RAG & Knowledge BasesproFluxonLab library

Document Embedding Extraction Pipeline

by FluxonLab Importadapted from SplitoutUpdated May 2026

RequiresOpenAI

Google Sheets

1/5

FLOWS

STEPS · 9

Run manually by an operator

On trigger, loads and splits documents, embeds them into Qdrant, then uses OpenAI to extract fields and log them to Google Sheets.

HTML Scrape Embedding Extractor

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

On manual run, fetches Hacker News items, embeds them into Qdrant, and uses OpenAI to extract structured data into Google Sheets.

On a chat message or Google Drive upload, embeds files into Supabase and answers questions with an OpenAI RAG agent.