Workflow Templates

How it works Receive a chat input as an image prompt. Call OpenAI's gpt-image-1 API to generate an image. Split the returned images and process them one by one. Upload each generated image to Google Drive. Save image links and thumbnails to a Google Sheets document. Record token usage and estimated cost into a separate sheet. Set up steps Connect your OpenAI API credentials for image generation. Connect your Google Drive and Google Sheets accounts. Set the destination folder in Google Drive. Set the target Google Sheet and specify the correct sheet tabs. The setup usually takes around 5-10 minutes. Detailed field mappings are already pre-configured inside the workflow. Additional tips and instructions are included as sticky notes inside the workflow. Google Sheet copy url Copy Sheet Link

Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers who want to build an AI-powered knowledge assistant with retrieval-augmented generation (RAG) and reinforcement learning from human feedback (RLHF) via Telegram. What problem is this workflow solving? Manual knowledge management and answering support queries can be time-consuming and error-prone. This solution automates importing and indexing official documentation into MongoDB vector search and enhances AI responses with Telegram-based user feedback to continuously improve answer quality. What these workflows do Workflow 1: Document ingestion & indexing Manually triggered workflow imports product documentation from Google Docs. Documents are split into manageable chunks and embedded using OpenAI embeddings. Embedded document chunks are stored in MongoDB Atlas vector store to enable semantic search. Workflow 2: Telegram chat with RLHF feedback loop Listens for user messages via Telegram bot integration. Uses vector similarity search on MongoDB to retrieve relevant documentation chunks. Generates answers with OpenAI GPT-4o-mini model using retrieval-augmented generation. Sends answers back via Telegram and waits for user feedback (approval or disapproval). Captures feedback, maps it as positive or negative, and stores it with the conversation data for future model improvement. Setup Setting up vector embeddings Authenticate Google Docs and connect your Google Docs URL containing the product documentation you want to index. Authenticate MongoDB Atlas and connect the collection where you want to store the vector embeddings. Create a search index on this collection to support vector similarity queries. Ensure the index name matches the one configured in n8n (data_index). See the example MongoDB search index template below for reference. Setting up chat with Telegram RLHF Create a bot in Telegram with @botFather using the /newbot command. Connect the MongoDB database and search index used for vector search in the previous workflow. Also create two new collections in MongoDB Atlas: one for feedback and one for chat history. Create a search index for feedback, copying the provided template. Configure the AI system prompt in the “Knowledge Base Agent” node, making sure it references all three tools connected (productDocs, feedbackPositive, feedbackNegative) as provided in the template prompt. Make sure Product documentation and feedback collections must connect to the same MongoDB database. There are three distinct MongoDB collections: one for product documentation, one for feedback, and one for chat history (chat history collection can be separate). Telegram API credentials are valid and webhook URLs are correctly set up. MongoDB Search Index Templates Documentation Collection Index { "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } } Feedback Collection Index { "mappings": { "dynamic": false, "fields": { "prompt": { "type": "string" }, "response": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "feedback": { "type": "token" } } } }

Who is this for? This workflow is ideal for developers, content creators, or customer support teams looking to automate text-to-speech conversion using OpenAI. What problem does this solve? It automates the process of converting text inputs into speech, reducing manual effort and enhancing productivity. What this workflow does: This workflow triggers when a text input is received via a webhook, converts it into audio using the OpenAI API, and sends the generated speech back through a webhook response. Setup: Ensure you have an OpenAI API key (you can get it from OpenAI website). Set up the webhook URL and parameters. Configure the OpenAI node with your API key (Create New Credentials). set up the responde to webhook node.

Analyze & Sort Suspicious Email Contents with ChatGPT and Jira Who is this for? This workflow is tailored for IT security teams, managed service providers (MSPs), and organizations aiming to streamline the detection and reporting of phishing emails. It's especially useful for teams handling high email volumes and requiring quick, automated analysis. What problem is this workflow solving? Phishing emails pose a significant cybersecurity threat, and manual review processes are time-consuming and prone to human error. This workflow automates the identification of malicious emails, provides AI-driven insights, and generates structured reports, enabling faster and more efficient responses to email-based threats. What this workflow does This workflow integrates Gmail or Microsoft Outlook to monitor and capture incoming emails. It processes the email content and headers, converts the email's body to a visual screenshot for clarity, and uses ChatGPT's advanced AI to analyze the email for phishing indicators. Based on the analysis, it categorizes emails as potentially malicious or benign, creating detailed Jira tickets for each case. Attachments, including the email body and screenshots, are automatically uploaded for comprehensive reporting. Key steps include: Email Integration: Captures emails from Gmail or Microsoft Outlook. Content Processing: Extracts and organizes email content and metadata. AI Analysis: Uses ChatGPT to evaluate email content and headers. Classification: Categorizes emails as malicious or benign. Automated Reporting: Creates Jira tickets with detailed analysis and attachments. Setup Authentication: Configure Gmail or Microsoft Outlook credentials in n8n. API Keys: Add credentials for the HTML screenshot service (hcti.io) and OpenAI. Jira Configuration: Set up project and issue types in the Jira nodes. Customization: Update sticky notes and nodes to fit your organizational requirements, such as modifying the AI prompt or Jira ticket fields. How to customize this workflow to your needs Adjust email triggers to include or exclude specific senders or subjects. Refine the AI prompt in the ChatGPT node to tailor phishing detection criteria. Modify Jira ticket content to include additional fields or match specific workflows. This workflow is ideal for automating email threat detection, reducing response times, and enhancing overall cybersecurity processes. By leveraging AI-powered insights, it helps organizations stay ahead of phishing attacks.

🔍 Scrape Glassdoor with Bright Data Designed for sales teams, recruiters, and marketers aiming to automate job discovery and prospecting. This workflow scrapes Glassdoor job listings using Bright Data and automatically generates targeted pitches using AI, streamlining lead identification and outreach. 🧩 How It Works This automation leverages n8n, Bright Data, Google Sheets, and OpenAI: 1. Trigger Starts with a custom form input (Location, Keyword, Country). 2. Bright Data Job Scrape Triggers a Bright Data dataset snapshot via HTTP Request. Polls snapshot progress using a Wait node, ensuring data readiness. Retrieves full job listings dataset once ready. 3. Google Sheets Integration Writes detailed job data (company, role, location, overview, metrics) into a Google Sheet. Uses a pre-built template for organized data storage. 4. Automated Pitch Generation (AI) Splits listings into actionable parts: company name, title, and description. Sends data to OpenAI (via LangChain) to generate relevant pitches or icebreakers. Saves generated content back into the same sheet for easy access. ✅ Requirements Ensure you have the following: Google Sheets Google account Template Sheet with columns for job details and AI-generated pitches Bright Data Active account with Dataset API access API key and dataset ID OpenAI Valid OpenAI API key for GPT models n8n Environment Nodes: HTTP Request, Wait, If, Google Sheets, Split Out, LangChain (OpenAI) Credentials: Google Sheets OAuth2 Bright Data API credentials OpenAI API key ⚙️ Setup Instructions Step 1: Prepare Google Sheets Copy the provided Google Sheets template Do not change headers Step 2: Import & Configure Workflow in n8n Import the workflow JSON file Set Google Sheets node: Link to your copied sheet Confirm correct tab name Step 3: Configure Bright Data Replace <YOUR_BRIGHT_DATA_API_KEY> with your real key Set your dataset ID in all HTTP Request nodes Step 4: Configure OpenAI (LangChain) Connect OpenAI API key to the LangChain node Customize prompt to match tone and outreach style Step 5: Testing & Scheduling Test via manual form trigger Schedule runs or leave form enabled for on-demand use 🧠 Tips & Best Practices Use specific keywords and locations for better results Adjust polling intervals based on dataset size Refine AI prompts regularly to improve pitch quality Clean unused columns from your sheet to boost performance 💬 Support & Feedback For help or customization: 📧 Email: Yaron@nofluff.online 📺 YouTube: @YaronBeen 🔗 LinkedIn: linkedin.com/in/yaronbeen 📚 Bright Data Docs: docs.brightdata.com/introduction

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.

This n8n template introduces the Dynamic Prompts AI workflow pattern which are incredible for certain types of data extraction tasks where attributes are unknown or need to remain flexible. The general idea behind this pattern is that the prompts for requested attributes to be extracted live outside the template and so can be changed at any time - without needing to edit the template. This seriously cuts down on maintainance requirements and is reusable for any number of tables at little cost. Check out the n8n Studio Episode here: https://www.youtube.com/watch?v=_fNAD1u8BZw Community post here: https://community.n8n.io/t/dynamic-prompts-with-n8n-baserow-and-airtable/72052 Looking for the Airtable Version? https://n8n.io/workflows/2771-ai-data-extraction-with-dynamic-prompts-and-airtable/ How it works Given we have an "input" field for context and a number of fields for the data we want to extract, this template will run in the background to react to any changes to either the "input" or fields and automatically update the rows accordingly. The key is that Baserow fields have a special property called the "field description". In this pattern, we use this property to allow the user to store a simple prompt describing the data that should exist in the column. Our n8n template reads these column descriptions aka "prompts" to use as instructions to perform tasks on the "input". In this template, the "input" is a PDF of a resume/CV and the columns are attributes a HR person would want to extract from it - such as full name, address, last position, years of experience etc. How to use First publish this template and ensure it's accessible via webhook URL. You then have to complete the "create Baserow webhooks" steps to configure your baserow to send change events to the n8n template. Baserow webhooks are created in the Baserow web interface. Check the template for more instructions. Requirements Baserow for Tables/Database OpenAI for LLM and extraction. Feel free to choose another LLM if preferred. Customising this workflow If you're not using files, you can replace the "input" field with anything you like. For example, the "input" could be single line text.

How it works: Webhook URL that responds to Requests with an AI generated Image based on the prompt provided in the URL. Setup Steps: Ideate your prompt URL Encode The Prompt (as shown in the Template) Authenticate with your OpenAI Credentials Put together the Webhook URL with your prompt and enter into a webbrowser In this way you can expose a public url to users, employee's etc. without exposing your OpenAI API Key to them. Click here to find a blog post with additional information.

Compare Local Ollama Vision Models for Image Analysis using Google Docs Process images using locally hosted Ollama Vision Models to extract detailed descriptions, contextual insights, and structured data. Save results directly to Google Docs for efficient collaboration. Who is this for? This workflow is ideal for developers, data analysts, marketers and AI enthusiasts who need to process and analyze images using locally hosted Ollama Vision Language Models. It’s particularly useful for tasks requiring detailed image descriptions, contextual analysis, and structured data extraction. What problem is this workflow solving? / Use Case The workflow solves the challenge of extracting meaningful insights from images in exhaustive detail, such as identifying objects, analyzing spatial relationships, extracting textual elements, and providing contextual information. This is especially helpful for applications in real estate, marketing, engineering, and research. What this workflow does This workflow: Downloads an image file from Google Drive. Processes the image using multiple Ollama Vision Models (e.g., Granite3.2-Vision, Gemma3, Llama3.2-Vision). Generates detailed markdown-based descriptions of the image. Saves the output to a Google Docs file for easy sharing and further analysis. Setup Ensure you have access to a local instance of Ollama. https://ollama.com/ Pull the Ollama vision models. Configure your Google Drive and Google Docs credentials in n8n. Provide the image file ID from Google Drive in the designated node. Update the list of Ollama vision models Test the workflow by clicking ‘Test Workflow’ to trigger the process. How to customize this workflow to your needs Replace the image source with another provider if needed (e.g., AWS S3 or Dropbox). Modify the prompts in the "General Image Prompt" node to suit specific analysis requirements. Add additional nodes for post-processing or integrating results into other platforms like Slack or HubSpot. Key Features: Detailed Image Analysis**: Extracts comprehensive details about objects, spatial relationships, text elements, and contextual settings. Multi-Model Support**: Utilizes multiple vision models dynamically for optimal performance. Markdown Output**: Formats results in markdown for easy readability and documentation. Google Drive Integration**: Seamlessly downloads images and saves results to Google Docs.

This workflow template, "Chinese Translator via Line x OpenRouter (Text & Image)" is designed to provide seamless Chinese translation services directly within the LINE messaging platform. By integrating with OpenRouter.ai and advanced language models like Qwen, this workflow translates text or images containing Chinese characters into pinyin and English translations, making it an invaluable tool for language learners, travelers, and businesses operating in multilingual environments. This template is ideal for: Language Learners: Who want to practice Chinese by receiving instant translations of text or images. Travelers: Looking for quick translations of Chinese signs, menus, or documents while abroad. Educators: Teaching Chinese language courses and needing tools to assist students with translations. Businesses: Operating in multilingual markets and requiring efficient communication tools. Automation Enthusiasts: Seeking to build intelligent chatbots that can handle language translation tasks. What Problem Does This Workflow Solve? Translating Chinese text or images into English and pinyin can be challenging, especially for beginners or those without access to reliable translation tools. This workflow solves that problem by: Automatically detecting and translating text or images containing Chinese characters. Providing accurate translations in both pinyin and English for better comprehension. Supporting multiple input formats (text, images) to cater to diverse user needs. Sending replies directly to users via the LINE messaging platform , ensuring accessibility and ease of use. What This Workflow Does 1) Receive Messages via LINE Webhook The workflow is triggered when a user sends a message (text, image, or other types) to the LINE bot. 2) Display Loading Animation A loading animation is displayed to reassure the user that their request is being processed. 3) Route Input Types The workflow uses a Switch node to determine the type of input (text, image, or unsupported formats). If the input is text , it is sent to the OpenRouter.ai API for translation. If the input is an image , the workflow extracts the image content, converts it to base64, and sends it to the API for translation. Unsupported formats trigger a polite response indicating the limitation. 4) Translate Content Using OpenRouter.ai The workflow leverages Qwen models from OpenRouter.ai to generate translations: For text inputs, it provides Chinese characters , pinyin , and English translations . For images, it extracts and translates using the qwen-VL model which can take images 5) Reply with Translations The translated content is formatted and sent back to the user via the LINE Reply API. Setup Guide Pre-Requisites Access to the LINE Developers Console to configure your webhook and channel access token. An OpenRouter.ai account with credentials to access Qwen models. Basic knowledge of APIs, webhooks, and JSON formatting. Step-by-Step Setup 1) Configure the LINE Webhook: Go to the LINE Developers Console and set up a webhook to receive incoming messages. Copy the Webhook URL from the Line Webhook node and paste it into the LINE Console. Remove any "test" configurations when moving to production. 2) Set Up OpenRouter.ai: Create an account on OpenRouter.ai and obtain your API credentials. Connect your credentials to the OpenRouter nodes in the workflow. 3) Test the Workflow: Simulate sending text or images to the LINE bot to verify that translations are processed and replied correctly. How to Customize This Workflow to Your Needs Add More Languages: Extend the workflow to support additional languages by modifying the API calls. Enhance Image Processing: Integrate more advanced OCR tools to improve text extraction from complex images. Customize Responses: Modify the reply format to include additional details, such as grammar explanations or cultural context. Expand Use Cases: Adapt the workflow for specific industries, such as tourism or e-commerce, by tailoring the translations to relevant vocabulary. Why Use This Template? Real-Time Translation: Provides instant translations of text and images, improving user experience and accessibility. Multimodal Support: Handles both text and image inputs, catering to diverse user needs. Scalable: Easily integrate into existing systems or scale to support multiple users and workflows. Customizable: Tailor the workflow to suit your specific audience or industry requirements.

Auto Source LinkedIn Candidates with GPT-4 Boolean Search & Google X-ray How It Works: User Input: The user pastes a job description or ideal candidate specifications into the workflow. Boolean Search String Generation: OpenAI processes the input and generates a precise LinkedIn Boolean search string formatted as: site:linkedin.com/in ("Job Title" AND "Skill1" AND "Skill2") This search string is optimized to find relevant LinkedIn profiles matching the provided criteria. Google Sheet Creation: A new Google Sheet is automatically created within a specified document to store extracted LinkedIn profile URLs. Google Search Execution: The workflow sends a search request to Google using an HTTP node with the generated Boolean string. Iterative Search & Data Extraction: The workflow retrieves the first 10 results from Google. If the desired number of LinkedIn profiles has not been reached, the workflow loops, fetching the next set of 10 results until the if condition is met. Data Storage: The workflow extracts LinkedIn profile URLs from the search results and saves them to the newly created Google Sheet for further review. Setup Steps: 1. API Key Configuration Under "Credentials", add your OpenAI API key from your OpenAI account settings. This key is used to generate the LinkedIn Boolean search string. 2. Adjust Search Parameters Navigate to the "If" node and update the condition to define the desired number of LinkedIn profiles to extract. The default is 50, but you can set it to any number based on your needs. 3. Establish Google Sheets Connection Connect your Google Sheets account** to the workflow. Create a document** to store the sourced LinkedIn profiles. The workflow automatically creates a new sheet for each new search, so no manual setup is needed. 4. Authenticate Google Search Google search requires authentication** for better results. Use the Cookie-Editor browser extension to export your header string and enable authenticated Google searches within the workflow. 5. Run the Workflow Execute* the workflow and monitor the *Google Sheet** for newly added LinkedIn profiles. Benefits: ✅ Automates profile sourcing, reducing manual search time. ✅ Generates precise LinkedIn Boolean search strings tailored to job descriptions. ✅ Extracts and saves LinkedIn profiles efficiently for recruitment efforts. This solution leverages OpenAI and advanced search techniques to enhance your talent sourcing process, making it faster and more accurate! 🚀

Summary Engage multiple, uniquely configured AI agents (using different models via OpenRouter) in a single conversation. Trigger specific agents with @mentions or let them all respond. Easily scalable by editing simple JSON settings. Overview This workflow is for users who want to experiment with or utilize multiple AI agents with distinct personalities, instructions, and underlying models within a single chat interface, without complex setup. It solves the problem of managing and interacting with diverse AI assistants simultaneously for tasks like brainstorming, comparative analysis, or role-playing scenarios. It enables dynamic conversations with multiple AI assistants simultaneously within a single chat interface. You can: Define multiple unique AI agents. Configure each agent with its own name, system instructions, and LLM model (via OpenRouter). Interact with specific agents using @AgentName mentions. Have all agents respond (in random order) if no specific agents are mentioned. Maintain conversation history across multiple turns. It's designed for flexibility and scalability, allowing you to easily add or modify agents without complex workflow restructuring. Key Features Multi-Agent Interaction:** Chat with several distinct AI personalities at once. Individual Agent Configuration:** Customize name, system prompt, and LLM for each agent. OpenRouter Integration:** Access a wide variety of LLMs compatible with OpenRouter. Mention-Based Triggering:** Direct messages to specific agents using @AgentName. All-Agent Fallback:** Engages all defined agents randomly if no mentions are used. Scalable Setup:** Agent configuration is centralized in a single Code node (as JSON). Conversation Memory:** Remembers previous interactions within the session. How to Set Up Configure Settings (Code Nodes): Open the Define Global Settings Code node: Edit the JSON to set user details (name, location, notes) and add any system message instructions that all agents should follow. Open the Define Agent Settings Code node: Edit the JSON to define your agents. Add or remove agent objects as needed. For each agent, specify: "name": The unique name for the agent (used for @mentions). "model": The OpenRouter model identifier (e.g., "openai/gpt-4o", "anthropic/claude-3.7-sonnet"). "systemMessage": Specific instructions or persona for this agent. Add OpenRouter Credentials: Locate the AI Agent node. Click the OpenRouter Chat Model node connected below it via the Language Model input. In the 'Credential for OpenRouter API' field, select or create your OpenRouter API credentials. How to Use Start a conversation using the Chat Trigger input. To address specific agents, include @AgentName in your message. Agents will respond sequentially in the order they are mentioned. Example: "@Gemma @Claude, please continue the count: 1" will trigger Gemma first, followed by Claude. If your message contains no @mentions, all agents defined in Define Agent Settings will respond in a randomized order. Example: "What are your thoughts on the future of AI?" will trigger Chad, Claude, and Gemma (based on your default settings) in a random sequence. The workflow will collect responses from all triggered agents and return them as a single, formatted message. How It Works (Technical Details) Settings Nodes: Define Global Settings and Define Agent Settings load your configurations. Mention Extraction: The Extract mentions Code node parses the user's input (chatInput) from the When chat message received trigger. It looks for @AgentName patterns matching the names defined in Define Agent Settings. Agent Selection: If mentions are found, it creates a list of the corresponding agent configurations in the order they were mentioned. If no mentions are found, it creates a list of all defined agent configurations and shuffles them randomly. Looping: The Loop Over Items node iterates through the selected agent list. Dynamic Agent Execution: Inside the loop: An If node (First loop?) checks if it's the first agent responding. If yes (true path -> Set user message as input), it passes the original user message to the Agent. If no (false path -> Set last Assistant message as input), it passes the previous agent's formatted output (lastAssistantMessage) to the next agent, creating a sequential chain. The AI Agent node receives the input message. Its System Message and the Model in the connected OpenRouter Chat Model node are dynamically populated using expressions referencing the current agent's data from the loop ({{ $('Loop Over Items').item.json.* }}). The Simple Memory node provides conversation history to the AI Agent. The agent's response is formatted (e.g., AgentName:\n\nResponse) in the Set lastAssistantMessage node. Response Aggregation: After the loop finishes, the Combine and format responses Code node gathers all the lastAssistantMessage outputs and joins them into a single text block, separated by horizontal rules (---), ready to be sent back to the user. Benefits Scalability & Flexibility:** Instead of complex branching logic, adding, removing, or modifying agents only requires editing simple JSON in the Define Agent Settings node, making setup and maintenance significantly easier, especially for those managing multiple assistants. Model Choice:** Use the best model for each agent's specific task or persona via OpenRouter. Centralized Configuration:** Keeps agent setup tidy and manageable. Limitations Sequential Responses:** Agents respond one after another based on mention order (or randomly), not in parallel. No Direct Agent-to-Agent Interaction (within a turn):* Agents cannot directly call or reply to each other *during the processing of a single user message. Agent B sees Agent A's response only because the workflow passes it as input in the next loop iteration. Delayed Output:* The user receives the combined response only *after all triggered agents have completed their generation.