Runbook - 06 RAG Vector Classified Docs

Objective

Show that a RAG agent retrieves only authorized chunks/documents before sending context to the LLM.

Security Value

Reduces over-retrieval in RAG.
Prevents confidential chunks from being sent to the model.
Combines vector search with data grants by classification.

Prerequisites

Oracle AI Database with support for VECTOR, TO_VECTOR, and VECTOR_DISTANCE.
Database compatible with Oracle Deep Data Security.
SQLcl or SQL*Plus.

Before - Vulnerable Environment

From the repository root, connect as ADMIN:
```
cd ~/DEEP-DATA-SECURITY/oracle-deep-data-security-lab
export TNS_ADMIN=~/DEEP-DATA-SECURITY/wallet-ddslab
sql admin@ddslab_tunnel
```
Presenter note: ADMIN prepares the classified chunks and security personas.

SQLcl note: after running a script with @file.sql, do not type /. The slash reruns the last command in the SQLcl buffer and can make a successful command look like an error.
Reset the scenario:
```
@scenarios/06-rag-vector-classified-docs/sql/99_reset.sql
```
Presenter note: this removes prior Data Grants, roles, users, and test data.

Create chunks and personas without applying data grants:

@scenarios/06-rag-vector-classified-docs/sql/00_schema.sql
@scenarios/06-rag-vector-classified-docs/sql/01_seed_data.sql
@scenarios/06-rag-vector-classified-docs/sql/02_identities.sql

Presenter note: rag_legacy_retrieval_role simulates a broad RAG retrieval layer before DDS is enforced.

Show every chunk and its classification:
```
SELECT chunk_id, document_title, department, classification, chunk_text
FROM dds_rag_chunks
ORDER BY chunk_id;
```
Presenter note: explain that confidential chunks should not be sent to the LLM for every user.

Simulate the RAG question:

Summarize critical documents about renewals, people, and legal risks.

Exit and connect as Nina, a regular employee:
```
exit
```
```
sql 'nina/Welcome1_DDS!@ddslab_tunnel'
```
Presenter note: Nina represents a regular employee using an internal copilot.
Run the vector search before DDS:
```
@scenarios/06-rag-vector-classified-docs/sql/04_test_queries.sql
```
Presenter note: before DDS, a broad retrieval path can place HR, legal, or executive confidential chunks in the LLM context.

Expected Result Before

The search may retrieve HR_CONFIDENTIAL, LEGAL_CONFIDENTIAL, and EXECUTIVE_CONFIDENTIAL chunks.
The LLM could receive sensitive context before it even generates an answer.

After - Applying Deep Data Security

Exit and reconnect as ADMIN:
```
exit
```
```
sql admin@ddslab_tunnel
```
Apply data grants by classification:
```
@scenarios/06-rag-vector-classified-docs/sql/03_data_grants.sql
```
Presenter note: the database now filters chunks before the LLM receives any context.

Test Nina after DDS:

exit

sql 'nina/Welcome1_DDS!@ddslab_tunnel'

@scenarios/06-rag-vector-classified-docs/sql/04_test_queries.sql

Presenter note: Nina should retrieve only PUBLIC and INTERNAL chunks.

Repeat the same search as HR, legal, and executive personas:
```
sql 'heitor/Welcome1_DDS!@ddslab_tunnel'
sql 'sofia/Welcome1_DDS!@ddslab_tunnel'
sql 'carlos/Welcome1_DDS!@ddslab_tunnel'
```
Presenter note: each persona receives only the chunk classifications authorized for that business role.

Expected Result After

nina retrieves only PUBLIC and INTERNAL chunks.
heitor retrieves authorized HR content.
sofia retrieves authorized legal content.
carlos retrieves all chunks through the executive role.
The RAG layer sends only authorized context to the LLM.

Demo Evidence

Retrieved chunk list before and after protection.
Visible classifications by persona.
Explanation that enforcement happens before the LLM call.

Official References

Oracle Deep Data Security Guide: https://docs.oracle.com/en/database/oracle/oracle-database/26/ddscg/index.html
Create Data Grants: https://docs.oracle.com/en/database/oracle/oracle-database/26/ddscg/create-data-grants.html
TO_VECTOR SQL Reference: https://docs.oracle.com/en/database/oracle/oracle-database/26/sqlrf/to_vector.html
VECTOR operations in PL/SQL: https://docs.oracle.com/en/database/oracle/oracle-database/26/lnpls/sql-data-types.html

4.5 KiB Executable File Raw Blame History