Library / RAG & Knowledge Bases
RAG & Knowledge Bases
Sync Notion pages and Supabase embeddings for scheduled RAG retrieval
Runs on a schedule to chunk and embed Notion content into Supabase using OpenAI embeddings, keeping the retrieval store current as source data changes.
What it does
## Adjust chunk size and overlap For more accurate search results, increase the overlap. For the *text-embedding-ada-002* model the chunk size plus overlap must not exceed 8191
The steps
- Embeddings OpenAI
- Token Splitter
- Loop Over Items
- Question and Answer Chain
- Vector Store Retriever
- OpenAI Chat Model
- When chat message received
- Schedule Trigger
- Limit
- Limit1
- Delete old embeddings if exist
- Get page blocks
- Default Data Loader
- Input Reference
20 steps in total.
Similar automations
RAG & Knowledge BasesEmbed New Notion Pages with OpenAI into a Supabase Vector Store9 stepsRAG & Knowledge BasesStore Notion Pages as Vector Documents in Supabase10 stepsRAG & Knowledge BasesStore Notion Pages as Vectors in Supabase with OpenAI8 stepsMCP Servers & ToolsOpenIndex Retrieval Plugin API as an MCP Server2 steps