Vectorize Medical Procedures for Semantic Search with TUSS, Gemini & pgVector
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 8 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Postgres PGVector Store, Embeddings Google Gemini and Oracle Database Parameterization (community).
How it runs
Trigger: Manually, when you click “Execute workflow”.
- ORACLE DATABASE CONNECTION (Oracle Database with Parameterization): uses Oracle Database with Parameterization
- COLLECTION OF MEDICAL PROCEDURES (Code): runs custom JavaScript code
- FOR - MEDICAL PROCEDURES (Loop Over Items (Split in Batches)): loops over the items in batches
- Postgres PGVector Store: stores documents in the Postgres PGVector Store vector store, with embeddings: Embeddings Google Gemini; document loader: Data Loader
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-oracle-database-parameterization is verified or supports 3.0 (used in ORACLE DATABASE CONNECTION).
Nodes used (8)
- Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Token Splitter
@n8n/n8n-nodes-langchain.textSplitterTokenSplitter - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Manual Trigger
n8n-nodes-base.manualTrigger - Oracle Database with Parameterization
n8n-nodes-oracle-database-parameterization.Oracle Database with Parameterization - Code
n8n-nodes-base.code - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader
From the author
Description This workflow vectorizes the TUSS (Terminologia Unificada da Saúde Suplementar) table by transforming medical procedures into vector embeddings ready for semantic search. It automates the import of TUSS data, performs text preprocessing, and uses…