Oracle Cloud Infrastructure Documentation
Try Free Tier

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 AI technologies to create intelligent virtual agents that can provide personalized, context-aware, and highly engaging customer experiences.

Key Features

  • Simple agent setup: A fully managed few-step setup process to create and deploy the agents.
  • Tools orchestration: Orchestrate several tools and services to address complex workflows and automate conversations.
  • Multi-turn chat experience: Engage in dynamic, multi-turn dialogues with more human-like interactions.
  • Context retention: Ask follow-up questions, because agents remember conversation context across turns for personalized and consistent interactions.
  • Custom instructions: Guide the agent's behavior with added instructions.
  • Guardrails: Have the agent help identify and apply content moderation, and help identify and protect against prompt injection (PI) and personally identifiable information (PII) at its endpoints.
  • Human-in-the-loop: Optional feature for real-time monitoring and human intervention.
  • Scalability and security: Get OCI's inherent secure and scalable infrastructure.
In Generative AI Agents, depending on the use case, you can empower each agent with one or more of the following tools:
Ready-to-use SQL Tool
Converts natural language queries into SQL statements and can run the SQL commands to generate responses against a connected database. Learn about Managing SQL tools.
Ready-to-use RAG Tool
Retrieves information from one or more knowledge bases and aims to respond with relevant and context-aware information in natural language. Learn about Managing RAG tools.
Custom Function Calling Tool
Calls functions that you define to expand the features that the agent covers. You can set up the agent to demand an action in natural language. The agent can run the related function and respond depending on what the function does. Learn about Managing function calling tools.

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. Example use cases include:

  • Customer Support: In the customer service industry, RAG agents can retrieve information from a company’s knowledge base to provide contextually relevant answers to customer inquiries, to help reduce response times.
  • Legal Research: Legal professionals can use RAG agents to assist in searching precedents and case law from vast legal databases.
  • Financial Analysis: In finance, RAG agents can analyze large volumes of financial data, reports, and news.
  • Educational Tutoring: RAG agents can function as personal tutors, providing students with explanations, resources, and answers to questions by accessing educational content.
  • Content Creation: In media and content creation, RAG agents can help writers and journalists by pulling information from specific topics and drafting suggestions.
  • 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 potentially optimize operations and help 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, to support 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, to support personalized travel advice and itineraries.

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
Japan Central (Osaka) (New) Osaka ap-osaka-1 KIX
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 select Analytics & AI. Under AI Services, select Generative AI Agents.

Was this article helpful?