This comprehensive n8n workflow automates the process of monitoring Google Drive for new PDF files, extracting and normalizing their content, and storing the data in a Pinecone vector database. When a user submits a query via a webhook, the system retrieves relevant documents based on semantic embeddings generated through Google Gemini, and constructs a context-aware response using an AI agent powered by OpenRouter’s language model. This setup enables efficient document ingestion, semantic search, and intelligent question-answering, making it ideal for scenarios like knowledge base management, document review, and customer support automation.

Node Count	11 – 20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsGoogleGemini, @n8n/n8n-nodes-langchain.lmChatOpenRouter, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStorePinecone, code, extractFromFile, googleDrive, googleDriveTrigger