Oracle Cloud Infrastructure Documentation

Overview of Generative AI Agents Service

OCI Generative AI Agents is a fully managed service that combines the power of large language models (LLMs) with an intelligent retrieval system to create contextually relevant answers by searching your knowledge base, making your AI applications smart and efficient.

OCI Generative AI Agents supports several ways to on-board your data where you and your customers can interact with your data using a chat interface or API.

Key Features
  • Supports several data on-boarding methods and interaction channels (chat interface or API)
  • Creates contextually relevant answers by searching your knowledge base
  • Provides source attribution for every answer
  • Offers hybrid search capabilities (lexical and semantic) for more correct answers
  • Includes content moderation options for input and output to ensure a safe and respectful chat experience
  • Supports multi-turn conversations, where users can ask follow-up questions and receive answers that consider the context of previous questions and answers
  • Can interpret data from two-axis charts and reference tables in a PDF, without needing explicit descriptions of the visual elements

  • All the hyperlinks present in the PDF documents are extracted and displayed as hyperlinks in the chat response.

Knowledge Base Data Types

  • Service-Managed Option

    • OCI Object Storage files where you can have up to 1,000 text and PDF files of 100 MB each. And you can request an increase through limit request.

  • Bring Your Own (BYO) Options

    • Oracle Database 23ai vector search
    • OCI Search with OpenSearch ingested and indexed data
Benefits
  • Transparent Accountability: Track responses back to their source for clear visibility and accountability.
  • Seamless Updates: Update data sources without disrupting agent functionality, ensuring continuous operation.
  • Robust Architecture: Leverage a scalable and secure architecture that supports growing demands and maintains data integrity.
  • Version Control and Incremental Ingestion: Manage data updates with precision through incremental ingestion and version control.
  • Enhanced Customer Experience: Engage in more natural and intuitive conversations with customers, driving improved satisfaction and loyalty.

Getting Started

To use OCI Generative AI Agents, create a knowledge base, add your data, create an agent, and set up endpoints for user interaction. OCI Generative AI Agents takes care of the rest, providing relevant answers to you and your customers' questions, and tracks the conversation context to enable more informed and helpful responses.

Use Cases

A retrieval-augmented generation (RAG) agent is a type of artificial intelligence application that combines retrieval and generation capabilities to produce responses. The RAG agent retrieves relevant documents or data from a knowledge source and then uses a language generation model to create a coherent and contextually relevant answer based on the retrieved information. This approach leverages both the factual accuracy of retrieval methods and the flexibility of generative models, making it useful for tasks that require both depth of knowledge and fluency in response generation. You can use the RAG agents in OCI Generative AI Agents for the following use cases:

  • Customer Support: In the customer service industry, RAG agents can retrieve information from a company’s knowledge base to provide correct and contextually relevant answers to customer inquiries, reducing response times and improving customer satisfaction.
  • Legal Research: Legal professionals can use RAG agents to quickly find precedents and relevant case law from vast legal databases, streamlining the research process and ensuring thorough consideration of relevant legal texts.
  • Financial Analysis: In finance, RAG agents can analyze large volumes of financial data, reports, and news to provide analysis and recommendations for traders and analysts, helping them make informed investment decisions.
  • Educational Tutoring: RAG agents can function as personal tutors, providing students with explanations, resources, and answers to questions by accessing educational content and tailoring explanations to the student’s current level of understanding.
  • Content Creation: In media and content creation, RAG agents can help writers and journalists by pulling information on specific topics, suggesting content ideas, and even drafting sections of articles based on the latest data and trends.
  • Technical Support and Troubleshooting: RAG agents can guide users through technical troubleshooting processes by accessing and synthesizing technical manuals and support forums to offer step-by-step help.
  • Supply Chain Management: In supply chain and logistics, RAG agents can provide insights by retrieving and synthesizing information on inventory levels, supplier data, and logistic metrics to optimize operations and predict potential disruptions.
  • Real Estate Market Analysis: RAG agents can help real estate professionals by aggregating and analyzing data from several sources, including market trends, property listings, and regulatory changes, to provide comprehensive market analyses.
  • Travel Planning and Help: In the travel industry, RAG agents can serve as interactive travel guides, pulling information on destinations, weather, local attractions, and regulations to provide personalized travel advice and itineraries.

Each of these use cases shows how RAG agents can enhance efficiency and decision-making by combining the retrieval of specific, relevant information with the generation of insightful, context-aware responses.

Regions with Generative AI Agents

Oracle hosts its OCI services in regions and availability domains. A region is a localized geographic area, and an availability domain is one or more data centers in that region. OCI Generative AI Agents is hosted in the following regions:

Region Name Location Region Identifier Region Key
Germany Central (Frankfurt) Frankfurt eu-frankfurt-1 FRA
UK South (London) London uk-london-1 LHR
US Midwest (Chicago) Chicago us-chicago-1 ORD

See About Regions and Availability Domains for the list of available OCI regions, along with associated locations, region identifiers, region keys, and availability domains.

Accessing Generative AI Agents in the Console

  1. Sign in to the Console by using a supported browser.
  2. In the navigation bar of the Console, select a region that hosts Generative AI Agents, for example, US Midwest (Chicago).
  3. Open the navigation menu and click Analytics & AI. Under AI Services, click Generative AI Agents.