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. 3. This is the third pipeline --- 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. The second is the KNN classifier tool, which takes any image as input and classifies it on the uploaded to Qdrant dataset.
Tags
Related workflows
See all General Automation→UGC Video Generation with Wan 2.5 on Replicate
This workflow automatically converts static images into dynamic videos using AI-powered animation. It saves you hours of video editing by transforming product photos, marketing images, or any static visuals into engaging video content perfect for social media and advertising campaigns. Overview This workflow automates the entire image-to-video generation process using the WAN-VIDEO 2.5 model via Replicate API. Simply provide an image URL and a text prompt describing the desired motion, and the workflow handles the video creation, status monitoring, and delivery of your animated content - typically ready in 30-120 seconds. Tools Used n8n**: The automation platform that orchestrates the workflow Replicate API**: Powers the WAN-VIDEO 2.5 AI model for image-to-video generation Status Monitoring**: Automated checking system with intelligent retry logic Error Handling**: Built-in resilience with comprehensive error management How to Install Import the Workflow: Download the .json file and import it into your n8n instance Get Replicate API Key: Sign up at replicate.com and copy your API token Configure API Token: Replace the placeholder in the "Set API Token" node Add Your Image: Update t
Get Xiaohongshu note details from a keyword with JustOneAPI
Use this n8n workflow template to get Xiaohongshu note details from a keyword with JustOneAPI. Who’s it for This template is for content researchers, creator operations teams, marketing teams, and automation builders who want to turn a Xiaohongshu keyword into a structured list of note details inside n8n. How it works The workflow starts with a single configuration node where you add your JustOneAPI token and the keyword you want to research. It then searches Xiaohongshu notes with the V2 search endpoint, extracts note IDs from the returned results, removes duplicates, and keeps only the first unique note ID by default. After that, it requests note details and outputs a structured note detail record that can be reused in downstream workflows. You can increase maxNotes if you want to retrieve details for more than one unique note ID. How to set up Import the workflow into n8n. Open the Set API Token and Research Inputs node. Add your JustOneAPI token. Replace the placeholder values for keyword and other optional search inputs. Leave maxNotes set to 1 if you want to fetch only the first unique result by default. Run the workflow and review the final output node. Requirements A JustOn
Generate and edit images with Havis AI Nano Banana 2
Havis AI - Nano Banana 2 n8n Workflow Summary This n8n workflow submits an image generation job to Havis AI Nano Banana 2, waits for processing, polls task status, and returns result data when the job completes. Who is this for? Creators who want a reusable no-code generation form. Agencies building client-facing AI automation. Developers who want an importable API test workflow. n8n users connecting Havis AI output to storage, Slack, Sheets, Airtable, webhooks, or a CMS. What this workflow does Opens an n8n Form Trigger for Nano Banana 2 inputs. Builds a clean JSON payload and removes empty optional fields. Sends a POST request to https://havis.ai/api/nano-banana-2. Waits 8 seconds, then polls https://havis.ai/api/task/{task_id}. Loops while the task is processing. Returns task ID, status, result URLs, credits used, and submitted payload. Returns a clean error object if the task fails. Setup Import the JSON workflow into n8n. Open the Form Trigger URL. Enter your Havis API key in api_key. Use only the key value; the workflow adds Bearer automatically. Fill in the model inputs and submit. For production, store the API key in n8n credentials or environment variables instead of typin