Vector database as a big data analysis tool for AI agents [2/2 KNN]
Vector Database as a Big Data Analysis Tool for AI Agents Workflows from the webinar "Build production-ready AI Agents with Qdrant and n8n". This series of workflows shows how to build big data analysis tools for production-ready AI agents with the help of vector databases. These pipelines are adaptable to any dataset of images, hence, many production use cases. Uploading (image) datasets to Qdrant Set up meta-variables for anomaly detection in Qdrant Anomaly detection tool KNN classifier tool For anomaly detection The first pipeline to upload an image dataset to Qdrant. The second pipeline is to set up cluster (class) centres & cluster (class) threshold scores needed for anomaly detection. The third is the anomaly detection tool, which takes any image as input and uses all preparatory work done with Qdrant to detect if it's an anomaly to the uploaded dataset. For KNN (k nearest neighbours) classification The first pipeline to upload an image dataset to Qdrant. This pipeline is the KNN classifier tool, which takes any image as input and classifies it on the uploaded to Qdrant dataset. To recreate both You'll have to upload crops and lands datasets from Kaggle to your own Google Storage bucket, and re-create APIs/connections to Qdrant Cloud (you can use Free Tier cluster), Voyage AI API & Google Cloud Storage. [This workflow] KNN classification tool This tool takes any image URL, and as output, it returns a class of the object on the image based on the image uploaded to the Qdrant dataset (lands). An image URL is received via the Execute Workflow Trigger*, which is then sent to the Voyage AI Multimodal Embeddings API to fetch its embedding. The image's embedding vector is then used to query Qdrant, returning a set of X similar images with pre-labeled classes. Majority voting is done for classes of neighbouring images. A loop is used to resolve scenarios where there is a tie in Majority Voting, and we increase the number of neighbours to retrieve. When the loop finally resolves, the identified class is returned to the calling workflow.
By Jenny Website SEO health analytics with Google Sheets, PDF reports & Gmail alerts
Automated SEO Health Monitoring & Reporting This workflow automatically monitors the SEO health of websites stored in a Google Sheet. It fetches each website’s HTML, analyzes key SEO metrics (title, meta description, H1 count, canonical, robots, performance score, etc.) and updates results back into Google Sheets. If performance is poor (<50), it sends an alert email. For healthy sites, it generates a detailed PDF report and stores it in Google Drive. Who’s it for Digital marketing teams SEO agencies Website administrators who want automated SEO health checks Businesses with multiple websites or landing pages to monitor How it works Daily Trigger – Runs every day at 9 AM. Fetch Website List – Reads website URLs from Google Sheets. Crawl Websites – Uses HTTP requests to fetch each website’s HTML. SEO Analysis – Extracts SEO-related metadata (title, meta description, H1, etc.). Health Check – Scores SEO performance based on predefined rules. Decision Node – If score < 50 → Send alert email; else → Generate full SEO report. Update Logs – Logs results back into Google Sheets. Generate PDF Reports – Converts HTML reports into PDFs via PDF.co API. Save to Drive – Stores the PDF reports in Google Drive for long-term access. How to set up Open n8n and import the workflow. Configure your Google Sheets credentials and specify the sheet containing your website URLs. Add your Gmail account to allow automated alert emails. Set up your Google Drive credentials for storing PDF reports. Obtain an API key from PDF.co and configure the HTTP Request node. Adjust the Schedule Trigger to the time that works best (default: 9 AM daily). Test the workflow with a sample domain list. Requirements n8n instance (self-hosted or cloud) Google Sheets account (to store website URLs and logs) Gmail account (for sending alerts) Google Drive account (to save SEO reports) PDF.co API Key (for HTML → PDF conversion) How to customize Change performance threshold: Modify the IF node condition (default <50). Custom SEO rules: Edit the “SEO Health Check” Function node to add/remove checks (e.g., missing schema tags, page load times). Different output storage: Replace Google Drive with Dropbox, S3 or OneDrive. Alternate notification channels: Swap Gmail with Slack, Microsoft Teams or Telegram. Add-ons Send Slack/Teams notifications for low scores. Add PageSpeed Insights API for performance scoring. Generate weekly summary reports per domain. Integrate with Notion/Confluence to log SEO health history. Use Case Examples An SEO agency monitors 100+ client websites daily and sends alerts when a site has poor SEO signals. A company’s marketing manager gets a daily SEO health PDF report stored in Drive. A SaaS product team automatically logs performance changes for each release. Common Troubleshooting | Issue | Possible Cause | Solution | | ------------------------------------ | ------------------------------------------------ | --------------------------------------------------------------------------- | | Workflow fails at HTTP Crawl | Website blocks requests / timeout | Increase timeout in Set Config node or add retry logic. | | Always returns https://example.com | Missing canonical / OG tags in HTML | Enhanced code now infers from JSON-LD or domain detection. Update analyzer. | | PDF not generated | Invalid API key or wrong endpoint in PDF.co node | Verify PDF.co API key and endpoint URL. | | Email not sending | Gmail credentials not set or blocked | Reconnect Gmail in n8n credentials manager. | | Google Sheet not updating | Wrong column mapping in Update Sheet node | Check node mapping: domain column vs performance/date columns. | | Google Drive upload fails | Missing folder permissions | Ensure correct Drive folder ID and credentials. | Need Help? If you’d like assistance setting up, customizing or scaling this workflow for your use case, our n8n automation team at WeblineIndia can help you: Tailor SEO rules for your industry. Connect to additional APIs (Ahrefs, Semrush, PageSpeed). Automate weekly/monthly reporting with summary dashboards.
By WeblineIndia