vector similarity search, and Google Sheets logging. It is designed for airports, travel agencies, or travelers seeking quick access to lounge information.
The workflow begins with a POST webhook endpoint where user queries or requests are received. These inputs are then split into manageable chunks using a text splitter node, which prepares the data for embedding and semantic search. The embeddings are generated via Cohere’s API and stored in a Redis vector database for fast similarity retrieval.
When a user inquiry is received, the workflow queries the Redis vector store to find the most relevant lounge information based on the semantic vector, ensuring accurate and context-aware responses. The retrieved data is processed through a language model (like Hugging Face’s models) to generate natural language responses for the user.
An agent node defines the task and directs outputs to a Google Sheets log, recording each exchange or search event for further analysis or tracking. This setup makes it ideal for creating an intelligent, scalable airport lounge finder integrated with real-time database and NLP capabilities.
Practically, this workflow serves airports or travel apps, enabling easy, automated access to lounge information based on user queries, improving traveler experience and operational efficiency.
Reviews
There are no reviews yet.