Notion to Pinecone vector store integration

This n8n automation is designed to extract, process, and store content from Notion pages into a Pinecone vector store. Here's a breakdown of the workflow:

Notion - Page Added Trigger: The automation starts by monitoring for newly added pages in a specific Notion database. It triggers whenever a new page is created, capturing the page's metadata.

Notion - Retrieve Page Content: Once triggered, the automation fetches the full content of the newly added Notion page, including blocks like text, images, and videos.

Filter Non-Text Content: The next step filters out non-text content (such as images and videos), ensuring only textual content is processed.

Summarize - Concatenate Notion's blocks content: The remaining text content is concatenated into a single block of text for easier processing.

Token Splitter: The concatenated text is then split into manageable tokens, which are chunks of text that can be used for embedding.

Create metadata and load content: Metadata such as the page ID, creation time, and title are added to the content, making it easy to reference and track.

Embeddings Google Gemini: The processed text is passed through a Google Gemini model to generate embeddings, which are numerical representations of the text that capture its semantic meaning.