RAG Document Ingestion (Chunk → Embed → Store)

Turn any document into searchable knowledge: receive text via webhook, split it into overlapping chunks, generate OpenAI embeddings, and store each chunk in a Supabase (pgvector) table. Pairs with the RAG Chatbot template.

Steps in this flow

  1. Webhook: Document In
  2. Split into Chunks
  3. For Each Chunk
  4. OpenAI: Embed Chunk
  5. Supabase: Store Chunk

All templates