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

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 Hybrid search for the text input in the Chat interface on the Documents table.

Setup Steps

Download the ONNX model

[allMiniLML12v2augmented.zip](https://adwc4pm.objectstorage.us-ashburn-1.oci.customer-oci.com/p/VBRD9P8ZFWkKvnfhrWxkpPe8K03-JIoM5h8EJyJcpE80c108fuUjg7R5L5O7mMZ/n/adwc4pm/b/OML-Resources/o/allMiniLML12v2augmented.zip)

Extract the ZIP file on the database server into a directory, for example /opt/oracle/onnx. After extraction, the folder contents should look like:

bash bash-4.4$ pwd /opt/oracle/onnx bash-4.4$ ls allMiniLML12v2.onnx

Connect as SYSDBA and create the DBA user