Sync PostgreSQL data to a Pinecone vector knowledge base using Gemini embeddings

by Taiwo Hassan ✓ · 21 views · created 2026-05-19 · Document Extraction, AI RAG

What this workflow does

This workflow has 12 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Postgres.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Workflow Configuration (Edit Fields (Set)): sets 20 fields: sourceName, allowedSchemas, allowedTables…
2. Discover PostgreSQL Metadata (Postgres): run a query
3. Filter Indexable Tables (Code): runs custom JavaScript code
4. Fetch Table Rows (Postgres): run a query
5. Build Embedding Documents (Code): runs custom JavaScript code
6. Prepare Gemini Embedding Batches (Code): runs custom JavaScript code
7. Generate Gemini Embeddings (HTTP Request): calls an HTTP API (POST)
8. Prepare Pinecone Upsert Batches (Code): runs custom JavaScript code
9. Upsert Vectors to Pinecone (HTTP Request): calls an HTTP API (POST)
10. Return Sync Summary (Code): runs custom JavaScript code

Services it uses

Postgres

Before you upgrade to n8n 3.0

Nodes used (6)

• Manual Triggern8n-nodes-base.manualTrigger
• Schedule Triggern8n-nodes-base.scheduleTrigger
• Edit Fields (Set)n8n-nodes-base.set
• Postgresn8n-nodes-base.postgres
• Coden8n-nodes-base.code
• HTTP Requestn8n-nodes-base.httpRequest

From the author

PostgreSQL Auto-Discovery to Pinecone Vector Knowledge Base Turn existing PostgreSQL databases into AI-searchable Pinecone vector knowledge bases without manually defining every table and column. This template discovers your PostgreSQL schema, selects…

View the original on n8n.io → Check your own copy