Oracle Cloud Infrastructure Documentation

Creating a RAG Tool in Generative AI Agents

In Generative AI Agents, each agent must have one or more tools. You can create an agent's tool during or after creating the agent. For both options, creating a tool has the same steps. This section shows you the steps to create a RAG tool.

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.

Creating a RAG Tool

  1. Select Create tool.
  2. Select RAG.
  3. (Optional) Enter the following information:
    • Name: A name that starts with a letter or underscore, followed by letters, numbers, hyphens, or underscores. The length can be from 1 to 255 characters.
    • Description: An optional description.
  4. (Optional) For Custom instructions, enter an instruction in natural language for the agent's responses. For example, ask the agent to answer prompts in a certain way.
  5. In the Add knowledge bases section, select a knowledge base from the listed knowledge bases or create one. Change the compartment if the knowledge base that you want to use is in another compartment. If you need help creating a knowledge base, see Creating a Knowledge Base in Generative AI Agents.
    See Limits and Limitations for Generative AI Agents for the number of knowledge bases that you can have for RAG tool.
  6. Select Create tool.
Tip

Perform one of the following actions:

  • If you're creating an agent, go back to Creating an Agent in Generative AI Agents to create another tool or an endpoint.
  • If you added the tool to an existing agent, after the tool is active, from the agent's detail page, select Launch chat to chat with the agent using this tool.
  • If you created the agent without an endpoint, when you're ready to use the agent, create an endpoint for this agent.