--- title: RheoData Blog | AI description: AI | RheoData Blog Posts --- [![RheoData - Logo - transparent-1](https://rheodata.com/hs-fs/hubfs/RheoData%20-%20Logo%20-%20transparent-1.png?width=250&height=50&name=RheoData%20-%20Logo%20-%20transparent-1.png "RheoData - Logo - transparent-1")](https://rheodata.com/) - Who We Are - [About Us](https://rheodata.com/who-we-are) - Services - Consulting - [The Studio](https://rheodata.com/the-studio) - Accelerators - [FrostCore](https://rheodata.com/frostcore) - [FrostAI](https://rheodata.com/frostai) - [RedCore](https://rheodata.com/redcore) - [RedAI](https://rheodata.com/redai) - [RedGuard](https://rheodata.com/redguard) - [BlueCore](https://rheodata.com/bluecore) - [Calypso](https://rheodata.com/calypso) - Services - [Data Integration](https://rheodata.com/data-integration) - [Analytics](https://rheodata.com/data-analytics) - [Multi-Cloud](https://rheodata.com/multi-cloud) - [Oracle@Google Cloud](https://rheodata.com/oracle-google-cloud) - [Exadata & Oracle Database](https://rheodata.com/exadata-and-oracle-database-26ai) - Verticals - [Manufacturing](https://rheodata.com/manufacturing) - [Retail](https://rheodata.com/retail) - [State & Local](https://rheodata.com/sled) - [Customer Stories](https://rheodata.com/customer-stories) - [Altec](https://rheodata.com/customer-stories/altec-oci-goldengate-data-migration) - [Shoe Carnival](https://rheodata.com/customer-stories/shoe-carnival-goldengate-microservices-migration) - [Icon](https://rheodata.com/customer-stories/icon-transatlantic-replication) - [Inovalon](https://rheodata.com/customer-stories/inovalon-data-pipeline-automation) - Resources - [Blog](https://rheodata.com/en-us/blog) - Books - [Pro Oracle GoldenGate 23ai](https://rheodata.com/pro-oracle-goldengate-23ai-for-the-dba-pdf-landing-page) - [Contact](https://rheodata.com/contact) [![](https://rheodata.com/hs-fs/hubfs/Imported_Blog_Media/blog-feature-Logo-Nov-26-2025-07-14-39-7226-PM.png?width=100&height=100&name=blog-feature-Logo-Nov-26-2025-07-14-39-7226-PM.png)](https://rheodata.com/) [![RheoData - Logo - transparent-1](https://rheodata.com/hs-fs/hubfs/RheoData%20-%20Logo%20-%20transparent-1.png?width=250&height=50&name=RheoData%20-%20Logo%20-%20transparent-1.png "RheoData - Logo - transparent-1")](https://rheodata.com/) - Who We Are - [About Us](https://rheodata.com/who-we-are) - Services - Consulting - [The Studio](https://rheodata.com/the-studio) - Accelerators - [FrostCore](https://rheodata.com/frostcore) - [FrostAI](https://rheodata.com/frostai) - [RedCore](https://rheodata.com/redcore) - [RedAI](https://rheodata.com/redai) - [RedGuard](https://rheodata.com/redguard) - [BlueCore](https://rheodata.com/bluecore) - [Calypso](https://rheodata.com/calypso) - Services - [Data Integration](https://rheodata.com/data-integration) - [Analytics](https://rheodata.com/data-analytics) - [Multi-Cloud](https://rheodata.com/multi-cloud) - [Oracle@Google Cloud](https://rheodata.com/oracle-google-cloud) - [Exadata & Oracle Database](https://rheodata.com/exadata-and-oracle-database-26ai) - Verticals - [Manufacturing](https://rheodata.com/manufacturing) - [Retail](https://rheodata.com/retail) - [State & Local](https://rheodata.com/sled) - [Customer Stories](https://rheodata.com/customer-stories) - [Altec](https://rheodata.com/customer-stories/altec-oci-goldengate-data-migration) - [Shoe Carnival](https://rheodata.com/customer-stories/shoe-carnival-goldengate-microservices-migration) - [Icon](https://rheodata.com/customer-stories/icon-transatlantic-replication) - [Inovalon](https://rheodata.com/customer-stories/inovalon-data-pipeline-automation) - Resources - [Blog](https://rheodata.com/en-us/blog) - Books - [Pro Oracle GoldenGate 23ai](https://rheodata.com/pro-oracle-goldengate-23ai-for-the-dba-pdf-landing-page) - [Contact](https://rheodata.com/contact) [![](https://rheodata.com/hs-fs/hubfs/Imported_Blog_Media/blog-feature-Logo-Nov-26-2025-07-14-39-7226-PM.png?width=100&height=100&name=blog-feature-Logo-Nov-26-2025-07-14-39-7226-PM.png)](https://rheodata.com/) - Who We Are - [About Us](https://rheodata.com/who-we-are) - Services - Consulting - [The Studio](https://rheodata.com/the-studio) - Accelerators - [FrostCore](https://rheodata.com/frostcore) - [FrostAI](https://rheodata.com/frostai) - [RedCore](https://rheodata.com/redcore) - [RedAI](https://rheodata.com/redai) - [RedGuard](https://rheodata.com/redguard) - [BlueCore](https://rheodata.com/bluecore) - [Calypso](https://rheodata.com/calypso) - Services - [Data Integration](https://rheodata.com/data-integration) - [Analytics](https://rheodata.com/data-analytics) - [Multi-Cloud](https://rheodata.com/multi-cloud) - [Oracle@Google Cloud](https://rheodata.com/oracle-google-cloud) - [Exadata & Oracle Database](https://rheodata.com/exadata-and-oracle-database-26ai) - Verticals - [Manufacturing](https://rheodata.com/manufacturing) - [Retail](https://rheodata.com/retail) - [State & Local](https://rheodata.com/sled) - [Customer Stories](https://rheodata.com/customer-stories) - [Altec](https://rheodata.com/customer-stories/altec-oci-goldengate-data-migration) - [Shoe Carnival](https://rheodata.com/customer-stories/shoe-carnival-goldengate-microservices-migration) - [Icon](https://rheodata.com/customer-stories/icon-transatlantic-replication) - [Inovalon](https://rheodata.com/customer-stories/inovalon-data-pipeline-automation) - Resources - [Blog](https://rheodata.com/en-us/blog) - Books - [Pro Oracle GoldenGate 23ai](https://rheodata.com/pro-oracle-goldengate-23ai-for-the-dba-pdf-landing-page) - [Contact](https://rheodata.com/contact) Posts about # AI ## [GenAI: How to get started](https://rheodata.com/en-us/blog/genai-getstarted) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:31:00 PM This post we are going to look at some items related to getting started with Generative AI. This is... [CONTINUE READING](https://rheodata.com/en-us/blog/genai-getstarted) ## [Similarity Search with Oracle’s Vector Datatype](https://rheodata.com/en-us/blog/similarity-search-oracle-vector-datatype) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:55 PM In my last two posts I showed you what the Oracle Vector Datatype is and how to update existing... [CONTINUE READING](https://rheodata.com/en-us/blog/similarity-search-oracle-vector-datatype) ## [What is Retrieval Augmentation Generation (RAG)?](https://rheodata.com/en-us/blog/retrieval-augmented-generation-rag-technical-guide) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:50 PM Retrieval Augmented Generation (RAG) represents a significant advancement in natural language... [CONTINUE READING](https://rheodata.com/en-us/blog/retrieval-augmented-generation-rag-technical-guide) ## [Harnessing the Power of AI and Machine Learning with RheoData: A Path to Success](https://rheodata.com/en-us/blog/harnessing-ai) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:48 PM In the dynamic landscape of modern technology, few fields hold as much promise and potential as... [CONTINUE READING](https://rheodata.com/en-us/blog/harnessing-ai) ## [Oracle to GCP Migration: Oracle@GCP vs. Cloud SQL – The Strategic Choice That Drives Results](https://rheodata.com/en-us/blog/oracle-gcp-vs-cloud-sql-migration) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:47 PM The partnership between Oracle and Google Cloud represents one of the most significant... [CONTINUE READING](https://rheodata.com/en-us/blog/oracle-gcp-vs-cloud-sql-migration) ## [Oracle Database 23ai: Where Enterprise Data Meets Artificial Intelligence](https://rheodata.com/en-us/blog/oracle-database-23ai-enterprise-ai-transformation) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:10 PM [CONTINUE READING](https://rheodata.com/en-us/blog/oracle-database-23ai-enterprise-ai-transformation) ## [Building a Data Governance Framework](https://rheodata.com/en-us/blog/build-data-governance-framework) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:06 PM # Building a Data Governance Framework Data governance is crucial for any organization looking to... [CONTINUE READING](https://rheodata.com/en-us/blog/build-data-governance-framework) ## [Transforming Oracle GoldenGate Operations with AI: Building MCP Servers for Real-World Impact](https://rheodata.com/en-us/blog/transforming-oracle-goldengate-operations-with-ai-mcp-servers) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:04 PM Remember when everyone said the cloud was just a fad? We’re hearing similar skepticism about AI in... [CONTINUE READING](https://rheodata.com/en-us/blog/transforming-oracle-goldengate-operations-with-ai-mcp-servers) ## [Oracle’s Vector Datatype](https://rheodata.com/en-us/blog/vector-datatype) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:30:03 PM At Oracle Cloud World 2023, Oracle announced they were moving toward enabling Artificial... [CONTINUE READING](https://rheodata.com/en-us/blog/vector-datatype) ## [Oracle to Azure Migration: Oracle@Azure vs. SQL Server – The Strategic Choice That Drives Results](https://rheodata.com/en-us/blog/oracle-azure-vs-sql-server-migration) Posted by [Bobby Curtis](https://rheodata.com/en-us/blog/author/bobby-curtis) | Nov 10, 2025 9:29:58 PM [CONTINUE READING](https://rheodata.com/en-us/blog/oracle-azure-vs-sql-server-migration) ### Recent Posts #### [Coordinated Replicats: Faster, Lower-Risk GoldenGate Loads](https://rheodata.com/en-us/blog/coordinated-replicats-initial-load) Posted at Jun 26, 2026 11:08:13 AM ![Post Featured Image](https://rheodata.com/hubfs/Gemini_Generated_Image_509fjc509fjc509f.png) #### [Forward Deployed Engineering: The Operating Model the Agentic Era Demands](https://rheodata.com/en-us/blog/forward-deployed-engineering-agentic-era) Posted at May 30, 2026 11:46:34 AM ![Post Featured Image](https://rheodata.com/hubfs/Gemini_Generated_Image_r8vpntr8vpntr8vp.png) #### [The Bowl Is Broken: A CEO's Note on Mental Health Month and Tech Team Burnout](https://rheodata.com/en-us/blog/tech-team-burnout-mental-health-month-2026) Posted at May 12, 2026 7:23:33 AM ![Post Featured Image](https://rheodata.com/hubfs/IMG_2142.jpg) ### Posts by Tag - [Cloud (88)](https://rheodata.com/en-us/blog/tag/cloud) - [GoldenGate (73)](https://rheodata.com/en-us/blog/tag/goldengate) - [Business Insights (51)](https://rheodata.com/en-us/blog/tag/business-insights) - [AI (36)](https://rheodata.com/en-us/blog/tag/ai) - [19c (22)](https://rheodata.com/en-us/blog/tag/19c) - [ai pipelines (17)](https://rheodata.com/en-us/blog/tag/ai-pipelines) - [18c (15)](https://rheodata.com/en-us/blog/tag/18c) - [21c (14)](https://rheodata.com/en-us/blog/tag/21c) - [12c (11)](https://rheodata.com/en-us/blog/tag/12c) - [machine learning (10)](https://rheodata.com/en-us/blog/tag/machine-learning) - [23ai (9)](https://rheodata.com/en-us/blog/tag/23ai) - [database (9)](https://rheodata.com/en-us/blog/tag/database) - [goldengate 21c (9)](https://rheodata.com/en-us/blog/tag/goldengate-21c) - [artificial intelligence (8)](https://rheodata.com/en-us/blog/tag/artificial-intelligence) - [data analytics (8)](https://rheodata.com/en-us/blog/tag/data-analytics) - [Google (7)](https://rheodata.com/en-us/blog/tag/google) - [23ai AI vector search (6)](https://rheodata.com/en-us/blog/tag/23ai-ai-vector-search) - [aws ec2 (6)](https://rheodata.com/en-us/blog/tag/aws-ec2) - [aws ec2 compute (6)](https://rheodata.com/en-us/blog/tag/aws-ec2-compute) - [ec2 (6)](https://rheodata.com/en-us/blog/tag/ec2) - [ggs (6)](https://rheodata.com/en-us/blog/tag/ggs) - [goldengate 19c (6)](https://rheodata.com/en-us/blog/tag/goldengate-19c) - [install nginx (6)](https://rheodata.com/en-us/blog/tag/install-nginx) - [23.4 (5)](https://rheodata.com/en-us/blog/tag/23-4) - [AI Vector Search (5)](https://rheodata.com/en-us/blog/tag/ai-vector-search) - [analytics (5)](https://rheodata.com/en-us/blog/tag/analytics) - [classic to microservices (5)](https://rheodata.com/en-us/blog/tag/classic-to-microservices) - [cloud-migration (5)](https://rheodata.com/en-us/blog/tag/cloud-migration) - [data mesh (5)](https://rheodata.com/en-us/blog/tag/data-mesh) - [database migration (5)](https://rheodata.com/en-us/blog/tag/database-migration) - [goldengate microservices (5)](https://rheodata.com/en-us/blog/tag/goldengate-microservices) - [11g (4)](https://rheodata.com/en-us/blog/tag/11g) - [19c goldengate (4)](https://rheodata.com/en-us/blog/tag/19c-goldengate) - [Azure (4)](https://rheodata.com/en-us/blog/tag/azure) - [Database Modernization (4)](https://rheodata.com/en-us/blog/tag/database-modernization) - [Google Cloud (4)](https://rheodata.com/en-us/blog/tag/google-cloud) - [Oracle GoldenGate (4)](https://rheodata.com/en-us/blog/tag/oracle-goldengate) - [autonomous database (4)](https://rheodata.com/en-us/blog/tag/autonomous-database) - [cloud management (4)](https://rheodata.com/en-us/blog/tag/cloud-management) - [cloud services (4)](https://rheodata.com/en-us/blog/tag/cloud-services) - [data engineering (4)](https://rheodata.com/en-us/blog/tag/data-engineering) - [data engineers (4)](https://rheodata.com/en-us/blog/tag/data-engineers) - [data governance (4)](https://rheodata.com/en-us/blog/tag/data-governance) - [heatwave (4)](https://rheodata.com/en-us/blog/tag/heatwave) - [12.2.1.x (3)](https://rheodata.com/en-us/blog/tag/12-2-1-x) - [12.3.x (3)](https://rheodata.com/en-us/blog/tag/12-3-x) - [12c goldengate (3)](https://rheodata.com/en-us/blog/tag/12c-goldengate) - [18c goldengate (3)](https://rheodata.com/en-us/blog/tag/18c-goldengate) - [23c (3)](https://rheodata.com/en-us/blog/tag/23c) - [AI Integration (3)](https://rheodata.com/en-us/blog/tag/ai-integration) - [Database Administration (3)](https://rheodata.com/en-us/blog/tag/database-administration) - [GoldenGate 23c (3)](https://rheodata.com/en-us/blog/tag/goldengate-23c) - [MySQL (3)](https://rheodata.com/en-us/blog/tag/mysql) - [Oracle Cloud Migration (3)](https://rheodata.com/en-us/blog/tag/oracle-cloud-migration) - [Oracle Database 26ai (3)](https://rheodata.com/en-us/blog/tag/oracle-database-26ai) - [adminclient (3)](https://rheodata.com/en-us/blog/tag/adminclient) - [architecture of data pipelines (3)](https://rheodata.com/en-us/blog/tag/architecture-of-data-pipelines) - [automation (3)](https://rheodata.com/en-us/blog/tag/automation) - [batch processing (3)](https://rheodata.com/en-us/blog/tag/batch-processing) - [big data (3)](https://rheodata.com/en-us/blog/tag/big-data) - [data cleaning (3)](https://rheodata.com/en-us/blog/tag/data-cleaning) - [data integration (3)](https://rheodata.com/en-us/blog/tag/data-integration) - [data pipelines (3)](https://rheodata.com/en-us/blog/tag/data-pipelines) - [data pipelines vs ETL pipelines (3)](https://rheodata.com/en-us/blog/tag/data-pipelines-vs-etl-pipelines) - [data science (3)](https://rheodata.com/en-us/blog/tag/data-science) - [data-replication (3)](https://rheodata.com/en-us/blog/tag/data-replication) - [database-platforms (3)](https://rheodata.com/en-us/blog/tag/database-platforms) - [enterprise data replication (3)](https://rheodata.com/en-us/blog/tag/enterprise-data-replication) - [gcp (3)](https://rheodata.com/en-us/blog/tag/gcp) - [hashicorp vault enterprise (3)](https://rheodata.com/en-us/blog/tag/hashicorp-vault-enterprise) - [Agentic AI (2)](https://rheodata.com/en-us/blog/tag/agentic-ai) - [Bring Your Own License (BYOL) Oracle (2)](https://rheodata.com/en-us/blog/tag/bring-your-own-license-byol-oracle) - [Cloud Database (2)](https://rheodata.com/en-us/blog/tag/cloud-database) - [Cloud modernization strategy (2)](https://rheodata.com/en-us/blog/tag/cloud-modernization-strategy) - [Docker (2)](https://rheodata.com/en-us/blog/tag/docker) - [EnterpriseDB (2)](https://rheodata.com/en-us/blog/tag/enterprisedb) - [Flask (2)](https://rheodata.com/en-us/blog/tag/flask) - [Google Cloud for Oracle workloads (2)](https://rheodata.com/en-us/blog/tag/google-cloud-for-oracle-workloads) - [Legacy Oracle systems (2)](https://rheodata.com/en-us/blog/tag/legacy-oracle-systems) - [Oracle AI Vector Search (2)](https://rheodata.com/en-us/blog/tag/oracle-ai-vector-search) - [Oracle Cloud Infrastructure (2)](https://rheodata.com/en-us/blog/tag/oracle-cloud-infrastructure) - [Oracle DBA skills in the cloud (2)](https://rheodata.com/en-us/blog/tag/oracle-dba-skills-in-the-cloud) - [Oracle GoldenGate 23ai (2)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-23ai) - [Oracle migration assessment (2)](https://rheodata.com/en-us/blog/tag/oracle-migration-assessment) - [Oracle on GCP (2)](https://rheodata.com/en-us/blog/tag/oracle-on-gcp) - [Snowflake (2)](https://rheodata.com/en-us/blog/tag/snowflake) - [Snowflake cost optimization (2)](https://rheodata.com/en-us/blog/tag/snowflake-cost-optimization) - [aws (2)](https://rheodata.com/en-us/blog/tag/aws) - [azure ai studio (2)](https://rheodata.com/en-us/blog/tag/azure-ai-studio) - [build mysql heatwave (2)](https://rheodata.com/en-us/blog/tag/build-mysql-heatwave) - [cloud dba (2)](https://rheodata.com/en-us/blog/tag/cloud-dba) - [cloud ready (2)](https://rheodata.com/en-us/blog/tag/cloud-ready) - [cohere generate documentation (2)](https://rheodata.com/en-us/blog/tag/cohere-generate-documentation) - [data-pipeline (2)](https://rheodata.com/en-us/blog/tag/data-pipeline) - [database replication security (2)](https://rheodata.com/en-us/blog/tag/database-replication-security) - [deployment (2)](https://rheodata.com/en-us/blog/tag/deployment) - [docker adminclient (2)](https://rheodata.com/en-us/blog/tag/docker-adminclient) - [golden gate (2)](https://rheodata.com/en-us/blog/tag/golden-gate) - [goldengate cloud (2)](https://rheodata.com/en-us/blog/tag/goldengate-cloud) - [goldengate migrations (2)](https://rheodata.com/en-us/blog/tag/goldengate-migrations) - [goldengate parameter files (2)](https://rheodata.com/en-us/blog/tag/goldengate-parameter-files) - [google postgresql migration (2)](https://rheodata.com/en-us/blog/tag/google-postgresql-migration) - [ml (2)](https://rheodata.com/en-us/blog/tag/ml) - [real-time data replication (2)](https://rheodata.com/en-us/blog/tag/real-time-data-replication) - [0.12upgrade (1)](https://rheodata.com/en-us/blog/tag/0-12upgrade) - [11.2.0.4 (1)](https://rheodata.com/en-us/blog/tag/11-2-0-4) - [11g to 19c (1)](https://rheodata.com/en-us/blog/tag/11g-to-19c) - [11g to 21c (1)](https://rheodata.com/en-us/blog/tag/11g-to-21c) - [11g to 23c (1)](https://rheodata.com/en-us/blog/tag/11g-to-23c) - [11g to OCI (1)](https://rheodata.com/en-us/blog/tag/11g-to-oci) - [19.1.0.0.0 (1)](https://rheodata.com/en-us/blog/tag/19-1-0-0-0) - [19.1.0.0.1 (1)](https://rheodata.com/en-us/blog/tag/19-1-0-0-1) - [2024 (1)](https://rheodata.com/en-us/blog/tag/2024) - [5.7 (1)](https://rheodata.com/en-us/blog/tag/5-7) - [5.7 to 8.0 (1)](https://rheodata.com/en-us/blog/tag/5-7-to-8-0) - [8.0 (1)](https://rheodata.com/en-us/blog/tag/8-0) - [AI Agents (1)](https://rheodata.com/en-us/blog/tag/ai-agents) - [AI Data Platform (1)](https://rheodata.com/en-us/blog/tag/ai-data-platform) - [AI Infrastructure Management (1)](https://rheodata.com/en-us/blog/tag/ai-infrastructure-management) - [AI Machine Learning (1)](https://rheodata.com/en-us/blog/tag/ai-machine-learning) - [AI blog writing (1)](https://rheodata.com/en-us/blog/tag/ai-blog-writing) - [AI business productivity (1)](https://rheodata.com/en-us/blog/tag/ai-business-productivity) - [AI content creation (1)](https://rheodata.com/en-us/blog/tag/ai-content-creation) - [AI data infrastructure (1)](https://rheodata.com/en-us/blog/tag/ai-data-infrastructure) - [AI data management (1)](https://rheodata.com/en-us/blog/tag/ai-data-management) - [AI data platform optimization (1)](https://rheodata.com/en-us/blog/tag/ai-data-platform-optimization) - [AI database administration (1)](https://rheodata.com/en-us/blog/tag/ai-database-administration) - [AI database management tools (1)](https://rheodata.com/en-us/blog/tag/ai-database-management-tools) - [AI ethics content (1)](https://rheodata.com/en-us/blog/tag/ai-ethics-content) - [AI governance (1)](https://rheodata.com/en-us/blog/tag/ai-governance) - [AI inference bottlenecks (1)](https://rheodata.com/en-us/blog/tag/ai-inference-bottlenecks) - [AI model deployment strategies (1)](https://rheodata.com/en-us/blog/tag/ai-model-deployment-strategies) - [AI security (1)](https://rheodata.com/en-us/blog/tag/ai-security) - [AI writing tools (1)](https://rheodata.com/en-us/blog/tag/ai-writing-tools) - [AI-Driven-Revenue-Growth (1)](https://rheodata.com/en-us/blog/tag/ai-driven-revenue-growth) - [AI-Native Applications (1)](https://rheodata.com/en-us/blog/tag/ai-native-applications) - [AI-ROI (1)](https://rheodata.com/en-us/blog/tag/ai-roi) - [AI-Ready Data (1)](https://rheodata.com/en-us/blog/tag/ai-ready-data) - [AI-accuracy (1)](https://rheodata.com/en-us/blog/tag/ai-accuracy) - [AI-compliance (1)](https://rheodata.com/en-us/blog/tag/ai-compliance) - [AI-hallucination-prevention (1)](https://rheodata.com/en-us/blog/tag/ai-hallucination-prevention) - [AI-powered database replication management (1)](https://rheodata.com/en-us/blog/tag/ai-powered-database-replication-management) - [API authentication (1)](https://rheodata.com/en-us/blog/tag/api-authentication) - [AWS S3 (1)](https://rheodata.com/en-us/blog/tag/aws-s3) - [Apache Iceberg (1)](https://rheodata.com/en-us/blog/tag/apache-iceberg) - [Apache Spark data platform (1)](https://rheodata.com/en-us/blog/tag/apache-spark-data-platform) - [Atlanta database consultants (1)](https://rheodata.com/en-us/blog/tag/atlanta-database-consultants) - [Azure Data Lake (1)](https://rheodata.com/en-us/blog/tag/azure-data-lake) - [Big Query (1)](https://rheodata.com/en-us/blog/tag/big-query) - [BigQuery Integration (1)](https://rheodata.com/en-us/blog/tag/bigquery-integration) - [Business-Intelligence-Modernization (1)](https://rheodata.com/en-us/blog/tag/business-intelligence-modernization) - [CLOB to VARCHAR (1)](https://rheodata.com/en-us/blog/tag/clob-to-varchar) - [Change Data Capture GoldenGate Extract (1)](https://rheodata.com/en-us/blog/tag/change-data-capture-goldengate-extract) - [Cloud Data Platform (1)](https://rheodata.com/en-us/blog/tag/cloud-data-platform) - [Cloud database migration (1)](https://rheodata.com/en-us/blog/tag/cloud-database-migration) - [Coordinated Replicat (1)](https://rheodata.com/en-us/blog/tag/coordinated-replicat) - [Cortex Agents (1)](https://rheodata.com/en-us/blog/tag/cortex-agents) - [Cosine distance Oracle (1)](https://rheodata.com/en-us/blog/tag/cosine-distance-oracle) - [Cross-platform data monitoring (1)](https://rheodata.com/en-us/blog/tag/cross-platform-data-monitoring) - [Customer-Experience-Optimization (1)](https://rheodata.com/en-us/blog/tag/customer-experience-optimization) - [DBA burnout prevention (1)](https://rheodata.com/en-us/blog/tag/dba-burnout-prevention) - [DBA productivity (1)](https://rheodata.com/en-us/blog/tag/dba-productivity) - [DBA skills AI (1)](https://rheodata.com/en-us/blog/tag/dba-skills-ai) - [Data Modernization (1)](https://rheodata.com/en-us/blog/tag/data-modernization) - [Data Pipeline Architecture (1)](https://rheodata.com/en-us/blog/tag/data-pipeline-architecture) - [Data Pipeline Management (1)](https://rheodata.com/en-us/blog/tag/data-pipeline-management) - [Data Streaming (1)](https://rheodata.com/en-us/blog/tag/data-streaming) - [Data Transformation (1)](https://rheodata.com/en-us/blog/tag/data-transformation) - [Data pipeline troubleshooting (1)](https://rheodata.com/en-us/blog/tag/data-pipeline-troubleshooting) - [Database Security (1)](https://rheodata.com/en-us/blog/tag/database-security) - [Database lag monitoring (1)](https://rheodata.com/en-us/blog/tag/database-lag-monitoring) - [Database migration strategy (1)](https://rheodata.com/en-us/blog/tag/database-migration-strategy) - [Database migration vs. replication (1)](https://rheodata.com/en-us/blog/tag/database-migration-vs-replication) - [Database replication blind spots (1)](https://rheodata.com/en-us/blog/tag/database-replication-blind-spots) - [Database replication monitoring (1)](https://rheodata.com/en-us/blog/tag/database-replication-monitoring) - [Database replication performance monitoring (1)](https://rheodata.com/en-us/blog/tag/database-replication-performance-monitoring) - [Databricks comparison (1)](https://rheodata.com/en-us/blog/tag/databricks-comparison) - [Delta Lake integration (1)](https://rheodata.com/en-us/blog/tag/delta-lake-integration) - [Digital-Transformation-ROI (1)](https://rheodata.com/en-us/blog/tag/digital-transformation-roi) - [EXTFILE (1)](https://rheodata.com/en-us/blog/tag/extfile) - [EXTRAIL (1)](https://rheodata.com/en-us/blog/tag/extrail) - [Edge computing AI (1)](https://rheodata.com/en-us/blog/tag/edge-computing-ai) - [Enterprise AI Strategy (1)](https://rheodata.com/en-us/blog/tag/enterprise-ai-strategy) - [Enterprise AI scalability (1)](https://rheodata.com/en-us/blog/tag/enterprise-ai-scalability) - [Enterprise cloud migration (1)](https://rheodata.com/en-us/blog/tag/enterprise-cloud-migration) - [Enterprise data migration (1)](https://rheodata.com/en-us/blog/tag/enterprise-data-migration) - [Enterprise database replication monitoring (1)](https://rheodata.com/en-us/blog/tag/enterprise-database-replication-monitoring) - [Forward Deployed Engineering (1)](https://rheodata.com/en-us/blog/tag/forward-deployed-engineering) - [GPU memory optimization (1)](https://rheodata.com/en-us/blog/tag/gpu-memory-optimization) - [GUI (1)](https://rheodata.com/en-us/blog/tag/gui) - [Gemini Enterprise (1)](https://rheodata.com/en-us/blog/tag/gemini-enterprise) - [GoldenGate 21c upgrade (1)](https://rheodata.com/en-us/blog/tag/goldengate-21c-upgrade) - [GoldenGate 23ai to 26ai (1)](https://rheodata.com/en-us/blog/tag/goldengate-23ai-to-26ai) - [GoldenGate 26ai new features (1)](https://rheodata.com/en-us/blog/tag/goldengate-26ai-new-features) - [GoldenGate 26ai release notes (1)](https://rheodata.com/en-us/blog/tag/goldengate-26ai-release-notes) - [GoldenGate 26ai upgrade (1)](https://rheodata.com/en-us/blog/tag/goldengate-26ai-upgrade) - [GoldenGate AI integration (1)](https://rheodata.com/en-us/blog/tag/goldengate-ai-integration) - [GoldenGate CDC configuration (1)](https://rheodata.com/en-us/blog/tag/goldengate-cdc-configuration) - [GoldenGate DAA (1)](https://rheodata.com/en-us/blog/tag/goldengate-daa) - [GoldenGate Extract user permissions (1)](https://rheodata.com/en-us/blog/tag/goldengate-extract-user-permissions) - [GoldenGate Yugabyte support (1)](https://rheodata.com/en-us/blog/tag/goldengate-yugabyte-support) - [GoldenGate certificate authentication (1)](https://rheodata.com/en-us/blog/tag/goldengate-certificate-authentication) - [GoldenGate cutover planning (1)](https://rheodata.com/en-us/blog/tag/goldengate-cutover-planning) - [GoldenGate deployment automation (1)](https://rheodata.com/en-us/blog/tag/goldengate-deployment-automation) - [GoldenGate granular permissions setup (1)](https://rheodata.com/en-us/blog/tag/goldengate-granular-permissions-setup) - [GoldenGate least privilege security (1)](https://rheodata.com/en-us/blog/tag/goldengate-least-privilege-security) - [GoldenGate lifecycle management (1)](https://rheodata.com/en-us/blog/tag/goldengate-lifecycle-management) - [GoldenGate migration guide (1)](https://rheodata.com/en-us/blog/tag/goldengate-migration-guide) - [GoldenGate migration sizing (1)](https://rheodata.com/en-us/blog/tag/goldengate-migration-sizing) - [GoldenGate monitoring and lag management (1)](https://rheodata.com/en-us/blog/tag/goldengate-monitoring-and-lag-management) - [GoldenGate operational ownership (1)](https://rheodata.com/en-us/blog/tag/goldengate-operational-ownership) - [GoldenGate password management (1)](https://rheodata.com/en-us/blog/tag/goldengate-password-management) - [GoldenGate port configuration (1)](https://rheodata.com/en-us/blog/tag/goldengate-port-configuration) - [GoldenGate replication lag detection (1)](https://rheodata.com/en-us/blog/tag/goldengate-replication-lag-detection) - [GoldenGate response file (1)](https://rheodata.com/en-us/blog/tag/goldengate-response-file) - [GoldenGate trail file management (1)](https://rheodata.com/en-us/blog/tag/goldengate-trail-file-management) - [GoldenGate troubleshooting solutions (1)](https://rheodata.com/en-us/blog/tag/goldengate-troubleshooting-solutions) - [GoldenGate unified console (1)](https://rheodata.com/en-us/blog/tag/goldengate-unified-console) - [GoldenGateMCP (1)](https://rheodata.com/en-us/blog/tag/goldengatemcp) - [Google Cloud Platform (1)](https://rheodata.com/en-us/blog/tag/google-cloud-platform) - [Google Cloud Storage (1)](https://rheodata.com/en-us/blog/tag/google-cloud-storage) - [Google-AlloyDB (1)](https://rheodata.com/en-us/blog/tag/google-alloydb) - [HashiCorp (1)](https://rheodata.com/en-us/blog/tag/hashicorp) - [Hybrid queries Oracle (1)](https://rheodata.com/en-us/blog/tag/hybrid-queries-oracle) - [IT cost optimization (1)](https://rheodata.com/en-us/blog/tag/it-cost-optimization) - [IT infrastructure simplification (1)](https://rheodata.com/en-us/blog/tag/it-infrastructure-simplification) - [IT leadership mental health (1)](https://rheodata.com/en-us/blog/tag/it-leadership-mental-health) - [Initial Load (1)](https://rheodata.com/en-us/blog/tag/initial-load) - [Inventory management data lag (1)](https://rheodata.com/en-us/blog/tag/inventory-management-data-lag) - [LLM inference optimization (1)](https://rheodata.com/en-us/blog/tag/llm-inference-optimization) - [Large language model performance (1)](https://rheodata.com/en-us/blog/tag/large-language-model-performance) - [MCP Server for Oracle (1)](https://rheodata.com/en-us/blog/tag/mcp-server-for-oracle) - [MCP Server, (1)](https://rheodata.com/en-us/blog/tag/mcp-server) - [Mental Health Awareness Month tech industry (1)](https://rheodata.com/en-us/blog/tag/mental-health-awareness-month-tech-industry) - [Migration readiness (1)](https://rheodata.com/en-us/blog/tag/migration-readiness) - [Model Context Protocol (1)](https://rheodata.com/en-us/blog/tag/model-context-protocol) - [Model inference costs (1)](https://rheodata.com/en-us/blog/tag/model-inference-costs) - [OMA assessment (1)](https://rheodata.com/en-us/blog/tag/oma-assessment) - [ONNX embedding model Oracle (1)](https://rheodata.com/en-us/blog/tag/onnx-embedding-model-oracle) - [Operating Model (1)](https://rheodata.com/en-us/blog/tag/operating-model) - [Oracle 23ai features (1)](https://rheodata.com/en-us/blog/tag/oracle-23ai-features) - [Oracle 26ai features (1)](https://rheodata.com/en-us/blog/tag/oracle-26ai-features) - [Oracle AI Data Platform (1)](https://rheodata.com/en-us/blog/tag/oracle-ai-data-platform) - [Oracle AI Solutions (1)](https://rheodata.com/en-us/blog/tag/oracle-ai-solutions) - [Oracle Autonomous Database migration (1)](https://rheodata.com/en-us/blog/tag/oracle-autonomous-database-migration) - [Oracle CPAT vs OMA comparison (1)](https://rheodata.com/en-us/blog/tag/oracle-cpat-vs-oma-comparison) - [Oracle Database 23ai vectors (1)](https://rheodata.com/en-us/blog/tag/oracle-database-23ai-vectors) - [Oracle Database 26ai vectors (1)](https://rheodata.com/en-us/blog/tag/oracle-database-26ai-vectors) - [Oracle EBS migration (1)](https://rheodata.com/en-us/blog/tag/oracle-ebs-migration) - [Oracle Exadata on Google Cloud (1)](https://rheodata.com/en-us/blog/tag/oracle-exadata-on-google-cloud) - [Oracle GoldenGate 26ai (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-26ai) - [Oracle GoldenGate AI diagnostics (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-ai-diagnostics) - [Oracle GoldenGate Azure (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-azure) - [Oracle GoldenGate Management (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-management) - [Oracle GoldenGate REST API automation (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-rest-api-automation) - [Oracle GoldenGate SQL Server permissions (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-sql-server-permissions) - [Oracle GoldenGate automation (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-automation) - [Oracle GoldenGate heartbeat (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-heartbeat) - [Oracle GoldenGate least privilege security (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-least-privilege-security) - [Oracle GoldenGate managed services (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-managed-services) - [Oracle GoldenGate migration strategy (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-migration-strategy) - [Oracle GoldenGate monitoring tools (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-monitoring-tools) - [Oracle GoldenGate replication best practices (1)](https://rheodata.com/en-us/blog/tag/oracle-goldengate-replication-best-practices) - [Oracle and Google Cloud AI (1)](https://rheodata.com/en-us/blog/tag/oracle-and-google-cloud-ai) - [Oracle cloud cost optimization (1)](https://rheodata.com/en-us/blog/tag/oracle-cloud-cost-optimization) - [Oracle cloud migration assessment (1)](https://rheodata.com/en-us/blog/tag/oracle-cloud-migration-assessment) - [Oracle data replication 2026 (1)](https://rheodata.com/en-us/blog/tag/oracle-data-replication-2026) - [Oracle data replication compliance (1)](https://rheodata.com/en-us/blog/tag/oracle-data-replication-compliance) - [Oracle database migration to OCI (1)](https://rheodata.com/en-us/blog/tag/oracle-database-migration-to-oci) - [Oracle replication governance (1)](https://rheodata.com/en-us/blog/tag/oracle-replication-governance) - [Oracle replication lag diagnosis (1)](https://rheodata.com/en-us/blog/tag/oracle-replication-lag-diagnosis) - [Oracle to cloud migration (1)](https://rheodata.com/en-us/blog/tag/oracle-to-cloud-migration) - [Oracle vs Databricks (1)](https://rheodata.com/en-us/blog/tag/oracle-vs-databricks) - [Oracle workload analysis (1)](https://rheodata.com/en-us/blog/tag/oracle-workload-analysis) - [Oracle@Google Cloud (1)](https://rheodata.com/en-us/blog/tag/oraclegoogle-cloud) - [Parallel Replicat (1)](https://rheodata.com/en-us/blog/tag/parallel-replicat) - [Parquet (1)](https://rheodata.com/en-us/blog/tag/parquet) - [RAG pipeline database (1)](https://rheodata.com/en-us/blog/tag/rag-pipeline-database) - [REST API (1)](https://rheodata.com/en-us/blog/tag/rest-api) - [Real-time AI processing (1)](https://rheodata.com/en-us/blog/tag/real-time-ai-processing) - [SQL Server replication security best practices (1)](https://rheodata.com/en-us/blog/tag/sql-server-replication-security-best-practices) - [Semantic search database (1)](https://rheodata.com/en-us/blog/tag/semantic-search-database) - [Similarity search Oracle (1)](https://rheodata.com/en-us/blog/tag/similarity-search-oracle) - [Snowflake Optima indexing (1)](https://rheodata.com/en-us/blog/tag/snowflake-optima-indexing) - [Snowflake Search Optimization Service (1)](https://rheodata.com/en-us/blog/tag/snowflake-search-optimization-service) - [Snowflake alternatives (1)](https://rheodata.com/en-us/blog/tag/snowflake-alternatives) - [Snowflake automatic clustering (1)](https://rheodata.com/en-us/blog/tag/snowflake-automatic-clustering) - [Snowflake budget monitoring (1)](https://rheodata.com/en-us/blog/tag/snowflake-budget-monitoring) - [Snowflake cloud data warehouse performance (1)](https://rheodata.com/en-us/blog/tag/snowflake-cloud-data-warehouse-performance) - [Snowflake cost governance (1)](https://rheodata.com/en-us/blog/tag/snowflake-cost-governance) - [Snowflake cost management (1)](https://rheodata.com/en-us/blog/tag/snowflake-cost-management) - [Snowflake cost reduction strategies (1)](https://rheodata.com/en-us/blog/tag/snowflake-cost-reduction-strategies) - [Snowflake credit usage (1)](https://rheodata.com/en-us/blog/tag/snowflake-credit-usage) - [Snowflake materialized views (1)](https://rheodata.com/en-us/blog/tag/snowflake-materialized-views) - [Snowflake migration staffing (1)](https://rheodata.com/en-us/blog/tag/snowflake-migration-staffing) - [Snowflake performance optimization (1)](https://rheodata.com/en-us/blog/tag/snowflake-performance-optimization) - [Snowflake query acceleration service (1)](https://rheodata.com/en-us/blog/tag/snowflake-query-acceleration-service) - [Snowflake query performance tuning (1)](https://rheodata.com/en-us/blog/tag/snowflake-query-performance-tuning) - [Snowflake resource monitors (1)](https://rheodata.com/en-us/blog/tag/snowflake-resource-monitors) - [Snowflake serverless compute costs (1)](https://rheodata.com/en-us/blog/tag/snowflake-serverless-compute-costs) - [Snowflake spend attribution (1)](https://rheodata.com/en-us/blog/tag/snowflake-spend-attribution) - [Snowflake warehouse optimization (1)](https://rheodata.com/en-us/blog/tag/snowflake-warehouse-optimization) - [Snowflake warehouse right-sizing (1)](https://rheodata.com/en-us/blog/tag/snowflake-warehouse-right-sizing) - [Token generation latency (1)](https://rheodata.com/en-us/blog/tag/token-generation-latency) - [VECTOR datatype Oracle (1)](https://rheodata.com/en-us/blog/tag/vector-datatype-oracle) - [VECTOR\_DISTANCE function (1)](https://rheodata.com/en-us/blog/tag/vector_distance-function) - [Vector embeddings Oracle (1)](https://rheodata.com/en-us/blog/tag/vector-embeddings-oracle) - [What's new GoldenGate 26ai (1)](https://rheodata.com/en-us/blog/tag/whats-new-goldengate-26ai) - [access control (1)](https://rheodata.com/en-us/blog/tag/access-control) - [activepass (1)](https://rheodata.com/en-us/blog/tag/activepass) - [adb (1)](https://rheodata.com/en-us/blog/tag/adb) - [add (1)](https://rheodata.com/en-us/blog/tag/add) - [add credentials (1)](https://rheodata.com/en-us/blog/tag/add-credentials) - [adminclient add credentials (1)](https://rheodata.com/en-us/blog/tag/adminclient-add-credentials) - [administration (1)](https://rheodata.com/en-us/blog/tag/administration) - [adw (1)](https://rheodata.com/en-us/blog/tag/adw) - [ai failures 2024 (1)](https://rheodata.com/en-us/blog/tag/ai-failures-2024) - [ai stratgies (1)](https://rheodata.com/en-us/blog/tag/ai-stratgies) - [ai-architecture (1)](https://rheodata.com/en-us/blog/tag/ai-architecture) - [all or nothing (1)](https://rheodata.com/en-us/blog/tag/all-or-nothing) - [allowPublicKeyRetrieval (1)](https://rheodata.com/en-us/blog/tag/allowpublickeyretrieval) - [alloydb (1)](https://rheodata.com/en-us/blog/tag/alloydb) - [alter extract 21c (1)](https://rheodata.com/en-us/blog/tag/alter-extract-21c) - [amazon (1)](https://rheodata.com/en-us/blog/tag/amazon) - [ansible (1)](https://rheodata.com/en-us/blog/tag/ansible) - [approximate-nearest-neighbor (1)](https://rheodata.com/en-us/blog/tag/approximate-nearest-neighbor) - [automl (1)](https://rheodata.com/en-us/blog/tag/automl) - [azure-cloud (1)](https://rheodata.com/en-us/blog/tag/azure-cloud) - [azure-native (1)](https://rheodata.com/en-us/blog/tag/azure-native) - [bastion (1)](https://rheodata.com/en-us/blog/tag/bastion) - [bastion host configuartion (1)](https://rheodata.com/en-us/blog/tag/bastion-host-configuartion) - [bastion setup oracle (1)](https://rheodata.com/en-us/blog/tag/bastion-setup-oracle) - [bug 30193036 (1)](https://rheodata.com/en-us/blog/tag/bug-30193036) - [bugs (1)](https://rheodata.com/en-us/blog/tag/bugs) - [build a compute node in oci (1)](https://rheodata.com/en-us/blog/tag/build-a-compute-node-in-oci) - [business-continuity (1)](https://rheodata.com/en-us/blog/tag/business-continuity) - [certificate-based authentication (1)](https://rheodata.com/en-us/blog/tag/certificate-based-authentication) - [change data capture (1)](https://rheodata.com/en-us/blog/tag/change-data-capture) - [changing ssh keys (1)](https://rheodata.com/en-us/blog/tag/changing-ssh-keys) - [channels (1)](https://rheodata.com/en-us/blog/tag/channels) - [cloud cost control (1)](https://rheodata.com/en-us/blog/tag/cloud-cost-control) - [cloud data platform cost control (1)](https://rheodata.com/en-us/blog/tag/cloud-data-platform-cost-control) - [cloud migration readiness assessment (1)](https://rheodata.com/en-us/blog/tag/cloud-migration-readiness-assessment) - [cloud-database-setup (1)](https://rheodata.com/en-us/blog/tag/cloud-database-setup) - [cloud-sql-migration (1)](https://rheodata.com/en-us/blog/tag/cloud-sql-migration) - [cloud-strategy (1)](https://rheodata.com/en-us/blog/tag/cloud-strategy) - [cohere command (1)](https://rheodata.com/en-us/blog/tag/cohere-command) - [compute (1)](https://rheodata.com/en-us/blog/tag/compute) - [compute portability (1)](https://rheodata.com/en-us/blog/tag/compute-portability) - [compute-instance (1)](https://rheodata.com/en-us/blog/tag/compute-instance) - [connect to database via bastion host (1)](https://rheodata.com/en-us/blog/tag/connect-to-database-via-bastion-host) - [connect to database via bastion host oci (1)](https://rheodata.com/en-us/blog/tag/connect-to-database-via-bastion-host-oci) - [consultants (1)](https://rheodata.com/en-us/blog/tag/consultants) - [content strategy (1)](https://rheodata.com/en-us/blog/tag/content-strategy) - [cost-optimization (1)](https://rheodata.com/en-us/blog/tag/cost-optimization) - [cryptographic authentication (1)](https://rheodata.com/en-us/blog/tag/cryptographic-authentication) - [curl (1)](https://rheodata.com/en-us/blog/tag/curl) - [daemon (1)](https://rheodata.com/en-us/blog/tag/daemon) - [data encryption (1)](https://rheodata.com/en-us/blog/tag/data-encryption) - [data fabric (1)](https://rheodata.com/en-us/blog/tag/data-fabric) - [data governance framework (1)](https://rheodata.com/en-us/blog/tag/data-governance-framework) - [data lake architecture (1)](https://rheodata.com/en-us/blog/tag/data-lake-architecture) - [data lakehouse platform (1)](https://rheodata.com/en-us/blog/tag/data-lakehouse-platform) - [data pipeline security (1)](https://rheodata.com/en-us/blog/tag/data-pipeline-security) - [data platform selection (1)](https://rheodata.com/en-us/blog/tag/data-platform-selection) - [data team workload management (1)](https://rheodata.com/en-us/blog/tag/data-team-workload-management) - [database AI transformation (1)](https://rheodata.com/en-us/blog/tag/database-ai-transformation) - [database administrators (1)](https://rheodata.com/en-us/blog/tag/database-administrators) - [database capacity planning tools (1)](https://rheodata.com/en-us/blog/tag/database-capacity-planning-tools) - [database certificate authentication (1)](https://rheodata.com/en-us/blog/tag/database-certificate-authentication) - [database compliance audit replication (1)](https://rheodata.com/en-us/blog/tag/database-compliance-audit-replication) - [database consolidation strategy (1)](https://rheodata.com/en-us/blog/tag/database-consolidation-strategy) - [database credential management (1)](https://rheodata.com/en-us/blog/tag/database-credential-management) - [database migration planning tools (1)](https://rheodata.com/en-us/blog/tag/database-migration-planning-tools) - [database modernization AI (1)](https://rheodata.com/en-us/blog/tag/database-modernization-ai) - [database replication management (1)](https://rheodata.com/en-us/blog/tag/database-replication-management) - [database transformation consulting (1)](https://rheodata.com/en-us/blog/tag/database-transformation-consulting) - [database-failover (1)](https://rheodata.com/en-us/blog/tag/database-failover) - [database-vectors (1)](https://rheodata.com/en-us/blog/tag/database-vectors) - [db\_owner risk SQL Server replication (1)](https://rheodata.com/en-us/blog/tag/db_owner-risk-sql-server-replication) - [dba\_capture (1)](https://rheodata.com/en-us/blog/tag/dba_capture) - [dba\_queues (1)](https://rheodata.com/en-us/blog/tag/dba_queues) - [dbms\_aqadm.drop\_queue\_table (1)](https://rheodata.com/en-us/blog/tag/dbms_aqadm-drop_queue_table) - [dbms\_comparison (1)](https://rheodata.com/en-us/blog/tag/dbms_comparison) - [ddl (1)](https://rheodata.com/en-us/blog/tag/ddl) - [direct initial load (1)](https://rheodata.com/en-us/blog/tag/direct-initial-load) - [dml (1)](https://rheodata.com/en-us/blog/tag/dml) - [docker goldengate (1)](https://rheodata.com/en-us/blog/tag/docker-goldengate) - [docker images (1)](https://rheodata.com/en-us/blog/tag/docker-images) - [dynamic (1)](https://rheodata.com/en-us/blog/tag/dynamic) - [edb database (1)](https://rheodata.com/en-us/blog/tag/edb-database) - [elephant database (1)](https://rheodata.com/en-us/blog/tag/elephant-database) - [eliminate database password authentication (1)](https://rheodata.com/en-us/blog/tag/eliminate-database-password-authentication) - [emd360 (1)](https://rheodata.com/en-us/blog/tag/emd360) - [enable ddl (1)](https://rheodata.com/en-us/blog/tag/enable-ddl) - [enterprise (1)](https://rheodata.com/en-us/blog/tag/enterprise) - [enterprise AI (1)](https://rheodata.com/en-us/blog/tag/enterprise-ai) - [enterprise AI implementation (1)](https://rheodata.com/en-us/blog/tag/enterprise-ai-implementation) - [enterprise AI infrastructure (1)](https://rheodata.com/en-us/blog/tag/enterprise-ai-infrastructure) - [enterprise data governance (1)](https://rheodata.com/en-us/blog/tag/enterprise-data-governance) - [enterprise data integration (1)](https://rheodata.com/en-us/blog/tag/enterprise-data-integration) - [enterprise data strategy (1)](https://rheodata.com/en-us/blog/tag/enterprise-data-strategy) - [enterprise goldengate backup solution (1)](https://rheodata.com/en-us/blog/tag/enterprise-goldengate-backup-solution) - [enterprise manager (1)](https://rheodata.com/en-us/blog/tag/enterprise-manager) - [exception handling (1)](https://rheodata.com/en-us/blog/tag/exception-handling) - [experts in oracle goldengate (1)](https://rheodata.com/en-us/blog/tag/experts-in-oracle-goldengate) - [extract changes (1)](https://rheodata.com/en-us/blog/tag/extract-changes) - [extract load transform (1)](https://rheodata.com/en-us/blog/tag/extract-load-transform) - [extract transform load (1)](https://rheodata.com/en-us/blog/tag/extract-transform-load) - [failures (1)](https://rheodata.com/en-us/blog/tag/failures) - [fintech postgreSQL (1)](https://rheodata.com/en-us/blog/tag/fintech-postgresql) - [firewalld goldengate (1)](https://rheodata.com/en-us/blog/tag/firewalld-goldengate) - [firewalld microservices (1)](https://rheodata.com/en-us/blog/tag/firewalld-microservices) - [fivetran (1)](https://rheodata.com/en-us/blog/tag/fivetran) - [framework (1)](https://rheodata.com/en-us/blog/tag/framework) - [frameworks (1)](https://rheodata.com/en-us/blog/tag/frameworks) - [free tools (1)](https://rheodata.com/en-us/blog/tag/free-tools) - [fresh data (1)](https://rheodata.com/en-us/blog/tag/fresh-data) - [gemini (1)](https://rheodata.com/en-us/blog/tag/gemini) - [genai (1)](https://rheodata.com/en-us/blog/tag/genai) - [general information (1)](https://rheodata.com/en-us/blog/tag/general-information) - [ggsci (1)](https://rheodata.com/en-us/blog/tag/ggsci) - [ggsmon (1)](https://rheodata.com/en-us/blog/tag/ggsmon) - [goldengate active passive (1)](https://rheodata.com/en-us/blog/tag/goldengate-active-passive) - [goldengate backup automation (1)](https://rheodata.com/en-us/blog/tag/goldengate-backup-automation) - [goldengate bug (1)](https://rheodata.com/en-us/blog/tag/goldengate-bug) - [goldengate errors (1)](https://rheodata.com/en-us/blog/tag/goldengate-errors) - [goldengate experts (1)](https://rheodata.com/en-us/blog/tag/goldengate-experts) - [goldengate free (1)](https://rheodata.com/en-us/blog/tag/goldengate-free) - [goldengate github integration (1)](https://rheodata.com/en-us/blog/tag/goldengate-github-integration) - [goldengate high availiability (1)](https://rheodata.com/en-us/blog/tag/goldengate-high-availiability) - [goldengate maa (1)](https://rheodata.com/en-us/blog/tag/goldengate-maa) - [goldengate microservices port (1)](https://rheodata.com/en-us/blog/tag/goldengate-microservices-port) - [goldengate microservices ports (1)](https://rheodata.com/en-us/blog/tag/goldengate-microservices-ports) - [goldengate ogg-02028 (1)](https://rheodata.com/en-us/blog/tag/goldengate-ogg-02028) - [goldengate parameter file backup (1)](https://rheodata.com/en-us/blog/tag/goldengate-parameter-file-backup) - [google cloudsql (1)](https://rheodata.com/en-us/blog/tag/google-cloudsql) - [google mysql migration (1)](https://rheodata.com/en-us/blog/tag/google-mysql-migration) - [heatwave experts (1)](https://rheodata.com/en-us/blog/tag/heatwave-experts) - [high performance mysql (1)](https://rheodata.com/en-us/blog/tag/high-performance-mysql) - [human creativity AI (1)](https://rheodata.com/en-us/blog/tag/human-creativity-ai) - [human vs AI writing (1)](https://rheodata.com/en-us/blog/tag/human-vs-ai-writing) - [hybrid cloud data architecture (1)](https://rheodata.com/en-us/blog/tag/hybrid-cloud-data-architecture) - [integrated extract oracle (1)](https://rheodata.com/en-us/blog/tag/integrated-extract-oracle) - [integrated replicat oracle (1)](https://rheodata.com/en-us/blog/tag/integrated-replicat-oracle) - [lic (1)](https://rheodata.com/en-us/blog/tag/lic) - [license (1)](https://rheodata.com/en-us/blog/tag/license) - [logmnr\_session$ (1)](https://rheodata.com/en-us/blog/tag/logmnr_session) - [managed service provider (1)](https://rheodata.com/en-us/blog/tag/managed-service-provider) - [managed services for database teams (1)](https://rheodata.com/en-us/blog/tag/managed-services-for-database-teams) - [management (1)](https://rheodata.com/en-us/blog/tag/management) - [migration compatibility validation (1)](https://rheodata.com/en-us/blog/tag/migration-compatibility-validation) - [monitor oracle goldengate rest api (1)](https://rheodata.com/en-us/blog/tag/monitor-oracle-goldengate-rest-api) - [monolithic database architecture (1)](https://rheodata.com/en-us/blog/tag/monolithic-database-architecture) - [move off of oracle (1)](https://rheodata.com/en-us/blog/tag/move-off-of-oracle) - [multi-cloud data platform (1)](https://rheodata.com/en-us/blog/tag/multi-cloud-data-platform) - [oci bastion (1)](https://rheodata.com/en-us/blog/tag/oci-bastion) - [oem emd360 (1)](https://rheodata.com/en-us/blog/tag/oem-emd360) - [ogg deployments (1)](https://rheodata.com/en-us/blog/tag/ogg-deployments) - [open table format (1)](https://rheodata.com/en-us/blog/tag/open-table-format) - [oracle database (1)](https://rheodata.com/en-us/blog/tag/oracle-database) - [preventing tech employee attrition (1)](https://rheodata.com/en-us/blog/tag/preventing-tech-employee-attrition) - [reducing on-call burnout (1)](https://rheodata.com/en-us/blog/tag/reducing-on-call-burnout) - [securing Oracle GoldenGate on SQL Server (1)](https://rheodata.com/en-us/blog/tag/securing-oracle-goldengate-on-sql-server) - [tech team burnout (1)](https://rheodata.com/en-us/blog/tag/tech-team-burnout) - [thought leadership (1)](https://rheodata.com/en-us/blog/tag/thought-leadership) - [vector database consolidation (1)](https://rheodata.com/en-us/blog/tag/vector-database-consolidation) See all - - [1](https://rheodata.com/en-us/blog) - [2](https://rheodata.com/en-us/blog/tag/ai/page/2) - [3](https://rheodata.com/en-us/blog/tag/ai/page/3) - [4](https://rheodata.com/en-us/blog/tag/ai/page/4) - ##### About RheoData RheoData is based out of Metro Atlanta, GA and provide expert Oracle, Microsoft, Google, and Snowflake services.  Let us  know how we can help! ##### Links - [About Us](https://rheodata.com/who-we-are) - [FrostCore](https://rheodata.com/frostcore) - [RedCore](https://rheodata.com/redcore) - [BlueCore](https://rheodata.com/bluecore) ##### Contact us [hello@rheodata.com](mailto:hello@rheodata.com) ©RheoData2026. All Rights Reserved. ```json { "@context" : "https://schema.org", "@type" : "Organization", "address" : { "@type" : "PostalAddress", "addressCountry" : "US", "addressRegion" : "GA" }, "description" : "Elite specialist partner for Oracle, Snowflake, BigQuery, and AI-ready data platforms.", "email" : "hello@rheodata.com", "foundingDate" : "2020", "logo" : "https://rheodata.com/hubfs/RheoData%20-%20Logo%20-%20transparent-1.png", "name" : "RheoData", "sameAs" : [ "https://www.linkedin.com/company/rheodata" ], "url" : "https://rheodata.com" } ``` ```json { "@context" : "https://schema.org", "@type" : "WebSite", "name" : "RheoData", "potentialAction" : { "@type" : "SearchAction", "query-input" : "required name=search_term_string", "target" : "https://rheodata.com/search?q={search_term_string}" }, "url" : "https://rheodata.com" } ``` ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "", "url" : "" }, "dateModified" : "2026-04-17T17:31:04+0000", "datePublished" : "2025-10-30T17:41:53+0000", "description" : "AI | RheoData Blog Posts", "headline" : "<span id="hs_cos_wrapper_name" class="hs_cos_wrapper hs_cos_wrapper_meta_field hs_cos_wrapper_type_text" style="" data-hs-cos-general-type="meta_field" data-hs-cos-type="text" >rheodata_blog listing page</span>", "image" : "", "mainEntityOfPage" : { "@id" : "https://rheodata.com/en-us/blog/tag/ai", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://rheodata.com/hubfs/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "This post we are going to look at some items related to getting started with Generative AI. This is mostly related to how I got started looking at GenAI and what I presented this year at the Rocky Mountain Open User Group (RMOUG). The presentation that I presented on provided details on what you should look forward and understand when talking about GenAI. I broke this topic down into three distinct sections: Artificial Intelligence How you can get started Possibilities Now, I cannot go into all the details of these section in this blog post, but there was a lot of good information handed out during this session. Artificial Intelligence Many people didn’t realize that the concept and terms related to Artificial Intelligence has been out since the Birth of AI (1950–1956). It has gone through many different stages to reach where it is now with General AI (2012-Present). The image below shows a rough timeline on what these stages have been and were: Over the last two years, AI has exploaded across every industry. Yet, many don’t see how and where AI is being used within their everyday spectrum. AI has be placed in every type of application you can think of. Microsoft has place in their productivity suite with the release of Copilot ($$/user/mo). Google has done the same thing with Gemini in Google Workspace (included in cost based on package). Oracle has embedded AI into its products, mostly applications, but leverage Cohere to do this. Apple was one of the first out with “siri” as a digital assistant, which many use today. There are many different ways that AI is being used within our every day lives, yet so many do not realize it. As you can see, AI is or can be built into any thing that is useful. How do you get started? There are four basic things needed in order to get started. During the presentation I talked about these four items in terms of personal growth. After all, that is what you need to move forward if you really want to understand AI. These four things that you need in order to understand AI, at a deeper layers is: A desire to learn Reading a lot of documentation, I mean a lot. A set of tools Large Language Models (LLM) A desire to learn With AI being such a new thing to many, although it has been around for 75 years, getting a good understanding of what AI is and how it can be useful is key. This, in my opinion, can only be done if you have a desire to learn and be uncomfortable for a short period of time. Many vendors out there, Microsoft, Google, and Oracle, are trying to make it easier for you. Yet at the same time, if you only know the top layer, you’ll never know how it truly works. You need to spend time digging deep into the topic. Which brings you to the next bullet point: Documentation All of the AI providers provide a lot of documentation. So much that is is confusing when you first start digging into them. For Microsoft, you need to read the OpenAI docs. For Oracle, Cohere. For Goolge, Gemini. I’ll let you in on a little secret thought, they are all pretty much the same. If you can learn one, you can learn all of them. Additionally, the concepts bleed over into the just about every GUI interface provided with vendors. The concept of “notebooks” which is referenced a lot if really just a development platform to introduce AI through python concepts. Keep reading. Keep writing. The read some more. Tools When it comes to tools, there are a lot of tools on the market that you can use. The hyperscalers provide tools through their cloud platform interfaces. There are third party tools like pycharm or VSCode that are good for writing python code to interact with AIs. Many of the AIs provide Application Programming Interfaces (APIs) that allow you to interact with the AI or tie external applications into the AI. These are very powerful approaches to making AI do some cool stuff. Lastly, the ability to just talk to AI in “natural language” makes the concepts even more intergruging to use. Who doesn’t like just being able to ask a question and get an answer back? Large Language Models (LLMs) The last tool you should know about are Large Language Models (LLMs). Many hear the term but don’t quite understand it. LLMs are models that are trained on a per-determined set of data. Some models are smaller than others, while the larger ones are trained on millions if not billions of tokens. What is a token? The term token has been explained in multiple ways. Some people think a token is a single “word” or “phrase” that is given and retured by the LLM. The best explination I’ve heard and made sense was by provided Google. A “token” is a “character and a half”. Is that actually correct? Not sure, but it makes sense when you start looking at the cost factor of running your queries against an LLM. Concepts With all the items listed in the previous section, there are concepts that have to be understood as well. These concepts are: Fine-Tuning Embedding Grounding Understanding these concepts, you’ll be able to start development some LLMs that make sense for you to use and build from. Fine-Tuning This is the process of “teaching” the LLM what you want it to know. This is like a student learning a specialized task to make their job easier. In order to tune an LLM, you would need to provide it a JSONL document that consists of a conversation like input, with questions and answers. Then the LLM can learn and you can ask it generalized questions around the topic it was trained on. The JSONL document that you provided should follow the 80/20 rule. 80% of the questions are used to train the LLM while the last 20% of of the questions are reserved to validate the training. Embedding Embedding is another concept; however, it makes a lot of sense when you are building applications like Vector Searches. The embedding process uses a specialized LLM that will convert your unstructured data into a “vector” that is stored in a database. Then this information is used to retrieve data based on “semantic” search. What does this mean? It means that your input is converted to a “vector” string and then compared to the “vector” stored in the database. All records returned, following a mathematical equation, are within a given range of the vector. This is known as the “top-K” approach. Grounding Grounding is the approach of providing relavant information to the LLM without training. It is an approach to elevate the halluination of the LLM when returning results. This approach is also known a “Retrieval Augmented Generation (RAG)”. By grounding an LLM, you care ensuing the context of the results are what is needed for the question being asked. The also leads you into the concept of “specialized” LLMs. An LLM becomes specialized when you train the LLM for a specific task and then provide context with external data sources. Agents Agents are the next evolution of the AI ecosystem. Although the General AI approach has only been around for two years, agents came about very quickly. Agents are autonomous entities that leverage AI to perfrom tasks. Some agents perform single tasks while some provide mulitiple tasks. At the same time, agents are goal-oriented and capable of making decisions on their own. Additionally, they can interact with other agents within their environments or outside their environments. Some of the most common agents are chatbots, virtual assistants, or gaming characters. AI Swarms This is a new concept that has been around for about six-months. The concept of a “swarm” is the ability to have an agent manage multiple agents. This greats a “swarm” of agents that can be interacted with and provide services — enabling a “hive mind” approach between the agents. Using AI swarms increase efficiency and effectivness through collabrative problem-solving. Yes, to be effective, it requires careful management of communication and coordination between agents. Summary In this post, I walked you through what I looked at when I was getting stared with GenAI. I provided highlights of all the concepts needed to build and use an AI/LLM. Lastly, I provided minor details on Agents and AI Swarms which are fairly new to the AI ecosystem and are forcing many to start looking at AI different.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "GenAI: How to get started", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/AdobeStock_335969170-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/genai-getstarted", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "In my last two posts I showed you what the Oracle Vector Datatype is and how to update existing data after adding a vector datatype column. In this post, we are going to quickly look at how to use those examples to implement a “similarity search” based on the vector stored in the vg_vec1 column of the table. Assumptions The prerequisites for this should be pretty straight forward, but I’ll make note of them here for reference. Oracle Database 23.4 (limited availability at the moment) python3.11 or later (what I’m using non-venv setup) python_oracledb (2.0.0 or later (limited availability)) LLM API Key (Using Cohere) With the prerequisites defined and ready to use, lets take a look at the code need implement a “similarity search” on top of the video game data stored in vector.video_games_vec. If we do a quick query of vector.video_games_vec table, we see that vectors are in place for every row of the table. SQL> select id, title, vg_vec1 from VECTOR.VIDEO_GAMES_VEC order by id; With vectors in place, we now need to write some code that will compare the data in column vg_vec1 with a search term or question we are looking for. Python First we need to import the packages and define the LLM API key we need for python: #! /usr/local/bin/python3 import oracledb import cohere import os import sys import array #set Cohere API key api_key = “eOubN0Yyj8ORoDk6MYjr co = cohere.Client(api_key) As you can tell, we are importing the new oracledb package for python along with the package for cohere. The other packages are needed and are already installed with python. Within the same section, we are defining the API Key that is needed to run embeddings against Cohere. Next, we are setting up a few definitions/functions for the process. I broke these into functions that partition what is happening with the script. There are two functions that we are going to define – database connection and vectorization. Within the database connection function, we are simply making a call to connect to the database and return the connection for usage within the script. If connection cannot be made, then the connection is not returned. #define database connection function def database_connection():   try:       connection = oracledb.connect(           user=”,           password=”,           dsn=100.166.255.254:1521/”           )       print('connected’)       return connection   except:         print('Could not make a connection’) The next function is used to create embedding for the search term or question that we are looking for in the “similarity search”. Breaking this out into a function helps simplify the code and relegates the vectorization to a single step. Then the vector array of embeddings are retuned for further processing. #define LLM embedding model def cohere_vectorize(vInput):   data = vInput   response = co.embed(       texts=[data],       model='embed-english-light-v3.0’,       input_type=“search_query       )   vector_value = response.embeddings[0]     return vector_value Lastly, we create a function called main(). This is just to compartmentalize main code into a single spot. Something, I like to do from time to time. Within the main function is where all the work is done for the “similarity search”. We setup the connection to the database, the select statement that is going to be used, and what to do with the search. def main():     connection = database_connection()   with connection.cursor() as select_cursor:       select_stmt = select title, genres, license                       from vector.video_games_vec                       order by vector_distance(vg_vec1, :1, DOT)                       fetch first :2 rows only”         while True:           prompt_input = input('Search Games or Game Question: ‘)           if (prompt_input == exit”):                 break           if (prompt_input == ”):                 continue             fetch_num = input(How many records to fetch: “)           vec = cohere_vectorize(prompt_input)             vec2 = array.array(d, vec)           for(title, genres, license) in select_cursor.execute(select_stmt, [vec2, fetch_num]):                 print(\t + title + | + genres + | + license) A couple of things to understand about the code above. The select _stmt parameter defines the select statement that is used to query the database table and return a result set based on the vectors. Within this select statement, we are using vector_distance to compare two vectors – stored vector and new embedding vector for search. Then the algorithm used for the search – DOT. All this is done in the order by clause. Additionally, the query is limiting the results based on the first number or rows fetched. To give a better view of this query, it looks like this: select title, genres, license from vector.video_games_vec order by vector_distance(vg_vec1, :1, DOT) fetch first :2 rows only You will notice that we are using :1 and :2 within the SQL statement. These are used by the cursor.execute function in python to pass values. Another thing to point out is that the returned embedding needs to be converted to a format that can be used by SQL. This is done by taking the embedding and converting it to a FLOAT64 value. This is done with the line in the main function as: vec2 = arrary.array(“d”, vec) Seems trivial, but is needed for the search to work. Lastly, we simply make a call to the main function for execution. Once execute, we can provide our search term or question related to a video game and get information back on the video game. Note: One thing to note, the for loop in the main function that executes the select statement needs to be updated if more columns are added to the select statement. Look at the below video, you will see that we are searching for various video games and looking to get the name of the video game, the genre it belongs in, and if it requires a license. The output is prefixed with a tab and broken up with pipe symbols. See this simple vector search in action: here When it comes down to the effectiveness of the search, it will be based on the quality of your data. If you have clean data, then your searches will be more efficient and yield better results.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Similarity Search with Oracle’s Vector Datatype", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/similarity_search_oracle_vector_datatype-1024x640-1.png", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/similarity-search-oracle-vector-datatype", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "Retrieval Augmented Generation (RAG) represents a significant advancement in natural language processing that addresses fundamental limitations in static language models. By combining the generative capabilities of large language models with dynamic information retrieval systems, RAG enables AI systems to access and incorporate external knowledge during inference, resulting in more accurate, current, and verifiable outputs. This architectural approach is particularly valuable in domains where knowledge evolves rapidly or where access to proprietary datasets is essential. RAG systems demonstrate superior performance in reducing confabulation rates while maintaining the fluency and coherence expected from modern language models. What We’ll Be Covering What is Retrieval-Augmented Generation? What are the Benefits of RAG? How Does RAG Work? When to Use RAG Over Retraining and Fine-Tuning Common Use Cases for RAG Implementing Retrieval-Augmented Generation Conclusion What is Retrieval-Augmented Generation? Retrieval Augmented Generation is an architectural pattern that enhances language model outputs by incorporating external knowledge retrieval during the generation process. Unlike traditional language models that rely solely on parametric knowledge encoded during training, RAG systems maintain a dynamic connection to external knowledge bases, enabling real-time information access and integration. The RAG architecture operates through a two-stage process: Retrieval Stage: A query-driven search mechanism identifies and extracts relevant information from external sources Generation Stage: The language model synthesizes retrieved information with its parametric knowledge to produce contextually appropriate responses This dual-stage approach significantly improves output accuracy and reduces hallucination rates – instances where models generate plausible but factually incorrect information. In my research, I’ve observed hallucination rates drop from 15-20% in standard models to 2-3% in well-implemented RAG systems. From a technical perspective, I prefer the term “confabulation” over “hallucination” as it more accurately describes the phenomenon of models generating coherent but false information when attempting to fill knowledge gaps. However, I’ll use the industry-standard term “hallucination” throughout this article for consistency. RAG’s effectiveness stems from its ability to ground responses in retrieved, verifiable information rather than relying solely on learned parameters. This makes it invaluable for applications requiring high accuracy and up-to-date information, such as scientific research, medical diagnosis support, and real-time financial analysis. What are the Benefits of RAG? RAG architectures offer three primary advantages over traditional generative models: Reduced Retraining Requirements: Traditional models require complete retraining cycles to incorporate new knowledge – a computationally expensive process with O(n) complexity relative to dataset size. RAG systems bypass this by maintaining separate, updateable knowledge bases that can be modified without altering model parameters. Computational Efficiency: The computational cost of maintaining current knowledge drops dramatically with RAG. While retraining a 175B parameter model might require thousands of GPU-hours, updating a RAG knowledge base requires only re-encoding new documents into embeddings – typically a matter of minutes on modest hardware. Enhanced Accuracy Through Real-Time Retrieval: RAG systems demonstrate superior performance on factual accuracy benchmarks. In controlled experiments, RAG-enhanced models show: 85% accuracy on time-sensitive queries vs. 42% for static models 91% citation accuracy when referencing source materials 3x reduction in factual errors on domain-specific tasks For instance, in medical applications, a RAG system can retrieve the latest clinical trial data or treatment guidelines during inference, ensuring recommendations align with current best practices rather than potentially outdated training data. How Does RAG Work? RAG systems integrate three core components that work synergistically to produce accurate, contextually relevant outputs. Vector Embeddings At the foundation of RAG systems are vector embeddings – dense numerical representations that capture semantic meaning in high-dimensional space. These embeddings map textual information to points in ℝⁿ (typically n=768 or n=1536) where semantic similarity corresponds to geometric proximity. The embedding process uses transformer-based encoders (e.g., BERT, Sentence-T5) to convert text into vectors where: Cosine similarity between vectors correlates with semantic similarity The embedding space exhibits useful properties like analogical reasoning Contextual nuances are preserved through attention mechanisms The Retrieval Module The retrieval module implements efficient similarity search over large document collections. When processing a query q, the system: Encodes the query: q → v_q ∈ ℝⁿ using the same encoder as the document embeddings Computes similarity scores: sim(v_q, v_d) for all documents d in the corpus Retrieves top-k documents: Returns documents with highest similarity scores Modern implementations use approximate nearest neighbor (ANN) algorithms to achieve sub-linear retrieval complexity: HNSW (Hierarchical Navigable Small World): O(log n) search complexity IVF (Inverted File Index): Clusters vectors for efficient pruning LSH (Locality Sensitive Hashing): Probabilistic approach trading accuracy for speed These methods enable retrieval from billion-scale document collections in milliseconds. Vector Databases Vector databases provide specialized infrastructure for storing and querying embeddings at scale. Key features include: Indexing Strategies: Hierarchical structures for multi-resolution search Quantization techniques to reduce memory footprint Distributed architectures for horizontal scaling Optimization Techniques: Product quantization reduces storage by 90% with minimal accuracy loss Learned indices adapt to data distribution GPU acceleration for similarity computations Popular implementations include Pinecone, Weaviate, and Milvus, each offering different trade-offs between performance, scalability, and features. In the last few years, Oracle has released its enhanced version of Oracle Database that supports vectors (Oracle Database 23ai – OCI or Engineered Systems only) and Google has done the same with AlloyDB (cloud and on-premises). The Generation Module The generation module synthesizes retrieved information with the model’s parametric knowledge. This involves: Context Integration: Retrieved documents are concatenated with the original query Attention Mechanisms: Self-attention layers weight the relevance of retrieved information Conditional Generation: The model generates tokens conditioned on both query and retrieved context Mathematically, this modifies the standard generation probability: P(y|x) → P(y|x, R(x)) where R(x) represents retrieved documents relevant to query x. Example RAG Workflow Consider a biomedical query: “Latest CRISPR applications in treating sickle cell disease” Query Encoding: The query is embedded into a 768-dimensional vector Retrieval: ANN search identifies relevant papers from PubMed embeddings Ranking: Documents are re-ranked using cross-encoder scores Context Formation: Top-5 papers are concatenated with the query Generation: The model synthesizes a response citing specific studies The entire process completes in <2 seconds, providing up-to-date, cited information impossible with static models. When to Use RAG Over Retraining and Fine-Tuning RAG architectures excel in specific scenarios where traditional approaches fall short: Dynamic Knowledge Requirements: When information changes frequently (daily/weekly), RAG’s ability to incorporate updates without retraining becomes invaluable. Time complexity for updates: O(d) for d new documents vs. O(n) for full retraining. Domain-Specific Applications: RAG allows models to access specialized knowledge bases without the catastrophic forgetting associated with fine-tuning. Memory requirements remain constant regardless of knowledge base size. Explainability Requirements: RAG systems provide natural attribution by linking outputs to source documents. This traceability is crucial for applications in regulated industries. Comparative Analysis: Fine-tuning: Lower inference latency (10-20ms) but static knowledge RAG: Higher latency (50-200ms) but dynamic, verifiable knowledge Hybrid approaches: Combine fine-tuned models with RAG for optimal performance Common Use Cases for RAG RAG systems have demonstrated significant impact across multiple domains: Scientific Research: RAG-powered literature review systems process millions of papers, identifying relevant studies with 94% precision. Researchers report 70% time savings in literature surveys. Clinical Decision Support: Integration with electronic health records enables real-time access to patient history, current guidelines, and drug interactions. Studies show 40% reduction in diagnostic errors when physicians use RAG-assisted tools. Financial Analysis:RAG systems analyzing market data, regulatory filings, and news sources demonstrate 2.3x improvement in prediction accuracy for earnings forecasts compared to static models. Legal Research: Automated case law retrieval and analysis reduces research time by 65%. RAG systems identify relevant precedents across jurisdictions with 89% recall. Implementing Retrieval-Augmented Generation Successful RAG implementation requires careful attention to technical details: Document Preprocessing: Chunk documents into semantically coherent segments (typically 200-500 tokens) Implement overlap to preserve context across boundaries Generate embeddings using domain-adapted encoders Retrieval Optimization: Tune similarity metrics for your domain (cosine vs. L2 distance) Implement hybrid search combining dense and sparse retrieval Use query expansion techniques to improve recall System Architecture: “`python # Simplified RAG Pipeline class RAGPipeline:     def __init__(self, encoder, vector_db, generator):         self.encoder = encoder         self.vector_db = vector_db         self.generator = generator     def process_query(self, query):         # Encode query         query_embedding = self.encoder.encode(query)         # Retrieve relevant documents         docs = self.vector_db.search(query_embedding, k=5)         # Generate response with context         context = self.format_context(docs)         response = self.generator.generate(query, context)         return response, docs # Include sources Performance Considerations: Batch encoding for efficiency Implement caching for frequently accessed documents Monitor retrieval quality metrics (MRR, NDCG) Conclusion Retrieval Augmented Generation represents a fundamental shift in how we approach knowledge-grounded language generation. By decoupling knowledge storage from model parameters, RAG enables systems that are simultaneously more accurate, more current, and more interpretable than traditional approaches. The architecture’s elegance lies in its modularity – retrieval and generation components can be optimized independently, allowing for continuous improvement without system-wide changes. As embedding models improve and vector databases become more sophisticated, RAG systems will continue to demonstrate enhanced capabilities. For practitioners, RAG offers a pragmatic solution to the challenges of maintaining current, accurate AI systems. The technical investment required for implementation is offset by dramatic reductions in retraining costs and significant improvements in output quality. As we move toward more specialized AI applications, RAG’s ability to seamlessly integrate domain-specific knowledge while maintaining the fluency of large language models positions it as a critical architecture for the next generation of AI systems.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "What is Retrieval Augmentation Generation (RAG)?", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/RAG-key-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/retrieval-augmented-generation-rag-technical-guide", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "In the dynamic landscape of modern technology, few fields hold as much promise and potential as Artificial Intelligence (AI) and Machine Learning (ML). These innovative technologies have revolutionized industries across the globe, from healthcare to finance, manufacturing to entertainment. The demand for AI and ML expertise is soaring, driven by the quest for efficiency, insights, and competitive advantage. In this fast-paced era, companies striving to stay ahead of the curve recognize the importance of integrating AI and ML into their operations. Whether optimizing processes, personalizing user experiences, or predicting future trends, AI and ML have become indispensable tools for innovation and growth. However, navigating the complexities of AI implementation requires specialized knowledge and expertise. This is where RheoData, as experts in Data Integration, ML, and AI, emerges as a crucial partner in building successful AI projects. The Rising Demand for AI and Machine Learning The digital transformation sweeping across industries has fueled the exponential growth of AI and ML. Organizations increasingly leverage these technologies to unlock value from vast amounts of data, automate tasks, and gain actionable insights. According to industry reports, the global AI market is projected to reach staggering heights, with estimates surpassing hundreds of billions of dollars by the decade’s end. Several factors are driving this surge in demand: Data Deluge: With the proliferation of digital platforms and connected devices, the volume of data generated is growing at an unprecedented rate. AI and ML algorithms thrive on data, making them essential for extracting meaningful insights and patterns from this vast sea of information. Competitive Edge: Companies constantly seek ways to differentiate themselves in today’s hyper-competitive business landscape. AI and ML offer a significant competitive advantage by enabling organizations to streamline processes, enhance decision-making, and deliver personalized experiences to customers. Cost Efficiency: By automating repetitive tasks and optimizing resource allocation, AI and ML solutions help businesses operate more efficiently, reducing operational costs and maximizing profitability. Innovation Catalyst: AI and ML have the potential to drive transformative innovation across various sectors, from healthcare and transportation to retail and agriculture. By pushing the boundaries of what’s possible, these technologies pave the way for groundbreaking discoveries and advancements. Why Choose RheoData for AI Projects? Amidst the growing demand for AI and ML solutions, selecting the right partner to spearhead your projects is paramount to success. Here’s why RheoData stands out as the ideal choice: Expertise and Experience: RheoData boasts a team of seasoned professionals with deep expertise in Data Integration, Machine Learning (ML), Artificial Intelligence (AI), and Data Science. With years of hands-on experience across diverse industries, our experts have the knowledge and skills to effectively tackle your complex AI challenges. Customized Solutions: At RheoData, we understand that every business is unique, with its goals, challenges, and opportunities. That’s why we take a tailored approach to AI project development, crafting bespoke solutions that align with your specific requirements and objectives. Cutting-edge Technologies: Keeping pace with the latest advancements in AI and ML is crucial for delivering innovative solutions that drive tangible results. RheoData leverages cutting-edge technologies and best practices to ensure our clients stay ahead of the curve and capitalize on emerging opportunities. End-to-End Support: From initial concept to deployment and beyond, RheoData provides comprehensive support at every stage of the AI project lifecycle. Whether you need assistance with data collection, model training, or performance monitoring, our dedicated team guides you every step of the way. Focus on Value Delivery: RheoData aims to deliver measurable value to our clients through AI and ML solutions. We prioritize outcomes over outputs, constantly striving to exceed expectations and drive tangible business impact. Conclusion As the demand for Artificial Intelligence (AI) and Machine Learning (ML) continues to soar, organizations must partner with trusted experts to unlock the full potential of these transformative technologies. RheoData stands at the forefront of AI innovation, offering unparalleled expertise, customized solutions, and unwavering support to help businesses thrive in the digital age. By harnessing the power of AI with RheoData, organizations can embark on a journey of discovery, innovation, and success. In a world where data is king, RheoData empowers businesses to reign supreme with AI-driven insights and solutions. Together, let’s embrace the future of technology and pave the way for a smarter, more efficient tomorrow.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Harnessing the Power of AI and Machine Learning with RheoData: A Path to Success", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/HarnessingAIwithRD-2-1.png", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/harnessing-ai", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "The partnership between Oracle and Google Cloud represents one of the most significant collaborative achievements in enterprise technology. Oracle Database@Google Cloud Platform brings together Oracle’s proven database excellence with Google Cloud’s industry-leading infrastructure and AI capabilities, creating unprecedented opportunities for enterprise digital transformation. This strategic alliance enables organizations to leverage Oracle’s advanced database technologies – including Oracle Database 23ai with its revolutionary AI features – while gaining full access to Google Cloud’s comprehensive service portfolio including BigQuery, Vertex AI, and Kubernetes Engine. The result is a unified platform that eliminates the traditional trade-offs between database capability and cloud innovation. As a someone who has led multiple enterprise Oracle migrations and working closely with Google Cloud’s enterprise sales team, we’ve witnessed this partnership deliver exceptional results for organizations seeking to modernize their data infrastructure. While Google Cloud SQL platforms offer solid managed database services for many use cases, Oracle@GCP provides enterprise-grade capabilities that drive competitive advantage and long-term strategic value. Two Paths, One Clear Winner We recently collaborated on evaluating two distinct migration architectures for a client modernizing their Oracle infrastructure on Google Cloud Platform. The contrast illuminated fundamental differences that every IT leader should understand. Path 1: Migration to Google Cloud SQL – A Viable Alternative Google Cloud SQL provides excellent managed database services with PostgreSQL, MySQL, and SQL Server options. These platforms offer strong operational benefits including automated backups, security patching, and high availability configurations. For organizations with simpler database requirements or those looking to standardize on open-source technologies, Cloud SQL represents a solid foundation for cloud operations. However, organizations with complex Oracle workloads may find that Cloud SQL requires additional planning for feature compatibility, performance optimization, and application integration considerations. Path 2: Oracle@GCP with Oracle Database 23ai – The Enterprise Excellence Platform Oracle@GCP deploys Oracle Database through Oracle’s cloud infrastructure services directly within Google Cloud Platform. This architecture provides seamless integration with Google Cloud services while maintaining Oracle’s advanced database capabilities, delivering transformation rather than mere platform conversion. The business case extends beyond technical considerations – it’s about maintaining competitive advantage while achieving cloud benefits. The Oracle 19c Support Reality: A Ticking Clock Based on Oracle’s official Lifetime Support Policy (effective June 10, 2025), Oracle 19c presents significant timeline constraints that both technical and sales perspectives must address: Premier Support ends December 2029 – Only four years of full support remaining from today Extended Support ends December 2032 – Seven-year limited runway with restrictions Java 8 support exclusion after December 2030 – Critical limitation for enterprise environments running integrated Java components Compare this to Oracle 21c (Innovation Release), which offers Premier Support only until July 2027 with no Extended Support available. The pattern is clear: investing in any Oracle release except 23ai means planning replacement before achieving full ROI.Our joint analysis shows that organizations choosing Oracle 19c today will face another migration decision within 3-4 years – creating compounded migration costs and technical debt accumulation. Oracle Database 23ai: Purpose-Built for AI-Powered Enterprise Success Oracle Database 23ai delivers over 300 enterprise-grade features designed for competitive differentiation. From our combined technical and sales perspective, these transformational capabilities drive measurable business outcomes: AI Vector Search integrates semantic search across documents, images, and unstructured data with your private business information – no data movement required, maintaining security while unlocking insights that Google Cloud SQL platforms cannot match. JSON Relational Duality eliminates the traditional document versus relational trade-off by providing unified access through both SQL and JSON APIs, surpassing the capabilities of standard PostgreSQL or MySQL JSON handling. Model Context Protocol (MCP) Integration enables direct AI assistant integration with built-in security, allowing agents to generate and execute SQL queries while maintaining enterprise governance – functionality unavailable in Google Cloud SQL managed services. Oracle True Cache delivers automatically managed, in-memory SQL and key-value caching that accelerates application performance beyond what Cloud SQL memory configurations can achieve. These aren’t incremental improvements – they’re foundational capabilities that position organizations for the next decade of data-driven competition within Google Cloud’s ecosystem. Why Oracle@GCP Wins the Total Cost Analysis Our comprehensive migration assessment reveals the hidden costs of Oracle-to-Cloud SQL conversion that impact bottom-line results: The 80/20 Reality of Database Migration While basic table structures may convert between platforms, they represent only 15-20% of total migration effort. The remaining 80% includes: PL/SQL to stored procedure conversion (60% of effort) – Complete rewriting for PostgreSQL functions or MySQL procedures Application integration changes (20% of effort) – ORM modifications, connection handling, query syntax adjustments Advanced feature reimplementation (10% of effort) – Partitioning, triggers, and constraints require platform-specific approaches Performance optimization (10% of effort) – Completely different tuning methodologies and capabilities Hidden Considerations for Cloud SQL Migration While Google Cloud SQL migration is certainly achievable, organizations should plan for several implementation aspects: Feature adaptation: Some Oracle-specific functionality may require alternative approaches in PostgreSQL, MySQL, or SQL Server environments Application integration updates: Connection handling, query optimization, and ORM configurations may need adjustment for different database engines Performance tuning methodology: Each Cloud SQL platform has unique optimization approaches that teams will need to master Operational procedures: Database administration practices will require updates for the new platform environments Oracle@GCP Advantage Through Partnership Our clients achieve immediate ROI through preserved investments: Zero application rewrite – Existing PL/SQL code base remains fully functional Retained expertise – Current Oracle DBA skills continue delivering value Maintained performance characteristics – No unknown optimization requirements across multiple platforms Preserved advanced features – Partitioning, advanced analytics, and enterprise security remain intact Strategic Positioning for Long-Term Success Oracle@GCP provides the enterprise foundation your organization needs for sustained competitive advantage within Google Cloud’s ecosystem: Google Cloud Integration Excellence – Oracle’s infrastructure services enable seamless connectivity to BigQuery for analytics, AI Platform for machine learning, Kubernetes Engine for containerization, and Vertex AI for advanced AI/ML workloads while maintaining Oracle’s database excellence. AI-Driven Competitive Advantage – Oracle’s built-in AI capabilities complement Google Cloud’s machine learning and analytics services, positioning organizations at the forefront of data-driven decision making. Performance Scalability – Enterprise-grade database performance that surpasses Cloud SQL limitations, particularly for complex analytical workloads and high-concurrency applications that leverage Google Cloud’s compute infrastructure. Operational Excellence – Unified database management with transparent pricing eliminates the complexity of managing multiple Cloud SQL instances for different workload types. The Partnership Perspective: Technical Leadership Meets Sales Excellence From the RheoData View: Oracle@GCP eliminates the technical risks associated with platform conversion while providing immediate access to Google Cloud’s innovation ecosystem. Your team maintains their Oracle expertise while gaining access to best-in-class cloud services. From the Google Cloud Sales Perspective: Oracle@GCP accelerates customer success on Google Cloud Platform by eliminating migration blockers and reducing project risk. Customers achieve faster time-to-value and higher platform adoption rates when database complexity is removed from the equation. Combined Value: This partnership approach ensures both technical success and business objectives align, creating sustainable competitive advantage through proven technology integration. Our Joint Recommendation The data tells a compelling story: Oracle 19c represents a short-term fix when your organization requires long-term strategic advantage. With only four years of Premier Support remaining and Java 8 limitations creating operational constraints, this path misaligns with sustainable operational excellence. Oracle Database 23ai via Oracle@GCP delivers the platform foundation necessary for competitive differentiation over the next 5-10 years. This approach provides true digital transformation – not just database conversion – positioning your organization for sustained success in an AI-powered marketplace while maximizing Google Cloud Platform investments. The Bottom Line for Executive Decision-Making When evaluating Oracle migration options within Google Cloud Platform, consider this strategic question: Does your organization want to invest in a complex multi-platform conversion requiring extensive reengineering, or maintain proven database excellence while gaining cloud benefits? Google Cloud SQL platforms serve specific use cases well, but they cannot match Oracle Database’s enterprise capabilities, advanced analytics features, or AI integration potential. Organizations with significant Oracle investments achieve better ROI by leveraging Oracle@GCP rather than pursuing costly platform conversions. We recommend proceeding with an Oracle@GCP proof of concept to validate performance characteristics and integration capabilities with your specific Google Cloud services. This strategic approach balances innovation with risk management while maintaining business continuity and maximizing both Oracle and GCP investment returns. Contact RheoData at cloud@rheodata.com to discuss how Oracle@GCP can accelerate your organization’s Google Cloud adoption while eliminating the risks and costs associated with heterogeneous database conversion.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Oracle to GCP Migration: Oracle@GCP vs. Cloud SQL – The Strategic Choice That Drives Results", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/Gemini_Generated_Image_3gph3a3gph3a3gph-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/oracle-gcp-vs-cloud-sql-migration", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "The enterprise data landscape just shifted fundamentally. Oracle Database 23ai isn’t simply another version release—it’s the convergence point where decades of enterprise database excellence meets the transformative power of artificial intelligence. After working with this technology since its first beta release, I can tell you we’re witnessing the emergence of the AI-native enterprise database. This release represents Oracle’s recognition that AI isn’t a feature to be bolted onto existing systems—it’s the new foundation for how enterprise applications will process, understand, and act on data. For organizations ready to transform their data strategy, 23ai provides capabilities that seemed like science fiction just a few years ago. Where You Can Access Oracle Database 23ai Today Understanding current availability is crucial for planning your AI transformation: 1. Cloud Infrastructure Ready Oracle Cloud Infrastructure (OCI): Generally available since May 2024 Deployment Options: Exadata Database Service with AI optimization Exadata Cloud@Customer for hybrid environments Base Database Service for standard workloads Autonomous Database with integrated AI capabilities 2. On-Premises Timeline Reality Current Status: Scheduled for sometime in 2025 (only the Oracle Product team knows the timeline) Strategic Context: Cloud-first approach reflects AI workload requirements Extended Support: Oracle 19c Premier Support extended to December 31, 2029 Planning Window: Sufficient time for comprehensive AI strategy development 3. Development and Testing Options Oracle Database 23ai Free: Full feature access for development environments Container Images: Local development with complete AI capabilities Always Free Autonomous Database: Cloud-based experimentation platform The cloud-first strategy aligns with AI workload characteristics—these applications benefit significantly from cloud-native scalability and integration with modern AI services. Ten Features That Redefine Enterprise Data Capabilities From over 300 enhancements, these ten features fundamentally change how enterprises can leverage their data: 1. AI Vector Search: The Intelligence Layer Capability: Native vector data types with specialized indexing for semantic similarity Enterprise Impact: Transform unstructured content into queryable intelligence Real Application: “Show me all customer communications similar to this complaint, regardless of how they phrased it” Strategic Value: Enables Retrieval Augmented Generation (RAG) with your proprietary data 2. JSON Relational Duality Views: Data Model Unification Capability: Single data source accessible as both JSON documents and relational tables Enterprise Impact: Eliminates the historical friction between application development and data storage Real Application: Build modern microservices that consume JSON while maintaining enterprise data integrity Developer Productivity: Reduces application complexity by 70% for hybrid data scenarios 3. Oracle True Cache: Intelligent Acceleration Capability: Self-managing, transactionally consistent middle-tier caching Enterprise Impact: Application performance improvements without architectural complexity Real Application: High-traffic e-commerce platforms with automatic cache coherency Operational Excellence: Zero cache management overhead for development teams 4. SQL Firewall: Behavioral Security Capability: Kernel-level protection against unauthorized database operations Enterprise Impact: Proactive defense against SQL injection and insider threats Real Application: Financial systems with strict regulatory compliance requirements Risk Mitigation: Blocks unknown SQL patterns while learning normal application behavior 5. Property Graph Analytics with SQL Capability: Native graph processing using standard ANSI SQL/PGQ syntax Enterprise Impact: Complex relationship analysis without separate graph databases Real Application: Supply chain risk analysis, fraud detection networks, customer journey mapping Integration Advantage: Graph analytics on existing relational and JSON data 6. Globally Distributed Database with RAFT Capability: Multi-region database with automatic failover and zero data loss Enterprise Impact: Global applications with data sovereignty compliance Real Application: International financial services with regulatory data residency requirements Business Continuity: Sub-second failover for mission-critical applications 7. Enhanced JSON Schema Validation Capability: Comprehensive JSON structure and content validation Enterprise Impact: Data quality enforcement for schema-flexible applications Real Application: API data contracts and microservices communication validation Quality Assurance: Prevents data corruption in document-oriented workflows 8. MongoDB API Compatibility Capability: Use MongoDB drivers and tools with Oracle Database backend Enterprise Impact: Leverage MongoDB application ecosystems with Oracle reliability Real Application: Modernize MongoDB applications with enterprise-grade capabilities Migration Advantage: Access Oracle security, backup, and performance without code changes 9. Advanced Machine Learning Integration Capability: In-database ML model training and inference with ONNX support Enterprise Impact: Real-time ML predictions where data lives Real Application: Fraud scoring, recommendation engines, predictive maintenance Performance Optimization: Eliminates data movement for ML workloads 10. Multi-Model Data Convergence Capability: Unified platform for relational, JSON, graph, spatial, and vector data Enterprise Impact: Single database supporting diverse application requirements Real Application: Modern applications requiring multiple data paradigms Architecture Simplification: Reduces infrastructure complexity and operational overhead Upgrade Strategy: Making the Right Move Your upgrade decision should align with your organization’s AI readiness and operational constraints: Immediate Cloud Adoption Scenarios New AI-enabled application development Organizations with cloud-first strategies Teams building modern microservices architectures Companies requiring advanced semantic search capabilities Applications needing real-time ML integration Strategic Waiting for On-Premises Mission-critical systems with strict on-premises requirements Applications dependent on third-party software certifications Organizations with complex compliance and testing cycles Environments where current 19c capabilities meet all business requirements Supported Upgrade Paths From 12c: Multi-step upgrade process through 19c From 18c: Requires intermediate 19c upgrade From 19c: Direct upgrade pathway available From 21c: Straightforward migration process Near-Zero/Online upgrades using Oracle GoldenGate 23ai The AI-First Database Era What we’re experiencing goes beyond typical database evolution. Oracle Database 23ai represents the maturation of AI as a core database capability rather than an external service. This convergence enables entirely new categories of applications that can understand, reason about, and act on enterprise data in ways that were previously impossible. The vector search capabilities, combined with JSON relational duality, create a foundation for applications that can process natural language queries against structured business data while maintaining the reliability and consistency enterprises require. This isn’t just about adding AI features—it’s about reimagining how applications interact with data. For organizations still evaluating their AI strategy, the extended Oracle 19c support provides adequate planning time. However, the competitive advantage belongs to companies that begin building AI-native applications now. The learning curve and organizational adaptation required for AI-first development shouldn’t be underestimated. Transform Your Enterprise Data Architecture RheoData has been deeply involved with Oracle Database 23ai since its initial beta release, continuing through ongoing preview programs. Our experience spans both the transformative potential and the practical implementation challenges organizations face. Comprehensive Migration and AI Strategy Services: Database Modernization Planning: Expert migration strategies from 12c, 18c, 19c, and 21c to 23ai AI Readiness Assessment: Evaluate your data architecture for AI capability integration Vector Search Implementation: Design and deploy semantic search solutions with your enterprise data JSON Duality Architecture: Transform application data models for modern development patterns Cloud Strategy Development: Optimize your path to AI-enabled cloud database services Team Enablement Programs: Prepare your database and development teams for AI-first operations The transition to AI-native database operations requires more than technical migration—it demands strategic thinking about how AI will transform your business processes and customer experiences. Success comes from combining deep Oracle expertise with practical AI implementation experience. Ready to architect your AI-enabled data future? Contact our cloud strategy team at cloud@rheodata.com to discuss how Oracle Database 23ai can accelerate your organization’s AI transformation while maintaining the enterprise reliability your business demands.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Oracle Database 23ai: Where Enterprise Data Meets Artificial Intelligence", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/Gemini_Generated_Image_yus26vyus26vyus2-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/oracle-database-23ai-enterprise-ai-transformation", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "Building a Data Governance Framework Data governance is crucial for any organization looking to leverage its data effectively. It provides a structured approach to managing, using, and protecting data assets. Let’s break down how to build a data governance framework in a simple and understandable way. What is Data Governance? Data governance is the overall management of the availability, usability, integrity, and security of data in an enterprise. It involves establishing policies, procedures, and standards to ensure data is consistent, reliable, and trustworthy. Key Components of a Data Governance Framework Here are the essential components you need to focus on when building your framework: 1. Define Goals and Objectives First, determine what you want to achieve with data governance. What are the business drivers? Common goals include: Improving data quality Ensuring regulatory compliance Enhancing decision-making Increasing data security 2. Identify Roles and Responsibilities Clearly define roles and responsibilities for data governance. Key roles include: Data Owner: Responsible for data definition, quality, and usage. Data Steward: Implements data policies and procedures. Data Custodian: Manages the technical aspects of data storage and access. Data Governance Council: Oversees the data governance program. 3. Establish Data Policies and Standards Create policies and standards that govern how data is managed and used. These should cover: Data quality rules Data security and privacy Data access and usage Data retention and disposal 4. Implement Data Quality Management Data quality is essential. Implement processes to: Identify and correct data errors Monitor data quality metrics Establish data validation rules 5. Develop a Data Dictionary and Metadata Management Create a data dictionary to document data elements, definitions, and relationships. This helps ensure everyone is on the same page. 6. Establish Communication and Training Ensure everyone in the organization understands the data governance framework. Provide training and regular communication to promote awareness and adherence. 7. Monitor and Measure Success Continuously monitor the effectiveness of your data governance framework. Track key metrics and make adjustments as needed. Steps to Implement Your Framework Here’s a simple step-by-step approach: Assessment: Evaluate your current data management practices. Planning: Define goals, roles, policies, and standards. Implementation: Roll out the framework and provide training. Monitoring: Track metrics and make improvements. Continuous Improvement: Regularly review and update the framework. Why Data Governance Matters Effective data governance leads to better decision-making, improved data quality, and reduced risk. It empowers organizations to use data as a strategic asset. By following these steps, you can build a robust and effective data governance framework that supports your organization’s goals.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Building a Data Governance Framework", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/AdobeStock_1040748327-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/build-data-governance-framework", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "Remember when everyone said the cloud was just a fad? We’re hearing similar skepticism about AI in enterprise data management today. But here’s what I’ve learned after thirty years in technology leadership: the organizations that dismiss transformative technologies early often spend the most catching up later. The difference this time? AI isn’t just changing how we work with data—it’s fundamentally reshaping what’s possible when humans and systems collaborate intelligently. I’ve watched teams struggle with Oracle GoldenGate troubleshooting for hours, digging through logs and configuration files, when the right AI integration could surface those insights in minutes. That breakthrough moment came when we discovered Anthropic’s Model Context Protocol. Suddenly, we weren’t just talking about AI as some distant future capability—we had a practical, secure way to connect AI directly to the enterprise systems our teams use every day. The Challenge: When AI Meets Enterprise Reality Walk into any enterprise data center, and you’ll find the same frustrating disconnect. Marketing teams are buzzing about AI transformation while database administrators are still manually checking replication lag at 2 AM. The promise is compelling, but the execution? That’s where most organizations stumble. I’ve seen too many AI projects that look impressive in demos but crumble under real-world operational pressure. Teams invest months building fragile custom integrations that break every time Oracle releases an update. Meanwhile, the DBAs who could benefit most from AI assistance continue working with the same tools they’ve used for years, waiting for someone to bridge that gap between possibility and practicality. Oracle’s microservices framework already gives us solid programmatic access through REST APIs. We can automate deployments and monitor replication status dynamically. But imagine if your database administrators could simply ask, “Which extracts are running slowly today?” and get immediate, accurate answers from live system data. The Model Context Protocol: Finally, a Standard That Makes Sense At Google NEXT this year, when Anthropic announced the Model Context Protocol, I knew we’d found something different. This wasn’t another flashy AI demo—it was a practical solution to the standardization problem that’s been holding back enterprise AI adoption. Think of MCP as creating a universal connection standard between AI and your existing infrastructure—like how USB-C eliminated the chaos of proprietary cables. One standardized interface that works across different AI platforms and evolves with your systems. But here’s what makes MCP genuinely powerful for enterprise environments: it respects your security boundaries. Instead of training AI models on sensitive data, MCP lets AI access live information through controlled, secure interfaces. Your critical data stays exactly where it belongs while AI gains the context it needs to provide meaningful assistance. Building MCP Servers That Actually Work in Production Let me show you how we approach MCP development for Oracle GoldenGate, using principles that work for any enterprise system integration. The architecture starts simple but reflects years of hard-won lessons about enterprise integrations: # server.py - Your integration foundation import sys from mcp.server.fastmcp import FastMCP mcp = FastMCP(GoldenGateMCP) # main.py - Your execution entry point from server import mcp if __name__ == __main__: mcp.run(transport='stdio') This foundation looks straightforward, but what’s happening underneath reflects everything we’ve learned about building systems that teams can depend on. Clean separation between configuration and execution makes managing different environments infinitely easier. Tools That Solve Real Problems The real work happens when you build tools around business operations, not just technical functions. Here’s how we structure our Oracle GoldenGate integration: class GoldenGateOperations: def __init__(self, config: dict = None): if config is None: from config_loader import load_config config = load_config() # Secure configuration management gg_config = config[golden_gate] self.host = gg_config[host] self.username = gg_config[username] self.process_configs = gg_config[processes] async def get_process_status(self, process_type: str): Retrieve real-time status for GoldenGate processes if process_type not in self.process_configs: available_types = list(self.process_configs.keys()) raise ValueError(fProcess type '{process_type}' not configured. Available: {available_types}) # Secure API interaction with proper authentication config = self.process_configs[process_type] url = fhttp://{self.host}:{config['port']}/services/v2/{config['endpoint']} # Enterprise security practices auth_credentials = f{self.username}:{config['password']} encoded_auth = base64.b64encode(auth_credentials.encode()).decode() headers = {Authorization: fBasic {encoded_auth}} response = requests.get(url, headers=headers, verify=False) return json.dumps(response.json(), indent=2) See what we’re doing here? Configuration stays external, authentication follows security best practices, and error handling gives clear feedback. These aren’t just coding preferences—they’re operational necessities when building systems that teams will stake their reputation on. Natural Language for Operations Teams The transformation happens when you expose these capabilities through conversational interfaces: @mcp.tool() async def get_extract_status(): Check the current status of all extraction processes return await gg_operations.get_process_status(extracts) @mcp.tool() async def get_replicat_status(): Monitor replication process health and performance return await gg_operations.get_process_status(replicats) Suddenly, your operations team can ask “Are all our extracts running normally?” and get immediate answers based on live system data. That’s when AI stops feeling like a science project and starts delivering real value. Strategy Beyond the Code Building the MCP server is the foundation, but successful implementation requires thinking strategically about how teams actually work. Enhancing Existing Workflows The most successful AI implementations enhance established processes rather than disrupting them. Your database administrators already have proven workflows for monitoring GoldenGate environments. Smart MCP servers accelerate these processes without forcing teams to abandon what’s already working. Starting with monitoring and status checking creates immediate value while building confidence. Teams can verify AI responses against familiar tools, gradually building trust in the system. Security That Actually Works Enterprise AI demands enterprise-grade security from day one: Credential Management: Enterprise-grade secrets management, never hardcoded passwords Network Security: Proper network segmentation and access controls Audit Logging: Complete tracking of all AI interactions with enterprise systems Data Governance: AI interactions that comply with organizational data policies Getting Teams on Board Technical implementation is often the straightforward part. Real success requires thoughtful change management: Start with Power Users: Find team members comfortable with new technology who can become advocates Demonstrate Clear Value: Show concrete time savings and improved accuracy, not just impressive technology Provide Fallback Options: Teams need confidence they can perform critical tasks even if AI systems are unavailable Iterate Based on Feedback: The best implementations evolve based on real user experiences Connecting to Production Systems Once your MCP server is tested and ready, connecting it to platforms like Claude Desktop requires attention to operational details. Configuration management becomes critical here. Your claude_desktop_config.json should reflect organizational deployment standards: { mcpServers: { GoldenGateOperations: { command: /opt/python/bin/uv, args: [ --directory, /opt/mcp/goldengate-server, run, main.py ] } } } Use absolute paths, establish consistent deployment locations, and ensure your configuration integrates with existing DevOps processes. These operational details determine whether your solution scales across the enterprise or remains a clever proof of concept. What Success Looks Like in the Real World When MCP servers work effectively, they transform how teams interact with complex enterprise systems. Here’s what we’ve observed: Faster Problem Resolution: Database administrators diagnose replication issues in minutes instead of hours, using natural language queries to quickly identify bottlenecks and configuration problems. Better Team Collaboration: Operations teams share system status and troubleshooting insights more effectively when AI provides context-rich explanations of system behavior. Smarter Decision Making: Managers get real-time operational insights without needing deep Oracle GoldenGate expertise. Reduced Learning Curves: New team members become productive faster when they can ask systems questions in plain English. The Bigger Picture MCP servers represent more than just another integration approach. They signal a fundamental shift toward more accessible, context-aware enterprise operations. Organizations wrestling with complex data architectures and the demand for real-time operational intelligence will find standardized protocols like MCP becoming essential infrastructure. Teams that embrace these approaches early gain significant competitive advantages in operational efficiency and system reliability. The key? Approach these implementations with the same discipline and strategic thinking you’d apply to any critical enterprise system. This isn’t about experimenting with AI—it’s about building production-ready solutions that genuinely enhance your team’s capabilities and improve business outcomes. Summary Building MCP servers for Oracle GoldenGate operations demonstrates a practical approach to enterprise AI integration—one that delivers immediate value while establishing the foundation for broader transformation initiatives. The technical implementation is straightforward when you apply proper architectural thinking and enterprise-grade practices. The real value emerges when operations teams can interact with complex systems using natural language while maintaining security, reliability, and compliance. Success requires balancing technical capabilities with thoughtful change management, ensuring AI enhancements integrate seamlessly with existing workflows and team practices. Organizations taking this measured, strategic approach build AI capabilities that scale across their enterprise architecture while delivering measurable operational improvements. The question isn’t whether AI will transform enterprise data operations—it’s whether your organization will lead that transformation or spend years catching up. MCP servers provide a clear, practical path forward for teams ready to bridge the gap between AI potential and enterprise reality. What’s our objective here? Clear communication, team success, and technology that serves the mission. That’s strategic AI integration in practice. Ready to Transform Your Enterprise Operations? At RheoData, we’ve built MCP servers and AI integrations for some of the most demanding enterprise environments. We understand the difference between impressive demos and production-ready solutions that your teams can depend on. Whether you’re looking to enhance Oracle GoldenGate operations, integrate AI with other enterprise systems, or develop a comprehensive AI strategy that aligns with your business objectives, our team brings the architectural expertise and operational experience to make it happen. Let’s coordinate on your next AI integration project. Contact us to discuss how MCP servers can transform your enterprise operations while maintaining the security, reliability, and performance your business demands. Ready to get started? Reach out to cloud@rheodata.com or visit rheodata.com to learn more about our enterprise AI integration services. Your success is our success. Let’s build something remarkable together.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Transforming Oracle GoldenGate Operations with AI: Building MCP Servers for Real-World Impact", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/AdobeStock_589427987-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/transforming-oracle-goldengate-operations-with-ai-mcp-servers", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "At Oracle Cloud World 2023, Oracle announced they were moving toward enabling Artificial Intelligence (AI) within many of their products. Oracle is making huge steps forward for many people to use AI daily. As 2023 ended, many other industry leaders announced they would do the same. Regarding databases, Oracle is the only industry leader that leverages its core product for many different things. For at least a decade, Oracle has turned the Oracle Database into a Swiss army knife by enabling it to support different modern data types, analytics, and development paradigms, all in one product. It is only natural that with the AI revolution starting, Oracle would build a data type that enables organizations to use Retrieval-Augmented Generation (RAG) within the databases. By adding a “vector” datatype, Oracle simplifies data architectures and the building of RAG or Private-LLM configurations for organizations. Where is the Vector datatype? If you use an Oracle Database today, you will not immediately have access to the Vector datatype. Even if you use the latest version, 23.3.x.x, on Oracle Cloud Infrastructure (OCI), you cannot access this datatype (Believe me, I tried). You have to be part of the beta program for the next release of Oracle Database, which will provide you details on the Vector datatype before the initial release in 23.4. In short, and for the moment, if you are not part of the beta program, this datatype will be available soon! What is the Vector datatype? The Vector datatype is a modern datatype designed to efficiently store, manage, and index massive amounts of high-dimensional data. This data type is growing in interest and is used to create additional value for generative AI use cases and applications. Vector Settings? The vector datatype is used within standard Oracle tables. This enables database schemas to use the data in real-time. The following command shows a simple example: sql> CREATE TABLE rd_vectors (id NUMBER, embed VECTOR); This simple example shows that the vector datatype can be set as a column within a table. Enabling it this way allows you to specify vectors of different dimensions with different formats. Think of this as a catch-all setting for vector data. It is great to have a catch-all; however, you can limit the type of vectors created by imposing constraints on the stored data. In this example, you can only store up to 1024 dimensions, and they must be formatted as INT8 (8-bit integers): sql> CREATE TABLE rd_vectors_int8 (id NUMBER, embed VECTOR(1024, INT8); With this complex example, you must have 1024 dimensions, each of which must be 8-bit integers (INT8). The number of dimensions should be greater than 0 with no limit. The dimensions formats are INT8, FLOAT32, and FLOAT64. FLOAT32 and FLOAT64 are the IEEE standards, and the Oracle Databases will automatically cast the values as needed. Examples of setting additional dimension formats are: sql> CREATE TABLE rd_vectors_int8 (id NUMBER, embed VECTOR(1024, FLOAT32); sql> CREATE TABLE rd_vectors_int8 (id NUMBER, embed VECTOR(1024, FLOAT64); Vector Forms? With the understanding of Vector settings, there are a few forms that a vector can take. Understanding these forms will help in defining the proper vector for your requirements: Important Note: A vector can be NULL, but the dimensions cannot be NULL. (example: You cannot have [(1.1, NULL, 2.3)] Examples of Vectors: Now that you understand the Vector datatype, how does the Oracle Database see the datatype? The following SQL example shows that the table rd_vector is created with only vector datatypes using different variations. sql> CREATE TABLE vector.rd_vector ( v1 VECTOR, v2 VECTOR(3, FLOAT32), v3 VECTOR(2, FLOAT64), v4 VECTOR(1, INT8), v5 VECTOR(1, *), v6 VECTOR(*, FLOAT32), v7 VECTOR(*, *) ); sql> desc vector.rd_vector; Name                                         Null?   Type ----------------------------------------- -------- —————————————— V1                                                         VECTOR(*, *)  V2                                                         VECTOR(3, FLOAT32) V3                                                         VECTOR(2, FLOAT64) V4                                                         VECTOR(1, INT8) V5                                                         VECTOR(1, *) V6                                                         VECTOR(*, FLOAT32) V7                                                         VECTOR(*, *) Hopefully, Oracle will release Oracle Database 23.4 soon! There will be many opportunities to use vector data types as organizations expand their usage of Generative AI. Enjoy!", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Oracle’s Vector Datatype", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/oracle-vector-datatype-1-1.png", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/vector-datatype", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ``` ```json { "@context" : "http://schema.org", "@type" : "BlogPosting", "articleBody" : "When IT executives evaluate Oracle workloads for Microsoft Azure migration, the conventional wisdom points toward SQL Server as the natural destination. However, this assumption overlooks a critical business reality: Oracle@Azure delivers superior ROI while preserving your technology investments. RheoData’s enterprise migration analysis reveals why Oracle@Azure represents the strategic choice for sustainable competitive advantage. Two Paths, One Clear Winner RheoData recently evaluated two distinct migration architectures for a client modernizing their Oracle infrastructure. The contrast illuminated fundamental differences that every IT leader should understand. Path 1: Oracle 19c on Azure VMs – The Short-Term Trap Traditional “lift and shift” approaches position Oracle 19c on Azure virtual machines with bi-directional replication capabilities. While this delivers immediate cloud benefits, it creates what RheoData identifies as “strategic debt” – investing in a platform with rapidly diminishing support runway. Path 2: Oracle@Azure with Oracle 23ai – The Growth Platform Oracle@Azure deploys Oracle Database 23ai through Oracle’s native cloud infrastructure directly within Azure. This architecture provides seamless integration between Azure services and Oracle’s most advanced database technology, delivering transformation rather than mere migration. The business case isn’t just technical – it’s about sustainable competitive advantage. The Oracle 19c Support Reality: A Ticking Clock Based on Oracle’s official Lifetime Support Policy (effective June 10, 2025), Oracle 19c presents significant timeline constraints: Premier Support ends December 2029 – Only four years of full support remaining from today Extended Support ends December 2032 – Seven-year limited runway with restrictions Java 8 support exclusion after December 2030 – Critical limitation for enterprise environments running integrated Java components Compare this to Oracle 21c (Innovation Release), which offers Premier Support only until July 2027 with no Extended Support available. The pattern is clear: investing in any Oracle release except 23ai means planning replacement before achieving full ROI. RheoData’s analysis shows that organizations choosing Oracle 19c today will face another migration decision within 3-4 years – creating compounded migration costs and technical debt accumulation. Oracle 23ai: Purpose-Built for AI-Powered Enterprise Success Oracle Database 23ai delivers over 300+enterprise-grade features designed for competitive differentiation. RheoData highlights the transformational capabilities that drive measurable business outcomes: AI Vector Search integrates semantic search across documents, images, and unstructured data with your private business information – no data movement required, maintaining security while unlocking insights. JSON Relational Duality eliminates the traditional document versus relational trade-off by providing unified access through both SQL and JSON APIs, accelerating application development cycles. Model Context Protocol (MCP) Integration enables direct AI assistant integration with built-in security, allowing agents to generate and execute SQL queries while maintaining enterprise governance. Oracle True Cache delivers automatically managed, in-memory SQL and key-value caching that accelerates application performance without complex configuration overhead. These aren’t incremental improvements – they’re foundational capabilities that position organizations for the next decade of data-driven competition. Why Oracle@Azure Wins the Total Cost Analysis RheoData’s comprehensive migration assessment reveals the hidden costs of Oracle-to-SQL Server conversion that impact bottom-line results: The 80/20 Reality of Database Migration While data type mappings appear straightforward, they represent only 15-20% of total migration effort. The remaining 80% includes: PL/SQL packages, procedures, and functions (60% of effort) – Complete code reconstruction required Application integration changes (20% of effort) – Connection strings, drivers, query modifications Triggers and complex constraints (10% of effort) – Logic restructuring across systems Performance optimization (10% of effort) – Platform-specific tuning requirements Hidden Cost Multipliers SQL Server migration introduces expense categories that Oracle@Azure eliminates: Development costs: 6-12 months of specialized conversion effort Risk mitigation costs: Extended parallel operations increase infrastructure expenses Retraining investment: DBA and developer education for new platform expertise Opportunity costs: Team focus diverted from strategic initiatives during extended migration period Oracle@Azure Value Acceleration RheoData’s clients achieve immediate ROI through preserved investments: Zero application rewrite – Existing PL/SQL code base remains fully functional Retained expertise – Current team skills continue delivering value Maintained performance characteristics – No unknown optimization requirements Preserved business logic – Critical processes require no reconstruction Strategic Positioning for Long-Term Success Oracle@Azure provides the enterprise foundation your organization needs for sustained competitive advantage: Cloud-native architecture through Oracle’s deep Azure integration delivers modern infrastructure benefits without platform migration risks. AI-driven capabilities position organizations at the forefront of data-driven decision making, with built-in security and governance. Innovation pipeline access ensures continuous competitive differentiation through Oracle’s ongoing AI and database technology investments. Enterprise-grade reliability combines Oracle’s proven database technology with Azure’s global infrastructure for maximum uptime and performance. RheoData’s Strategic Recommendation The data tells a compelling story: Oracle 19c represents a short-term fix when your organization requires long-term strategic advantage. With only four years of Premier Support remaining and Java 8 limitations creating operational constraints, this path misaligns with sustainable operational excellence. Oracle 23ai via Oracle@Azure delivers the platform foundation necessary for competitive differentiation over the next 5-10 years. This approach provides true digital transformation – not just infrastructure migration – positioning your organization for sustained success in an AI-powered marketplace. The Bottom Line for Executive Decision-Making When evaluating Oracle migration options, consider this strategic question: Does your organization want to invest in a solution requiring replacement planning during implementation, or one that accelerates competitive advantage for the next decade? RheoData recommends proceeding with an Oracle@Azure proof of concept to validate performance characteristics and cost structures for your specific workloads. This strategic approach balances innovation with risk management while maintaining business continuity and maximizing technology investment returns. Contact RheoData at cloud@rheodata.com to discuss how Oracle@Azure can accelerate your organization’s digital transformation objectives while eliminating the risks and costs associated with heterogeneous database migration.", "author" : { "@type" : "Person", "name" : "Bobby Curtis", "sameAs" : "", "url" : "https://rheodata.com/en-us/blog/author/bobby-curtis" }, "dateModified" : "10/11/2025", "datePublished" : "10/11/2025", "headline" : "Oracle to Azure Migration: Oracle@Azure vs. SQL Server – The Strategic Choice That Drives Results", "image" : { "@type" : "ImageObject", "height" : 400, "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/Imported_Blog_Media/Gemini_Generated_Image_5dnwx15dnwx15dnw-1.jpg", "width" : 750 }, "mainEntityOfPage" : "https://rheodata.com/en-us/blog/oracle-azure-vs-sql-server-migration", "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://50642793.fs1.hubspotusercontent-na1.net/hubfs/50642793/RheoData%20-%20Logo%20-%20transparent-1.png" }, "name" : "RheoData", "url" : "rheodata.com" } } ```