Publish a transcript through OKafka, extract useful facts with OCI Generative AI, and search the resulting memories in Oracle AI Database. The lab uses three event consumers, two durable tables, and Spring AI chat and embedding models. OKafka delivers events through Oracle AI Database Transactional Event Queues (TxEventQ).
What this sample demonstrates
Vector Search
Store embeddings and search records by semantic similarity.
Use when users search by meaning or AI answers need grounded records.
TxEventQ
Transactional queues for database-backed events and messaging.
Use when event delivery and data changes need the same transaction boundary.
AI Agents
Runnable AI Agents behavior on Oracle AI Database.
Use when AI Agents needs to be tested against real database behavior.
Testcontainers
Disposable Oracle AI Database Free containers for repeatable local and integration tests.
Use when tests need real database behavior without sharing a long-lived development instance.
Spring
Spring framework samples for data access, messaging, configuration, and application wiring.
Use when Java applications need Spring-managed components backed by Oracle AI Database.
Kafka
Kafka-compatible eventing and migration paths backed by Oracle AI Database queues.
Use when comparing separate-broker designs or moving Kafka-shaped workloads toward database-native eventing.
Security
Identity-aware access, data protection, and audit samples for Oracle AI Database applications.
Use when applications need database-enforced boundaries for who can see, update, or operate on sensitive data.
Highlights
- DemoProducer: publishes incoming OSON events.
- IntakePolicy: deterministic intake prerequisites.
- CandidatePreparationService: extraction, admission, persistence, and embedding handoffs.
- TransactionalEventConsumer: transaction ownership and retries.