Skip to content
FlowHubFluxonLab
C
General Automationfree

Vector Database as a Big Data Analysis Tool for AI Agents [2/3 - anomaly]

by Jennyadapted from n8n official workflow galleryUpdated Aug 2026
RequiresCCodeHTTP RequestHTTP Request
Share Post Share
MaWhen clicking ‘Test workflow’When clicking ‘…HRTotal Points in CollectionTotal Points in…HRCluster Distance MatrixCluster Distanc…CoScipy Sparse MatrixScipy Sparse Ma…HRSet medoid idHRGet Medoid VectorGet Medoid Vect…SePrepare for Searching ThresholdPrepare for Sea…HRSearching ScoreSeThreshold ScoreHRSet medoid threshold scoreSet medoid thre…SOSplit Out1MeMergeSeTextual (visual) crop descriptionsTextual (visual…HREmbed textHRGet Medoid by TextGet Medoid by T…HRSet text medoid idSet text medoid…SePrepare for Searching Threshold1Prepare for Sea…SeThreshold Score1HRSearching Text Medoid ScoreSearching Text …SeMedoids VariablesMedoids Variabl…SeText Medoids VariablesText Medoids Va…SeQdrant cluster variablesQdrant cluster …SeInfo About Crop ClustersInfo About Crop…HRCrop CountsSOSplit OutHRSet text medoid threshold scoreSet text medoid…1234567891011121314151617181920212223242526
1/5
STEPS · 26
Run manually by an operator

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. 2. This is the second pipeline 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. The second is the KNN classifier tool, which takes any image as input and classifies it on the uploaded to Qdrant dataset.

Tags

n8nreference-only
Connects
CCodeWHTTP Request
CategoryGeneral Automation
Triggermanual
Complexityadvanced
Nodes26
AddedDec 19, 2024
CW
free

Generate AI videos using Havis AI Grok Imagine

Havis AI - Grok Imagine n8n Workflow Summary This n8n workflow submits a video generation job to Havis AI Grok Imagine, 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 Grok Imagine inputs. Builds a clean JSON payload and removes empty optional fields. Sends a POST request to https://havis.ai/api/grok-imagine. 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 typing it

by Tran Trung Nghia
CW
free

Search Xiaohongshu users by keyword and get profile details with JustOneAPI

Use this n8n workflow to search Xiaohongshu users from a keyword and get profile details with JustOneAPI. Who’s it for This template is for creator research teams, marketing teams, creator operations teams, and automation builders who want to turn a Xiaohongshu keyword into structured user profile data inside n8n. What this workflow does The workflow starts from one keyword and searches Xiaohongshu users with the V2 user search endpoint. It extracts unique user IDs from the returned results, keeps the first unique user ID by default, fetches user profile details with the user profile endpoint, and returns a structured output for downstream use. This makes it useful for creator discovery, account research, brand research, and competitor monitoring workflows. How to set up Import the workflow into n8n. Open the Prepare API and Research Inputs node. Add your JustOneAPI token. Update keyword. Optionally adjust page and maxUsers. Leave maxUsers at 1 if you want to fetch only the first unique user result by default. Run the workflow and review the final output node. Requirements A JustOneAPI token An n8n environment with HTTP Request support How to customize the workflow You can increase

by apisub001
CW
free

Generate and edit images using Havis AI GPT Image 2

Havis AI - GPT Image 2 n8n Workflow Summary This n8n workflow submits an image generation job to Havis AI GPT Image 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 GPT Image 2 inputs. Builds a clean JSON payload and removes empty optional fields. Sends a POST request to https://havis.ai/api/gpt-image-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 typing it int

by Tran Trung Nghia