This n8n workflow automates the extraction, processing, and indexing of tour package information from PDF files stored in Google Drive. Triggered manually, it scans a designated folder on Google Drive for PDFs, downloads each file, extracts relevant content from each tour package PDF, and converts this data into vector embeddings using OpenAI’s API. These embeddings are then stored in a Pinecone vector database, facilitating efficient search and retrieval. The workflow is ideal for travel agencies or tour operators wanting to create a searchable database of tour packages from their PDF documents, enabling quick customer querying or internal data analysis.

Node Count	6 – 10 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOpenAi, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStorePinecone, googleDrive, manualTrigger, splitInBatches, stickyNote