Skip to content
FlowHub
FluxonLab
RAG & Knowledge BasesproFluxonLab library

HTML Scrape Embedding Extractor

by FluxonLab Importadapted from SplitoutUpdated May 2026
RequiresOpenAIGoogle SheetsGoogle Sheets
Share Post Share
MaWhen clicking ‘Test workflow’When clicking ‘…SeZip EntriesHtExtract ReviewsSOReviews to ListDDDefault Data LoaderDefault Data Lo…TSRecursive Character Text SplitterRecursive Chara…Embeddings OpenAIEmbeddings Open…SeSet VariablesHRGet Payload of PointsGet Payload of …SOClusters To ListOpenAI Chat ModelOpenAI Chat Mod…FiOnly Clusters With 3+ pointsOnly Clusters W…SeSet Variables1HRFind ReviewsSePrep Output For ExportPrep Output For…Export To SheetsHRClear Existing ReviewsClear Existing …EWTrigger InsightsSePrep Values For TriggerPrep Values For…EWExecute Workflow TriggerExecute Workflo…HRGet TrustPilot PageGet TrustPilot …VSQdrant Vector StoreQdrant Vector S…CoApply K-means Clustering AlgorithmApply K-means C…IECustomer Insights AgentCustomer Insigh…123456789101112
1/5
FLOWS
STEPS · 12
Run manually by an operator

On manual run, scrapes and splits HTML content, embeds it into Qdrant, and uses OpenAI to extract details into Google Sheets.

Tags

advancedtextsplitterrecursivecharactertextsplittereventai-agentssplitoutmanual-triggerembeddingsopenaidocumentdefaultdataloader
Connects
OpenAIsheetsGoogle Sheets
CategoryRAG & Knowledge Bases
Triggerevent
Complexityadvanced
Nodes24
AddedMay 9, 2026