Add Deep Research Agent with Oracle 26AI AI Database Demo

[businessarshgoyal]

Deep Research Agent with Oracle 26AI AI Database

This PR adds a comprehensive demo showcasing Oracle 26AI AI Database's powerful vector search capabilities through an intelligent research agent.

Key Features Demonstrated

• Native VECTOR Data Type: 1536-dimensional embeddings stored directly in Oracle 26AI AI Database
• HNSW Vector Indexing: Lightning-fast similarity search with 95% accuracy
• Semantic Memory: Understands context and meaning, not just keywords
• Enterprise Scale: Production-ready with ACID compliance and high availability

What's Included

• Complete Working Demo (main.py) - Full schema setup and vector operations
• Interactive Agent (agent_demo.py) - Research agent with memory recall
• Connection Testing (test_connection.py) - Oracle database validation
• Comprehensive Documentation - Setup guide and technical deep dive

Technical Highlights

• Combines OpenAI embeddings with Oracle's native vector storage
• Demonstrates cosine similarity search in pure SQL
• Shows hybrid search capabilities (structured + vector data)
• Includes performance optimizations and best practices

Perfect for developers exploring Oracle 26AI AI Database's vector capabilities!

[oracle-contributor-agreement]

Thank you for your pull request and welcome to our community! To contribute, please sign the Oracle Contributor Agreement (OCA).
The following contributors of this PR have not signed the OCA:

• PR author: business.arshgoyal@gmail.com (@businessarshgoyal)
• arsh@example.com

To sign the OCA, please create an Oracle account and sign the OCA in Oracle's Contributor Agreement Application.

When signing the OCA, please provide your GitHub username. After signing the OCA and getting an OCA approval from Oracle, this PR will be automatically updated.

If you are an Oracle employee, please make sure that you are a member of the main Oracle GitHub organization, and your membership in this organization is public.