Google Drive and OpenRouter Chat Model integration

This workflow automates the process of analyzing emails and their attachments (PDFs and images) using AI models (DeepSeek, Gemini, and OpenRouter). It extracts and summarizes the content of emails and attachments, saves the summaries to Google Sheets, and sends a final consolidated summary via Telegram. This is a powerful tool for automating email analysis and summarization, saving time and ensuring that important information is easily accessible and actionable. Below is a breakdown of the workflow: How It Works The workflow is designed to process incoming emails, analyze their content and attachments, and generate summaries. Here's how it works: Email Trigger: The workflow starts with the Email Trigger (IMAP) node, which monitors an email inbox for new emails. If an email contains attachments, the workflow processes them. Check for Attachments: The Contain Attachments? node checks if the email has attachments. If attachments are present, the workflow proceeds to process them. Process Attachments: The Get PDF and Images Attachments node extracts PDF and image attachments from the email. The Switch node separates PDFs and images for further processing: PDFs: The Extract from PDF node extracts text from PDFs, and the PDF Analyzer node summarizes the content. Images: The Analyze Image node uses AI to describe the content of images. Summarize Email Content: The Convert Text node converts the email's HTML content to plain text. The Email Summarization Chain node uses AI to generate a summary of the email's text content. Save Summaries: The Save Summary PDF, Save Summary Image, and Save Summary Text nodes save the summaries of PDFs, images, and email text, respectively, to Google Sheets. Consolidate Summaries: The All Summaries node aggregates the summaries of the email text, PDFs, and images. The Create Final Summary node uses AI to generate a unified summary of all the content. Send Final Summary: The Send Final Summary node sends the consolidated summary via Telegram to a specified chat ID. Set Up Steps To set up and use this workflow in n8n, follow these steps: IMAP Configuration: Set up IMAP credentials in n8n for the Email Trigger (IMAP) node. Ensure the email account is accessible via IMAP. AI Model Configuration: Configure the DeepSeek, Gemini, and OpenRouter credentials in n8n for the Email Summarization Chain, PDF Analyzer, and Create Final Summary nodes. Ensure the AI models are set up to generate summaries. Google Sheets Integration: Set up Google Sheets credentials in n8n for the Save Summary PDF, Save Summary Image, and Save Summary Text nodes. Specify the Google Sheet and worksheet where the summaries will be saved. Telegram Integration: Set up Telegram credentials in n8n for the Send Final Summary node. Insert your Chat ID in the Telegram node to receive the final summary. Test the Workflow: Send an email with attachments (PDFs and images) to the monitored email account. The workflow will: Extract and summarize the email content and attachments. Save the summaries to Google Sheets. Send a consolidated summary via Telegram. Optional Customization: replace IMAP trigger with Gmail or Outlook trigger Modify the workflow to include additional features, such as: Adding more AI models for different types of analysis. Sending notifications via other channels (e.g., Slack, email). Integrating with other storage services (e.g., Dropbox, AWS S3).

This n8n template empowers IT support teams by automating document ingestion and instant query resolution through a conversational AI. It integrates Google Drive, Pinecone, and a Chat AI agent (using Google Gemini/OpenRouter) to transform static support documents into an interactive, searchable knowledge base. With two interlinked workflows—one for processing support documents and one for handling chat queries—employees receive fast, context-aware answers directly from your support documentation. Overview Document Ingestion Workflow Google Drive Trigger:** Monitors a specified folder for new file uploads (e.g., updated support documents). File Download & Extraction:** Automatically downloads new files and extracts text content. Data Cleaning & Text Splitting:** Utilizes a Code node to remove line breaks, trim extra spaces, and strip special characters, while a text splitter segments the content into manageable chunks. Embedding & Storage:** Generates text embeddings using Google Gemini and stores them in a Pinecone vector store for rapid similarity search. Chat Query Workflow Chat Trigger:** Initiates when an employee sends a support query. Vector Search & Context Retrieval:** Retrieves the top relevant document segments from Pinecone based on similarity scores. Prompt Construction:** A Code node combines the retrieved document snippets with the user’s query into a detailed prompt. AI Agent Response:** The constructed prompt is sent to an AI agent (using OpenRouter Chat Model) to generate a clear, step-by-step solution. Key Benefits & Use Case Imagine a large organization where every IT support document—from troubleshooting guides to system configurations—is stored in a single Google Drive folder. When an employee encounters an issue (e.g., “How do I reset my VPN credentials?”), they simply type the query into a chat interface. Instantly, the workflow retrieves the most relevant context from the ingested documents and provides a detailed, actionable answer. This process reduces resolution times, enhances support consistency, and significantly lightens the load on IT staff. Prerequisites A valid Google Drive account with access to the designated folder. A Pinecone account for storing and retrieving text embeddings. Google Gemini* (or OpenRouter*) credentials to power the Chat AI agent. An operational n8n instance configured with the necessary nodes and credentials. Workflow Details 1 Document Ingestion Workflow Google Drive Trigger Node:** Listens for file creation events in the specified folder. Google Drive Download Node:** Downloads the newly added file. Extract from File Node:** Extracts text content from the downloaded file. Code Node (Data Cleaning):** Cleans the extracted text by removing line breaks, trimming spaces, and eliminating special characters. Recursive Text Splitter Node:** Segments the cleaned text into manageable chunks. Pinecone Vector Store Node:** Generates embeddings (via Google Gemini) and uploads the chunks to Pinecone. 2 Chat Query Workflow Chat Trigger Node:** Receives incoming user queries. Pinecone Vector Store Node (Query):** Searches for relevant document chunks based on the query. Code Node (Context Builder):** Sorts the retrieved documents by relevance and constructs a prompt merging the context with the query. AI Agent Node:** Sends the prompt to the Chat AI agent, which returns a detailed answer. How to Use Import the Template: Import the template into your n8n instance. Configure the Google Drive Trigger: Set the folder ID (e.g., 1RQvAHIw8cQbtwI9ZvdVV0k0x6TM6H12P) and connect your Google Drive credentials. Set Up Pinecone Nodes: Enter your Pinecone index details and credentials. Configure the Chat AI Agent: Provide your Google Gemini (or OpenRouter) API credentials. Test the Workflows: Validate the document ingestion workflow by uploading a sample support document. Validate the chat query workflow by sending a test query and verifying the returned support information. Additional Notes Ensure all credentials (Google Drive, Pinecone, and Chat AI) are correctly set up and tested before deploying the workflows in production. The template is fully customizable. Adjust the text cleaning, splitting parameters, or the number of document chunks retrieved based on your support documentation's size and structure. This template not only enhances IT support efficiency but also offers a scalable solution for managing and leveraging growing volumes of support content.