The RAG Agent is the first in a series of OCI GenAI Agents and offers ready-to-use RAG features, allowing customers to get started immediately and avoid manual processes such as scheduling, retrieving, reordering, generating, and integrating data through agents. It also provides a self-check to reduce hallucinations, enabling customers to use RAG technologies to streamline their business processes without having to go through various cycles of research and development. With OCI GenAI Agents, customers have access to Oracle Database 23ai AI Vector Search and can perform quick queries for matches on business data stored in the database. For customers subscribed to Oracle Database 23ai on OCI, the GenAI Agents service adds an automation layer to perform RAG functions and match queries without needing to move data to a separate vector database.

For organizations looking for open-source solutions for their generative AI workloads, the OCI GenAI Agents service also supports OCI Search with OpenSearch.

"AI is driving breakthroughs and efficiency at an unprecedented pace, leading to new business models, applications, and innovation across various industries," said Greg Pavlik, Executive Vice President, AI and Data Management Services, Oracle Cloud Infrastructure. "With the OCI Generative AI Agents service, customers of Oracle Database 23ai can subscribe to a fully managed RAG service that allows them to converse with their data. It is AI designed for businesses that want to quickly use AI in their real production environments by bringing AI directly to their data."

Key use cases for OCI GenAI Agents include:

• Call center optimization: helps operators increase customer satisfaction by providing more accurate responses and handling more inquiries faster.
• Accelerating legal research: helps researchers find answers faster by conversing with AI instead of manually searching databases of court records.
• Revenue insights: helps finance teams gain insights into customer purchase history and trends by asking questions in natural language instead of running reports.
• Recruiting qualified candidates: helps recruiters find potential new employees more easily by typing in natural language instead of having to create a database query.

To provide versatile and accessible AI solutions for developers and business users, Oracle also introduces AI innovations for the following:

• OCI Generative AI: helps users seamlessly integrate versatile language models for a wide range of use cases, such as writing assistance, summarization, analysis, and chat. To enable customers to leverage the latest open-source AI technology with enterprise-level security and privacy, OCI Generative AI now provides access to the Meta Llama 3.1 models ranging from 405 billion parameters for AI use cases requiring advanced capabilities to 70 billion parameters for more targeted workloads at a lower cost. Additionally, OCI Generative AI supports the Cohere Command R, Command R+, and Embed models.
• OCI Data Science: helps teams of data scientists access open-source tools for building, training, deploying, and managing AI models. OCI Data Science offers several new updates for the no-code AI Quick Actions feature, including support for the OCI Ampere A1 shape and the ability to transfer any Hugging Face model to OCI Data Science with just a few clicks.
• OCI Language: helps developers perform advanced text analysis and machine translation at scale. New multilingual models are designed for seamless support of over 100 languages, while the current service for personally identifiable information (PII) has been expanded with a new feature for protected health information (PHI) to detect and redact PHI entities based on textual data.
• OCI Document Understanding: helps developers automate manual business processes with ready-to-use AI models. With newly trained models for healthcare, developers can identify and extract important data from medical ID cards, while increasing efficiency and preventing manual errors.
• OCI Vision: helps developers analyze videos frame by frame to identify objects, labels, text, and faces. It provides data on detection timestamps and bounding box coordinates for objects to support use cases such as digital asset management, visual anomaly detection, security and surveillance, and ad tracking and placement.
• OCI Speech: helps users transcribe speech to text and synthesize speech from text with natural voices and a new real-time transcription feature supporting custom word lists.
• Oracle Code Assist: helps developers work faster by providing intelligent suggestions for building and optimizing applications written in modern programming languages such as Java, Python, JavaScript, SuiteScript, Rust, Ruby, Go, PL/SQL, C#, and C.

Additional resources

• Read the OCI Generative AI blog
• Learn more about Oracle AI