Agents & Automations

Instructions This automation enables you to upload any image (via Form) of a Logo Sheet, containing multiple images of product logos that bring them in some context to one another. After submitting, an AI agent processes that Logo Sheet, turning it into a list of "Product Name" and "Attributes". It also checks if tools are similar to one another, given the context of the image. We utilize AI vision capabilities for that. NOTE: It might not be able to extract all information. For a "upload and forget it" workflow, it works well. You can even run it multiple times to be sure. However, if you need to ensure it extracts everything, you might think about a multi-agent setup with validation agent steps. Once the agent finishes the extraction, it will traditionally and deterministically add those attributes to Airtable (creating them if they do not already exist) and also upsert the tool information. It uses MD5 hashes for turning product names into identifiers. You could also use it without that, but I wanted to have something that looks at least like an ID. Setup 1. Set up Airtable as shown below. 2. Update and set credentials for all Airtable nodes. 3. Check or adjust the prompt of the agent to match your use case. 4. Activate the workflow. 5. Open the form (default: https://your-n8n.io/form/logo-sheet-feeder). Enjoy growing your Airtable! Enjoy the workflow! ❤️ Let the work flow — Workflow Automation & Development

This workflow connects Telegram bots with LangChain nodes in n8n. The main AI Agent Node is configured as a Conversation Agent. It has a custom System Prompt which explains the reply formatting and provides some additional instructions. The AI Agent has several connections: - OpenAI GPT-4 model is called to generate the replies. - Window Buffer Memory stores the history of conversation with each user separately. - There is an additional Custom n8n Workflow tool (Dall-E 3 Tool). The AI Agent uses this tool when the user requests an image generation. In the lower part of the workflow, there is a series of nodes that call the Dall-E 3 model with the user Telegram ID and a prompt for a new image. Once the image is ready, it is sent back to the user. Finally, there is an extra Telegram node that masks HTML syntax for improved stability in case the AI Agent replies using the unsupported format.

Learn how to streamline your content creation process using OpenAI's GPT models and Google Sheets. This template, part of the AI Tools 101 YouTube course series, guides you through generating keywords, setting the tone, outlining, and drafting content, all within Google Sheets. Enhance your productivity and content quality with this comprehensive AI-driven solution.

This workflow is an experiment to integrate charts in AI Agents, using the new Structured Output from OpenAI and Quickchart.io. How it works Users chat with an AI Agent. Anytime the AI Agent considers a chart is needed, it calls a tool to generate a chart. OpenAI generates a chart using the Quickchart definition. This object is added at the end of a Quickchart.io URL (see documentation). The URL is added in the conversation via the AI Agent as markdown. Set up steps 1. Create an OpenAI API Key 2. Create the OpenAI credentials 3. Use the credentials for the HTTP Request node (as Predefined Credential type) 4. Activate your workflow 5. Start chatting For example, you can ask the AI Agent to generate a chart about the top 5 movies at the box office. Start exploring the limits Shout-out: Quickchart.io is an amazing open source project that provides a free API to test. Go check them out!

This workflow is designed to automate the generation and updating of SEO meta titles and descriptions for WooCommerce products using n8n. It leverages Google Sheets for data input, a FREE language model (Gemini 2.0 Flash Exp. via OpenRouter) for generating SEO-optimized meta tags, and WooCommerce for updating product details. How It Works:Trigger: The workflow can be triggered manually or on a schedule. The manual trigger allows for testing, while the schedule trigger can be set to run at regular intervals (e.g., every few minutes) to process new products. Data Retrieval: The workflow starts by retrieving product IDs from a Google Sheets document. It looks for products that do not yet have meta titles or descriptions. Using the retrieved product ID, the workflow fetches the corresponding product details from WooCommerce, including the product name, description, short description, and categories. Meta Tag Generation: The product details are passed to a language model (Gemini 2.0 Flash Exp) via OpenRouter. The model generates SEO-optimized meta titles and descriptions based on the provided content. The generated meta tags are structured and validated to ensure they meet SEO best practices, such as character limits and keyword inclusion. Update WooCommerce: The generated meta title and description are then updated in the WooCommerce product metadata using the Yoast SEO fields. Update Google Sheets: Finally, the workflow updates the Google Sheets document with the newly generated meta tags, along with the product URL, title, and the timestamp of the update. Set Up Steps: 1. Google Sheets Setup: - Create a copy of the provided Google Sheets template and insert WooCommerce product IDs in column "B". - Ensure the Google Sheets document has columns for METATITLE, METADESCRIPTION, URL, TITLE POST, and DATA (timestamp). 2. n8n Workflow Configuration: - Google Sheets Node: Configure the "Get product ID" node to connect to your Google Sheets document. Use OAuth2 for authentication. - WooCommerce Node: Set up the WooCommerce nodes to connect to your WooCommerce store using the WooCommerce API credentials. - OpenRouter Node: Configure the "Gemini 2.0 Flash Exp" node with your OpenRouter API credentials to access the language model. - Structured Output Parser: Ensure the output parser is set to handle the structured data format for meta titles and descriptions. Workflow Execution: Trigger the workflow manually to test the process or set up a schedule trigger to automate the workflow at regular intervals. Monitor the workflow execution to ensure that meta tags are generated and updated correctly in both WooCommerce and Google Sheets. Validation: After the workflow runs, verify that the meta titles and descriptions in WooCommerce are correctly updated and that the Google Sheets document reflects the changes. This workflow streamlines the process of optimizing WooCommerce product pages for SEO, saving time and ensuring consistency in meta tag generation. Need help customizing? Contact me for consulting and support or add me on LinkedIn.

Who is this for? This workflow is designed for businesses or developers looking to integrate voice-based chat applications with dynamic responses and conversational memory. What problem does this solve? It automates AI-powered voice conversations, maintaining context between sessions and converting speech-to-text and text-to-speech. What this workflow does: The workflow receives audio input, transcribes it using OpenAI, and processes the conversation using Google Gemini Chat Model (you can use OpenAI Chat Model). Responses are converted back to speech using ElevenLabs. Prerequisites: You'll need API keys for: - OpenAI (you can obtain it from the OpenAI website) - ElevenLabs (you can obtain it from their website) - Google Gemini (you can obtain it from Google AI Studio) Setup: Configure your API keys. Ensure that the value (voice_message) in the "Path" parameter in the Webhook node is used as the name of the parameter that will contain the voice message you are sending via the HTTP Post request.

What this workflow does: - Downloads the daily top podcasts of a selected genre. - Summarizes the content of each podcast in a few paragraphs. - Sends the summaries and the direct link to each podcast in a formatted email. Setup: 1. Create a free API key on Taddy. 2. Input your user number and API key into the TaddyTopDaily node in the header parameters X-USER-ID and X-API-KEY respectively. 3. Create access credentials for your Gmail as described in the Google Workspace documentation. Use the credentials from your client_secret.json in the Gmail node. 4. In the Genre node, set the genre of podcasts you want a summary for. Valid values are: TECHNOLOGY, NEWS, ARTS, COMEDY, SPORTS, FICTION, etc. Look at api.taddy.org for the full list. 5. Enter your email address in the Gmail node. 6. Change the schedule time for sending email from Schedule to whichever time you want to receive the email. Test: - Hit Test Workflow. - Check your email for the results. That's it! It should take less than 5 minutes total.

Automatically generate and publish WordPress blog posts from Google Sheets data using ChatGPT. Update Google Sheets with post details after publishing.

How it works This automated workflow discovers trending Instagram posts and creates similar AI-generated content. Here's the high-level process: 1. Content Discovery & Analysis - Scrapes trending posts from specific hashtags - Analyzes visual elements using AI - Filters out videos and duplicates 2. AI Content Generation - Creates unique images based on trending content - Generates engaging captions with relevant hashtags - Maintains brand consistency while being original 3. Automated Publishing - Posts content directly to Instagram - Monitors publication status - Sends notifications via TelegramSet up steps Setting up this workflow takes approximately 15-20 minutes: 1. API Configuration (7-10 minutes) - Instagram Business Account setup - Telegram Bot creation - API key generation (OpenAI, Replicate, Rapid API) 2. Database Setup (3-5 minutes) - Create required database table - Configure PostgreSQL credentials 3. Workflow Configuration (5-7 minutes) - Set scheduling preferences - Configure notification settings - Test connection and permissions Detailed technical specifications and configurations are available in sticky notes within the workflow.

This workflow demonstrates how to enrich data from a list of companies in a spreadsheet. While this workflow is production-ready if all steps are followed, adding error handling would enhance its robustness. Important notesCheck legal regulations: This workflow involves scraping, so make sure to check the legal regulations around scraping in your country before getting started. Better safe than sorry! Mind those tokens: OpenAI tokens can add up fast, so keep an eye on usage unless you want a surprising bill that could knock your socks off! 💸 Main WorkflowNode 1 - Webhook This node triggers the workflow via a webhook call. You can replace it with any other trigger of your choice, such as form submission, a new row added in Google Sheets, or a manual trigger. Node 2 - Get Rows from Google Sheet This node retrieves the list of companies from your spreadsheet. Here is the Google Sheet Template you can use. The columns in this Google Sheet are: - Company: The name of the company - Website: The website URL of the company These two fields are required at this step. - Business Area: The business area deduced by OpenAI from the scraped data - Offer: The offer deduced by OpenAI from the scraped data - Value Proposition: The value proposition deduced by OpenAI from the scraped data - Business Model: The business model deduced by OpenAI from the scraped data - ICP: The Ideal Customer Profile deduced by OpenAI from the scraped data - Additional Information: Information related to the scraped data, including: - Information Sufficiency: Indicates if the information was sufficient to provide a full analysis. Options: "Sufficient" or "Insufficient" - Insufficient Details: If labeled "Insufficient," specifies what information was missing or needed to complete the analysis. - Mismatched Content: Indicates whether the page content aligns with that of a typical company page. - Suggested Actions: Provides recommendations if the page content is insufficient or mismatched, such as verifying the URL or searching for alternative sources. Node 3 - Loop Over Items This node ensures that, in subsequent steps, the website in "extra workflow input" corresponds to the row being processed. You can delete this node, but you'll need to ensure that the "query" sent to the scraping workflow corresponds to the website of the specific company being scraped (rather than just the first row). Node 4 - AI Agent This AI agent is configured with a prompt to extract data from the content it receives. The node has three sub-nodes: - OpenAI Chat Model: The model used is currently gpt4-o-mini. - Call n8n Workflow: This sub-node calls the workflow to use ScrapingBee and retrieves the scraped data. - Structured Output Parser: This parser structures the output for clarity and ease of use, and then adds rows to the Google Sheet. Node 5 - Update Company Row in Google Sheet This node updates the specific company's row in Google Sheets with the enriched data. Scraper Agent WorkflowNode 1 - Tool Called from Agent This is the trigger for when the AI Agent calls the Scraper. A query is sent with: - Company name - Website: (the URL of the website) Node 2 - Set Company URL This node renames a field, which may seem trivial but is useful for performing transformations on data received from the AI Agent. Node 3 - ScrapingBee: Scrape Company's Website This node scrapes data from the URL provided using ScrapingBee. You can use any scraper of your choice, but ScrapingBee is recommended, as it allows you to configure scraper behavior directly. Once configured, copy the provided "curl" command and import it into n8n. Node 4 - HTML to Markdown This node converts the scraped HTML data to Markdown, which is then sent to OpenAI. The Markdown format generally uses fewer tokens than HTML. Improving the Workflow It's always a pleasure to share workflows, but creators sometimes want to keep some magic to themselves ✨. Here are some ways you can enhance this workflow: - Handle potential errors - Configure the scraper tool to scrape other pages on the website. Although this will cost more tokens, it can be useful (e.g., scraping "Pricing" or "About Us" pages in addition to the homepage). - Instead of Google Sheets, connect directly to your CRM to enrich company data. - Trigger the workflow from form submissions on your website and send the scraped data about the lead to a Slack or Teams channel.

This template provides a workflow to integrate a Telegram bot with NeurochainAI's inference capabilities, supporting both text processing and image generation. Follow these steps to get started: Purpose: Enables seamless integration between your Telegram bot and NeurochainAI for advanced AI-driven text and image tasks. Requirements: - Telegram Bot Token - NeurochainAI API Key - Sufficient credits to utilize NeurochainAI services Features: - Text processing through NeurochainAI's inference engine - AI-powered image generation (Flux) - Easy customization and scalability for your use case Setup: - Import the template into N8N - Add your Telegram Bot Token and NeurochainAI API Key where prompted - Follow the step-by-step instructions embedded in the template for configuration

This n8n template scrapes a list of AI grants from grants.gov and qualifies them using AI, determining interest and eligibility for the business. It then sends an email alert of interesting items to team members. The template also shows how you can use the "Remove Duplicates" node to simplify deduplication of external listings without the need to manage this yourself. Not particularly interested in AI Grants? This template works for other tender websites as long as you're able to scrape them. How it works A scheduled trigger is set to fetch a list of AI grants listed on the grants.gov website in the past day. A Remove Duplicates node is used to track Grant IDs to filter out those already processed by the workflow. New grants are summarized and analyzed by AI nodes to determine eligibility and interest, which is then saved to an Airtable database. Another scheduled trigger starts a little later than the first to collect and summarize the new grants. The results are then compiled into an email template using the HTML node, in the form of a newsletter designed to alert and brief team members of new AI grants. This email is then sent to a list of subscribers using the gmail node. How to use Make a copy of sample Airtable. The filters for fetching the grants are currently set to the "AI" category. Feel free to change this to include more categories. Not interested in grants? This template can work for other sources of leads; just change the endpoint and how you're defining the item ID to track. Requirements - Airtable for database - OpenAI for LLM Note: These are not hard requirements and can be exchanged for services available to you. Customizing the workflow: "Eligibility" criteria at this stage may be better served by identifying hard blockers instead, i.e., certifications, geographical considerations, or certain legal checks. Be sure to mention any hard blockers into the Eligibility prompt. Not particularly interested in AI prompts? This template works for other tender websites as long as you're able to scrape them.

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.

This n8n template builds a simple WhatsApp chatbot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer users' questions. This template is intended to help introduce n8n users interested in building with WhatsApp. How it works This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot. A product brochure is imported via the HTTP request node and its text contents extracted. The text contents are then uploaded to the in-memory vector store to build a knowledge base for the chatbot. A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out. The customer's message is sent to the AI Agent, which queries the product catalog using the vector store tool. The Agent's response is sent back to the user via the WhatsApp node. How to use Once you've set up and configured your WhatsApp account and credentials, first populate the vector store by clicking the "Test Workflow" button. Next, activate the workflow to enable the WhatsApp chatbot. Message your designated WhatsApp number and you should receive a message from the AI sales agent. Tweak the data source and behavior as required. Requirements - WhatsApp Business Account - OpenAI for LLM Customizing this workflow - Upgrade the vector store to Qdrant for persistence and production use-cases. - Handle different WhatsApp message types for a more rich and engaging experience for customers.

Disclaimer The Execute Command node is only supported on self-hosted (local) instances of n8n.Introduction KOKORO TTS - Kokoro TTS is a compact yet powerful text-to-speech model, currently available on Hugging Face and GitHub. Despite its modest size—trained on less than 100 hours of audio—it delivers impressive results, consistently topping the TTS leaderboard on Hugging Face. Unlike larger systems, Kokoro TTS offers the advantage of running locally, even on devices without GPUs, making it accessible for a wide range of users.Who will benefit from this integration? This will be useful for video bloggers, TikTokers, and it will also enable the creation of a free voice chat bot. Currently, TTS models are mostly paid, but this integration will allow for fully free voice generation. The possibilities are limited only by your imagination.Note Unfortunately, we can't interact with the KOKORO API via browser URL (GET/POST), but we can run a Python script through n8n and pass any variables to it. In the tutorial, the D drive is used, but you can rewrite this for any paths, including the C drive.Step 1 You need to have Python installed. Also, download and extract the portable version of KOKORO from GitHub. Create a file named voicegen.py with the following code in the KOKORO folder: (C:\KOKORO). As you can see, the output path is: (D:\output.mp3).python import sys import shutil from gradio_client import Client # Set UTF-8 encoding for stdout sys.stdout.reconfigure(encoding='utf-8') # Get arguments from command line text = sys.argv[1] # First argument: input text voice = sys.argv[2] # Second argument: voice speed = float(sys.argv[3]) # Third argument: speed (converted to float) print(f"Received text: {text}") print(f"Voice: {voice}") print(f"Speed: {speed}") # Connect to local Gradio server client = Client("<http://localhost:7860/>") # Generate speech using the API result = client.predict( text=text, voice=voice, speed=speed, api_name="/generate_speech" ) # Define output path output_path = r"D:\\\\output.mp3" # Move the generated file shutil.move(result[1], output_path) # Print output path print(output_path) Step 2 Go to n8n and create the following workflow.Step 3 Edit Field Module.json { "voice": "af_sarah", "text": "Hello world!" } Step 4 We’ll need an Execute Command module with the command:plaintext python C:\\KOKORO\\voicegen.py "{{ $json.text }}" "{{ $json.voice }}" 1 Step 5 The script is already working, but to listen to it, you can connect a Binary module with the path to the generated MP3 file: D:/output.mp3.Step 6 Click “Text workflow” and enjoy the result. There are more voices and accents than in ChatGPT, plus it’s free.P.S. If you want, there is a detailed tutorial on my blog.

Harness the power of Eden AI to create brief email summaries and effortlessly share them on Slack, enhancing productivity and optimizing team communication.

Every time a new Dialogflow fulfillment webhook is triggered, Make will automatically classify the query text by sentiment (positive, negative, or neutral) with a MonkeyLearn Machine Learning model. Then, a specific fulfillment response is sent depending on the sentiment.

⚠️ Important Disclaimer: This template is only compatible with a self-hosted n8n instance using a community node.Who is this for? This workflow is ideal for digital content creators, marketers, social media managers, and automation enthusiasts who want to produce fully automated vertical video content featuring inspirational or motivational quotes. Specifically tailored for Thai language, it effectively demonstrates integration of AI-generated imagery, video, ambient sound, and visually appealing quote overlays.What problem is this workflow solving? Manually creating high-quality, vertically formatted quote videos is often repetitive, time-consuming, and involves multiple tedious steps like selecting suitable visuals, editing audio tracks, and correctly overlaying text. Additionally, manual uploading to platforms like YouTube and maintaining accurate content records are prone to errors and inefficiencies.What this workflow does: - Fetches a quote, author, and scenic background description from a Google Sheet. - Automatically generates a vertical background image using the Flux AI (txt2img) API. - Transforms the AI-generated image into a subtly animated cinematic vertical video using the Kling video-generation API. - Generates an immersive, ambient background sound using ElevenLabs’ sound generation API. - Dynamically overlays the selected Thai-language quote and author text onto the generated video using FFmpeg, ensuring visually appealing typography (e.g., Kanit font). - Automatically uploads the final video to YouTube. - Updates the resulting YouTube video URL back to the Google Sheet, keeping your content records current and well-organized.Setup Requirements: This workflow requires a self-hosted n8n instance, as the execution of FFmpeg commands is not supported on n8n Cloud. Ensure FFmpeg is installed on your self-hosted environment. API keys and accounts setup for Flux, Kling, ElevenLabs, Google Sheets, Google Drive, and YouTube.Google Sheets Setup: Your Google Sheet must include these columns: - Index: Unique identifier for each quote - Quote (Thai): Quote text in Thai language (or your chosen language) - Pen Name (Thai): Author or pen name of the quote's creator - Background (EN): Short English description of the scene (e.g., "sunrise over mountains") - Prompt (EN): Detailed English prompt describing the image/video scene (e.g., "peaceful sunrise with misty mountains") - Background Image: URL of AI-generated image (updated automatically) - Background Video: URL of generated video (updated automatically) - Music Background: URL of generated ambient audio (updated automatically) - Video Status: YouTube URL (updated automatically after upload) A ready-to-use Google Sheets template is provided. To help you get started quickly, you can use this template spreadsheet.Next steps: - Authenticate Google Sheets, Google Drive, YouTube API, Flux AI, Kling API, and ElevenLabs API within n8n. - Ensure FFmpeg supports fonts compatible with your chosen language (for Thai, "Kanit" font is recommended). - Prepare your Google Sheets with desired quotes, authors, and image/video prompts.How to customize this workflow to your needs: - Fonts: Adjust font type, size, color, and positioning within the provided FFmpeg commands in the workflow’s code nodes. Verify that selected fonts properly support your target language. - Media Customization: Customize the scene descriptions in your Google Sheet to change image/video backgrounds automatically generated by AI. - Quote Management: Easily manage, add, or update quotes and associated details directly via Google Sheets without workflow modifications. - Audio Ambiance: Customize or adjust the ambient sound prompt for ElevenLabs within the workflow’s HTTP Request node to match your video's desired mood.Benefits of using AI-generated content and localized fonts: Leveraging AI-generated visual and audio elements along with localized fonts greatly enhances audience engagement by creating visually appealing, professional-quality content tailored specifically for your target audience. This automated workflow drastically reduces production time and manual effort, enabling rapid, consistent content creation optimized for platforms such as YouTube Shorts, Instagram Reels, and TikTok.

This Workflow simulates an AI-powered phone agent with two main functions: 📅 Appointment Booking – It can schedule appointments directly into Google Calendar. 🧠 RAG-based Information Retrieval – It provides answers using a Retrieval-Augmented Generation (RAG) system. For example, it can respond to questions such as store opening hours, return policies, or product details. The guide also explains how to purchase a dedicated phone number (with a +1 prefix) and link it to the AI agent. This setup is cost-effective, as it uses a FREE $10 credit to operate without additional charges in the beginning. ✨ Advantages 🕐 24/7 Availability – The AI agent can answer calls and assist customers at any time. 🤖 Automation – It reduces the workload on human staff by handling repetitive tasks like appointment scheduling and FAQ responses. 🔌 Easy Integration – Built with n8n, it’s flexible and customizable for various platforms and tools. 💸 Low-cost Setup – Using the free credit, businesses can get started without an upfront investment. 📦 Use Cases 🛍 E-commerce – Answer common product questions or order inquiries. 🏬 Retail Stores – Provide store hours, address info, and return policies. 🍽 Restaurants – Take reservations or share menu information. 💼 Service Providers – Book appointments or consultations. 📞 Any Local Business – Offer phone support without needing a live operator. How It Works This Workflow simulates an AI-powered phone agent with two primary functions: Appointment Booking The workflow captures call events (e.g., call_ended or call_analyzed) and extracts key details (transcript, caller info, duration, etc.). Using OpenAI, it summarizes the conversation and parses structured data (e.g., names, contact info, dates). For scheduling, it converts user-provided dates into Google Calendar-compatible formats and creates events automatically. RAG-Based Information Retrieval When a query is received (e.g., store hours, product details), the workflow retrieves relevant information from a Qdrant vector store. An AI agent processes the query using the retrieved data and responds via a webhook, ensuring accurate, context-aware answers. Set Up Steps 1. Prepare Qdrant Vector Store - Create/refresh a Qdrant collection (via HTTP requests). - Upload and vectorize documents (e.g., from Google Drive) using OpenAI embeddings. 2. Configure RetellAI Agent - Sign up for RetellAI, create an agent, and set the webhook URLs (n8n_call for call events, n8n_rag_function for RAG queries). - Purchase a Twilio phone number and link it to the agent. 3. n8n Workflow Setup - Connect OpenAI, Qdrant, Google Calendar, and Telegram nodes with credentials. - Customize prompts for summarization, date parsing, and RAG responses. - Test the workflow to ensure data flows from call events → processing → actions (e.g., calendar bookings, Telegram alerts). 4. Deploy - Trigger the workflow via RetellAI webhooks during calls. - Monitor outputs (e.g., call summaries in Telegram, calendar events). Note: Replace placeholders (e.g., QDRANTURL, COLLECTION, CHAT_ID) with actual values. Need help customizing? Contact me for consulting and support or add me on LinkedIn.

Overview This workflow aims to provide data visualization capabilities to a native SQL Agent. Together, they can help foster data analysis and data visualization within a team. It uses the native SQL Agent that works well and adds visualization capabilities thanks to OpenAI’s Structured Output and Quickchart.io. How it worksInformation Extraction: The Information Extractor identifies and extracts the user's question. If the question includes a visualization aspect, the SQL Agent alone may not respond accurately. SQL Querying: It leverages a regular SQL Agent: it connects to a database, queries it, and translates the response into a human-readable format. Chart Decision: The Text Classifier determines whether the user would benefit from a chart to support the SQL Agent's response. Chart Generation: If a chart is needed, the sub-workflow dynamically generates a chart and appends it to the SQL Agent’s response. If not, the SQL Agent’s response is output as is. Calling OpenAI for Chart Definition: The sub-workflow calls OpenAI via the HTTP Request node to retrieve a chart definition. Building and Returning the Chart: In the "Set Response" node, the chart definition is appended to a Quickchart.io URL, generating the final chart image. The AI Agent returns the response along with the chart. How to use it Use an existing database or create a new one. For example, I've used this Kaggle dataset and uploaded it to a Supabase DB. Add the PostgreSQL or MySQL credentials. Alternatively, you can use SQLite binary files (check this template). Activate the workflow. Start chatting with the AI SQL Agent. If the Text Classifier determines a chart would be useful, it will generate one in addition to the SQL Agent's response. Notes The full Quickchart.io specifications have not been fully integrated, so there may be some glitches (e.g., radar graphs may not display properly due to size limitations).

Enhance data management by filtering Google Sheets rows in two different sheets,generating insights with ChatGPT,and updating rows for streamlined operations.