AI-powered document search with Oracle and ONNX embeddings for recruiting

by sudarshan · 491 views · created 2025-10-29 · Engineering, AI RAG

What this workflow does

This AI workflow has 13 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Oracle Database.

How it runs

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

1. Text Input (Code): runs custom JavaScript code
2. Create a user (Oracle Database): execute
3. Perform Hybrid Search (Oracle Database): execute
4. Perform Semantic Search (Oracle Database): execute
5. ONNX Model Directory path (Code): runs custom JavaScript code
6. Format the result (Code): runs custom JavaScript code
7. Grant Privileges to user (Oracle Database): execute
8. Setup the table, Reload ONNX model and clear old data (Oracle Database): execute
9. Generate Documents data (Code): runs custom JavaScript code
10. Add Documents in to table (Oracle Database): uses Oracle Database

…plus 1 more step. See the full node list below.

Services it uses

Oracle Database

Before you upgrade to n8n 3.0

Nodes used (4)

• Manual Triggern8n-nodes-base.manualTrigger
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• Oracle Databasen8n-nodes-base.oracleDatabase
• Coden8n-nodes-base.code

From the author

How it works 1. Create a user for doing Hybrid Search. 2. Clear Existing Data, if present. 3. Add Documents into the table. 4. Create a hybrid index. 5. Run Semantic search on the Documents table for "prioritize teamwork and leadership experience". 6. Run…

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