Updating a RAG Tool in Generative AI Agents
-
On the Agents list page, select the agent that has the RAG tool you want to update.
If you need help finding the list page, see Listing Agents
-
In the Tools list of the agent, select the name of the RAG tool that you want to update.
A RAG tool is identified by the type
RAG_TOOL_CONFIG. - On the tool details page, select Edit.
- Update the RAG tool name or description.
- Update the custom instructions.
-
Add knowledge bases
Either select a knowledge base from the listed knowledge bases or create one. 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. -
Generation LLM: Select a model for the RAG tool from the following options:
-
- Default: A model used by the Generative AI Agents service
- Generative AI model: A model hosted in the Generative AI service
- Generative AI endpoint: A model hosted on a dedicated AI cluster endpoint in the Generative AI service
Tip
For guidance and a list of supported models and regions, see the Model Selection in Generative AI Agents page. -
- If you selected Generative AI model select a model. Based on the region that you're creating the RAG tool in, the list of models populates.
- If you selected Generative AI endpoint, select the Generative AI endpoint compartment and the endpoint.
- (Optional)
Update the default hyperparameters.
Hyperparameters and their default values differ by model type.
- Select Save changes.
- (Optional) Select Add tags to add tags to this tool. Then, select the Tags tab to view and manage the defined and free-form tags for this tool.