Any AI feature you build on top of Notion is only as good as the index behind it. This sync keeps a Pinecone vector store in lockstep with your workspace.
Any AI feature you build on top of Notion is only as good as the index behind it. This sync keeps a Pinecone vector store in lockstep with your workspace.
It watches for edits, re-chunks changed pages, and upserts them with clean metadata while removing anything you archive. You get a retrieval-ready index that never drifts out of date.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Chunk the content with overlap so headings stay attached to their paragraphs.
pending
Embed each chunk and upsert it into Pinecone keyed by page ID and block path.
pending
Delete vectors for archived pages so retrieval never returns stale content.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Chunk and embed the Notion page, attaching page ID and last-edited timestamp as metadata for every vector.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.