Recipe recommendations with Qdrant and Mistral
This n8n workflow demonstrates creating a recipe recommendation chatbot using the Qdrant vector store recommendation API. Use this example to build recommendation features in your AI Agents for your users. How it works For our recipes, we'll use HelloFresh's weekly course and recipes for data. We'll scrape the website for this data. Each recipe is split, vectorised and inserted into a Qdrant Collection using Mistral Embeddings Additionally the whole recipe is stored in a SQLite database for later retrieval. Our AI Agent is setup to recommend recipes from our Qdrant vector store. However, instead of the default similarity search, we'll use the Recommendation API instead. Qdrant's Recommendation API allows you to provide a negative prompt; in our case, the user can specify recipes or ingredients to avoid. The AI Agent is now able to suggest a recipe recommendation better suited for the user and increase customer satisfaction. Requirements Qdrant vector store instance to save the recipes Mistral.ai account for embeddings and LLM agent Customising the workflow This workflow can work for a variety of different audiences. Try different sets of data such as clothes, sports shoes, vehicles or even holidays.
By JimleukCreate voice assistant interface with OpenAI GPT-4o-mini and text-to-speech
Voice Assistant Interface with n8n and OpenAI This workflow creates a voice-activated AI assistant interface that runs directly in your browser. Users can click on a glowing orb to speak with the AI, which responds with voice using OpenAI's text-to-speech capabilities. Who is it for? This template is perfect for: Developers looking to add voice interfaces to their applications Customer service teams wanting to create voice-enabled support systems Content creators building interactive voice experiences Anyone interested in creating their own "Alexa-like" assistant How it works The workflow consists of two main parts: Frontend Interface: A beautiful animated orb that users click to activate voice recording Backend Processing: Receives the audio transcription, processes it through an AI agent with memory, and returns voice responses The system uses: Web Speech API for voice recognition (browser-based) OpenAI GPT-4o-mini for intelligent responses OpenAI Text-to-Speech for voice synthesis Session memory to maintain conversation context Setup requirements n8n instance (self-hosted or cloud) OpenAI API key with access to: GPT-4o-mini model Text-to-Speech API Modern web browser with Web Speech API support (Chrome, Edge, Safari) How to set up Import the workflow into your n8n instance Add your OpenAI credentials to both OpenAI nodes Copy the webhook URL from the "Audio Processing Endpoint" node Edit the "Voice Assistant UI" node and replace YOURWEBHOOKURL_HERE with your webhook URL Access the "Voice Interface Endpoint" webhook URL in your browser Click the orb and start talking! How to customize the workflow Change the AI personality: Edit the system message in the "Process User Query" node Modify the visual style: Customize the CSS in the "Voice Assistant UI" node Add more capabilities: Connect additional tools to the AI Agent Change the voice: Select a different voice in the "Generate Voice Response" node Adjust memory: Modify the context window length in the "Conversation Memory" node Demo Watch the template in action: https://youtu.be/0bMdJcRMnZY
By Anderson AdelinoSummarize meeting transcripts with GPT-4 & sentiment analysis for Gmail
Who it's for Project managers, AI builders, and teams who want structured, automated meeting summaries with zero manual work. What it does This workflow monitors a Google Drive folder for new meeting notes (PDF/TXT), extracts text, summarizes it via OpenAI GPT-4o, groups tasks by sentiment, builds a styled HTML summary, and sends it via Gmail. How to set it up Connect Google Drive, OpenAI, and Gmail credentials. Point the Drive Trigger to your meeting notes folder. Paste the system prompt into the AI node. Set Gmail Email Type to HTML and Message to {{$json.email_html}}. Drop a test file and execute once. Requirements n8n account Google Drive, OpenAI, and Gmail credentials Non-scanned PDFs or plain text files Customization ideas Add Slack or Notion logging Support additional file types Translate summaries automatically Tags ai automation productivity gmail drive meeting-summary openai
By Dhinesh RavikumarAutomated client journey appointment reminders & follow-ups with Twilio
How It Works ⚙️ This workflow is a comprehensive, AI-powered system that acts as a virtual client relationship manager for any appointment-based business. It handles the entire client journey—from appointment booking to follow-up and re-engagement—all on autopilot. Appointment Trigger: The workflow starts when a new event is created in your Google Calendar. Client Data Management: It queries your client CRM database (Airtable or Google Sheets) to check if the client's email exists, preparing to send a personalized message. Dynamic Reminders: An If node splits the workflow. It sends a personalized welcome message for new clients and a standard reminder for returning clients, drastically reducing no-shows. Post-Appointment Follow-up: A Wait node pauses the workflow until after the appointment ends. It then sends a personalized "thank you" message via Twilio with a link to a review or survey. Re-engagement Loop: A separate Cron trigger runs weekly, automatically identifying clients who haven't rebooked in a set period (e.g., 30 days) and sends them a personalized offer to encourage them to return. Data Logging: It automatically logs all client data and engagement actions into a central database like Airtable or Google Sheets, creating a real-time dashboard for your business. How to Set Up 🛠️ Import the Workflow: Copy the provided workflow JSON and import it into your n8n instance. Configure Credentials: Google Calendar: Add your OAuth2 credential. Twilio: Add your API credentials. Google Sheets / Airtable: Add your credentials for your chosen CRM. Customize Workflow Nodes: Node 1 (Google Calendar Trigger): Select your Google Calendar credential and the calendar you use for bookings. Node 2 (Google Sheets / Airtable): Connect to your client CRM. Adjust the filter to search by the client's email from the calendar event. Node 4 & 5 (Twilio Reminders): Replace YOURTWILIONUMBER with your Twilio number. Customize the message body to fit your business. Node 6 (Wait): Adjust the Wait Duration if you want to send the follow-up message at a different time after the appointment. Node 7 (Twilio Follow-up): Replace the placeholder [LINK TO YOUR REVIEW/SURVEY PAGE] with your actual link. Nodes 8, 9, 10 (Re-engagement Loop): This is an optional, high-value part of the workflow. Configure the Cron node to run on your desired schedule. Adjust the filter in the Find Clients node to your specific re-engagement criteria (e.g., last visit date is older than 30 days). Save & Activate: Once all settings and credentials are configured, save the workflow and click the "Inactive" toggle in the top-right corner to make it live.
By Marth