Managing RAG Tools in Generative AI Agents

A RAG tool in Generative AI Agents retrieves information from one or more knowledge bases and aims to respond with relevant and context-aware information in natural language.

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)
  • Includes content moderation options for input and output
  • 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.

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.
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
Before You Begin

Before you create a RAG tool, ensure that you review the guidelines for the data that you plan to provide to the agent and complete any tasks that are required.

Manage RAG Tools

If you have manage permissions to genai-agent-family, you can manage the RAG tools. See the following links for managing each tool: