Embeddings Google Gemini and Google Drive integration

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.

AI-Powered Tech Radar Advisor This project is built on top of the famous open source ThoughtWorks Tech Radar. You can use this template to build your own AI-Powered Tech Radar Advisor for your company or group of companies. Target Audience This template is perfect for: Tech Audit & Governance Leaders:** Those seeking to build a tech landscape AI platform portal. Tech Leaders & Architects:** Those aiming to provide modern AI platforms that help others understand the rationale behind strategic technology adoption. Product Managers:** Professionals looking to align product innovation with the company's current tech trends. IT & Engineering Teams:** Teams that need to aggregate, analyze, and visualize technology data from multiple sources efficiently. Digital Transformation Experts:** Innovators aiming to leverage AI for actionable insights and strategic recommendations. Data Analysts & Scientists:** Individuals who want to combine structured SQL analysis with advanced semantic search using vector databases. Developers:** Those interested in integrating RAG chatbot functionality with conversation storage. Description Tech Constellation is an AI-powered Tech Radar solution designed to help organizations visualize and steer their technology adoption strategy. It seamlessly ingests data from a Tech Radar Google Sheet—converting it into both a MySQL database and a vector index—to consolidate your tech landscape in one place. The platform integrates an interactive AI chat interface powered by four specialized agents: AI Agent Router:** Analyzes and routes user queries to the most suitable processing agent. SQL Agent:** Executes precise SQL queries on structured data. RAG Agent:** Leverages semantic, vector-based search for in-depth insights. Output Guardrail Agent:** Validates responses to ensure they remain on-topic and accurate. This powerful template is perfect for technology leaders, product managers, engineering teams, and digital transformation experts looking to make data-driven decisions aligned with strategic initiatives across groups of parent-child companies. Features Data Ingestion A Google Sheet containing tech radar data is used as the primary source. The data is ingested and converted into a MySQL database. Simultaneously, the data is indexed into a vector database for semantic (vector-based) search. Interactive AI Chat Chat Integration:** An AI-powered chat interface allows users to ask questions about the tech radar. Customizable AI Agents:** AI Agent Router: Determines the query type and routes it to the appropriate agent. SQL Agent: Processes queries using SQL on structured data. RAG Agent: Performs vector-based searches on document-like data. Output Guardrail Agent: Validates queries and ensures that the responses remain on-topic and accurate. Usage Examples Tell me, is TechnologyABC adopted or on hold, and why? List all the tools that are considered part of the strategic direction for company3 but are not adopted. Project Links & Additional Details GitHub Repository (Frontend Interface Source Code):** github.com/dragonjump/techconstellation Try It:** https://scaler.my

This workflow implements a Retrieval Augmented Generation (RAG) chatbot that answers employee questions based on company documents stored in Google Drive. It automatically indexes new or updated documents in a Pinecone vector database, allowing the chatbot to provide accurate and up-to-date information. The workflow uses Google's Gemini AI for both embeddings and response generation. How it works The workflow uses two Google Drive Trigger nodes: one for detecting new files added to a specified Google Drive folder, and another for detecting file updates in that same folder. Automated Indexing: When a new or updated document is detected The Google Drive node downloads the file. The Default Data Loader node loads the document content. The Recursive Character Text Splitter node breaks the document into smaller text chunks. The Embeddings Google Gemini node generates embeddings for each text chunk using the text-embedding-004 model. The Pinecone Vector Store node indexes the text chunks and their embeddings in a specified Pinecone index. 7.The Chat Trigger node receives user questions through a chat interface. The user's question is passed to an AI Agent node. The AI Agent node uses a Vector Store Tool node, linked to a Pinecone Vector Store node in query mode, to retrieve relevant text chunks from Pinecone based on the user's question. The AI Agent sends the retrieved information and the user's question to the Google Gemini Chat Model (gemini-pro). The Google Gemini Chat Model generates a comprehensive and informative answer based on the retrieved documents. A Window Buffer Memory node connected to the AI Agent provides short-term memory, allowing for more natural and context-aware conversations. Set up steps Google Cloud Project and Vertex AI API: Create a Google Cloud project. Enable the Vertex AI API for your project. Google AI API Key: Obtain a Google AI API key from Google AI Studio. Pinecone Account: Create a free account on the Pinecone website. Obtain your API key from your Pinecone dashboard. Create an index named company-files in your Pinecone project. Google Drive: Create a dedicated folder in your Google Drive where company documents will be stored. Credentials in n8n: Configure credentials in your n8n environment for: Google Drive OAuth2 Google Gemini(PaLM) Api (using your Google AI API key) Pinecone API (using your Pinecone API key) Import the Workflow: Import this workflow into your n8n instance. Configure the Workflow: Update both Google Drive Trigger nodes to watch the specific folder you created in your Google Drive. Configure the Pinecone Vector Store nodes to use your company-files index.

Workflow based on the following article. https://www.anthropic.com/news/contextual-retrieval This n8n automation is designed to extract, process, and store content from documents into a Pinecone vector store using context-based chunking. The workflow enhances retrieval accuracy in RAG (Retrieval-Augmented Generation) setups by ensuring each chunk retains meaningful context. Workflow Breakdown: 🔹 Google Drive - Retrieve Document: The automation starts by fetching a source document from Google Drive. This document contains structured content, with predefined boundary markers for easy segmentation. 🔹 Extract Text Content - Once retrieved, the document’s text is extracted for processing. Special section boundary markers are used to divide the text into logical sections. 🔹 Code Node - Create Context-Based Chunks: A custom code node processes the extracted text, identifying section boundaries and splitting the document into meaningful chunks. Each chunk is structured to retain its context within the entire document. 🔹 Loop Node - Process Each Chunk: The workflow loops through each chunk, ensuring they are processed individually while maintaining a connection to the overall document context. 🔹 Agent Node - Generate Context for Each Chunk: We use an Agent node powered by OpenAI’s GPT-4.0-mini via OpenRouter to generate contextual metadata for each chunk, ensuring better retrieval accuracy. 🔹 Prepend Context to Chunks & Create Embeddings - The generated context is prepended to the original chunk, creating context-rich embeddings that improve searchability. 🔹 Google Gemini - Text Embeddings: The processed text is passed through Google Gemini text-embedding-004, which converts the text into semantic vector representations. 🔹 Pinecone Vector Store - Store Embeddings: The final embeddings, along with the enriched chunk content and metadata, are stored in Pinecone, making them easily retrievable for RAG-based AI applications. Use Case: This automation enhances RAG retrieval by ensuring each chunk is contextually aware of the entire document, leading to more accurate AI responses. It’s perfect for applications that require semantic search, AI-powered knowledge management, or intelligent document retrieval. By implementing context-based chunking, this workflow ensures that LLMs retrieve the most relevant data, improving response quality and accuracy in AI-driven applications.

Personal Portfolio CV Rag Chatbot - with Conversation Store and Email Summary Target Audience This template is perfect for: Individuals looking to create a working professional and interactive personal portfolio chatbot. Developers interested in integrating RAG Chatbot functionality with conversation storage. Description Create a stunning Personal Portfolio CV with integrated RAG Chatbot capabilities, including conversation storage and daily email summaries. 2.Features: Training: Setup Ingestion stage Upload your CV to Google Drive and let the Drive trigger updates to read your resume cv and convert it into your vector database (RAG purpose). Modify any parts as needed. Chat & Track: Use any frontend/backend interface to call the chat API and chat history API. Reporting Daily Chat Conversations: Receive daily automatic summaries of chat conversations. Data stored via NocoDB. 3.Setup Guide: Step-by-Step Instructions: Ensure all credentials are ready. Follow the notes provided. Ingestion: Upload your CV to Google Drive. The Drive triggers RAG update in your vector database. You can change the folder name, files and indexname of the vector database accordingly. Chat: Use any frontend/backend interface to call the chat API (refer to the notes for details) . [optional] Use any frontend/backend interface to call the update chat history API (refer to the notes for details). 3.Tracking Chat: Get daily automatic summaries of chat conversations.Format email conversations report as you like. You are ready to go!

This n8n workflow creates a financial analysis tool that generates reports on a company's quarterly earnings using the capabilities of OpenAI GPT-4o-mini, Google's Gemini AI and Pinecone's vector search. By analyzing PDFs of any company's earnings reports from their Investor Relations page, this workflow can answer complex financial questions and automatically compile findings into a structured Google Doc. How it works: Data loading and indexing Fetches links to PDF earnings document from a Google Sheet containing a list of file links. Downloads the PDFs from Google Drive. Parses the PDFs, splits the text into chunks, and generates embeddings using the Embeddings Google AI node (text-embedding-004 model). Stores the embeddings and corresponding text chunks in a Pinecone vector database for semantic search. Report generation with AI agent Utilizes an AI Agent node with a specifically crafted system prompt. The agent orchestrates the entire process. The agent uses a Vector Store Tool to access and retrieve information from the Pinecone database. Report delivery Saves the generated report as a Google Doc in a specified Google Drive location. Set up steps Google Cloud Project & Vertex AI API: Create a Google Cloud project. Enable the Vertex AI API for your project. Google AI API key: Obtain a Google AI API key from Google AI Studio. Pinecone account and API key: Create a free account on the Pinecone website. Obtain your API key from your Pinecone dashboard. Create an index named company-earnings in your Pinecone project. Google Drive - download and save financial documents: Go to a company you want to analize and download their quarterly earnings PDFs Save the PDFs in Google Drive Create a Google Sheet that stores a list of file URLs pointing to the PDFs you downloaded and saved to Google Drive Configure credentials in your n8n environment for: Google Sheets OAuth2 Google Drive OAuth2 Google Docs OAuth2 Google Gemini(PaLM) Api (using your Google AI API key) Pinecone API (using your Pinecone API key) Import and configure the workflow: Import this workflow into your n8n instance. Update the List Of Files To Load (Google Sheets) node to point to your Google Sheet. Update the Download File From Google Drive to point to the column where the file URLs are Update the Save Report to Google Docs node to point to your Google Doc where you want the report saved.